Add Zbkb command lines to the bswap/bitreverse test.
+++ /dev/null
-; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
-; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
-; RUN: | FileCheck %s -check-prefix=RV32I
-; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
-; RUN: | FileCheck %s -check-prefix=RV64I
-; RUN: llc -mtriple=riscv32 -mattr=+zbb -verify-machineinstrs < %s \
-; RUN: | FileCheck %s -check-prefix=RV32ZBB
-; RUN: llc -mtriple=riscv64 -mattr=+zbb -verify-machineinstrs < %s \
-; RUN: | FileCheck %s -check-prefix=RV64ZBB
-
-declare i16 @llvm.bswap.i16(i16)
-declare i32 @llvm.bswap.i32(i32)
-declare i64 @llvm.bswap.i64(i64)
-declare i8 @llvm.bitreverse.i8(i8)
-declare i16 @llvm.bitreverse.i16(i16)
-declare i32 @llvm.bitreverse.i32(i32)
-declare i64 @llvm.bitreverse.i64(i64)
-declare i8 @llvm.cttz.i8(i8, i1)
-declare i16 @llvm.cttz.i16(i16, i1)
-declare i32 @llvm.cttz.i32(i32, i1)
-declare i64 @llvm.cttz.i64(i64, i1)
-declare i32 @llvm.ctlz.i32(i32, i1)
-declare i32 @llvm.ctpop.i32(i32)
-declare i64 @llvm.ctpop.i64(i64)
-
-define i16 @test_bswap_i16(i16 %a) nounwind {
-; RV32I-LABEL: test_bswap_i16:
-; RV32I: # %bb.0:
-; RV32I-NEXT: slli a1, a0, 8
-; RV32I-NEXT: slli a0, a0, 16
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bswap_i16:
-; RV64I: # %bb.0:
-; RV64I-NEXT: slli a1, a0, 8
-; RV64I-NEXT: slli a0, a0, 48
-; RV64I-NEXT: srli a0, a0, 56
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bswap_i16:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: rev8 a0, a0
-; RV32ZBB-NEXT: srli a0, a0, 16
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bswap_i16:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: rev8 a0, a0
-; RV64ZBB-NEXT: srli a0, a0, 48
-; RV64ZBB-NEXT: ret
- %tmp = call i16 @llvm.bswap.i16(i16 %a)
- ret i16 %tmp
-}
-
-define i32 @test_bswap_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_bswap_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: lui a2, 16
-; RV32I-NEXT: addi a2, a2, -256
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: srli a2, a0, 24
-; RV32I-NEXT: or a1, a1, a2
-; RV32I-NEXT: slli a2, a0, 8
-; RV32I-NEXT: lui a3, 4080
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: slli a0, a0, 24
-; RV32I-NEXT: or a0, a0, a2
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bswap_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srliw a1, a0, 8
-; RV64I-NEXT: lui a2, 16
-; RV64I-NEXT: addiw a2, a2, -256
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: srliw a2, a0, 24
-; RV64I-NEXT: or a1, a1, a2
-; RV64I-NEXT: slli a2, a0, 8
-; RV64I-NEXT: lui a3, 4080
-; RV64I-NEXT: and a2, a2, a3
-; RV64I-NEXT: slliw a0, a0, 24
-; RV64I-NEXT: or a0, a0, a2
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bswap_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: rev8 a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bswap_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: rev8 a0, a0
-; RV64ZBB-NEXT: srli a0, a0, 32
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.bswap.i32(i32 %a)
- ret i32 %tmp
-}
-
-define i64 @test_bswap_i64(i64 %a) nounwind {
-; RV32I-LABEL: test_bswap_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a2, a1, 8
-; RV32I-NEXT: lui a3, 16
-; RV32I-NEXT: addi a3, a3, -256
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: srli a4, a1, 24
-; RV32I-NEXT: or a2, a2, a4
-; RV32I-NEXT: slli a4, a1, 8
-; RV32I-NEXT: lui a5, 4080
-; RV32I-NEXT: and a4, a4, a5
-; RV32I-NEXT: slli a1, a1, 24
-; RV32I-NEXT: or a1, a1, a4
-; RV32I-NEXT: or a2, a1, a2
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: and a1, a1, a3
-; RV32I-NEXT: srli a3, a0, 24
-; RV32I-NEXT: or a1, a1, a3
-; RV32I-NEXT: slli a3, a0, 8
-; RV32I-NEXT: and a3, a3, a5
-; RV32I-NEXT: slli a0, a0, 24
-; RV32I-NEXT: or a0, a0, a3
-; RV32I-NEXT: or a1, a0, a1
-; RV32I-NEXT: mv a0, a2
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bswap_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 24
-; RV64I-NEXT: lui a2, 4080
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: srli a2, a0, 8
-; RV64I-NEXT: li a3, 255
-; RV64I-NEXT: slli a4, a3, 24
-; RV64I-NEXT: and a2, a2, a4
-; RV64I-NEXT: or a1, a2, a1
-; RV64I-NEXT: srli a2, a0, 40
-; RV64I-NEXT: lui a4, 16
-; RV64I-NEXT: addiw a4, a4, -256
-; RV64I-NEXT: and a2, a2, a4
-; RV64I-NEXT: srli a4, a0, 56
-; RV64I-NEXT: or a2, a2, a4
-; RV64I-NEXT: or a1, a1, a2
-; RV64I-NEXT: slli a2, a0, 24
-; RV64I-NEXT: slli a4, a3, 40
-; RV64I-NEXT: and a2, a2, a4
-; RV64I-NEXT: srliw a4, a0, 24
-; RV64I-NEXT: slli a4, a4, 32
-; RV64I-NEXT: or a2, a2, a4
-; RV64I-NEXT: slli a4, a0, 40
-; RV64I-NEXT: slli a3, a3, 48
-; RV64I-NEXT: and a3, a4, a3
-; RV64I-NEXT: slli a0, a0, 56
-; RV64I-NEXT: or a0, a0, a3
-; RV64I-NEXT: or a0, a0, a2
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bswap_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: rev8 a2, a1
-; RV32ZBB-NEXT: rev8 a1, a0
-; RV32ZBB-NEXT: mv a0, a2
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bswap_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: rev8 a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i64 @llvm.bswap.i64(i64 %a)
- ret i64 %tmp
-}
-
-define i8 @test_bitreverse_i8(i8 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_i8:
-; RV32I: # %bb.0:
-; RV32I-NEXT: andi a1, a0, 15
-; RV32I-NEXT: slli a1, a1, 4
-; RV32I-NEXT: slli a0, a0, 24
-; RV32I-NEXT: srli a0, a0, 28
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: andi a1, a0, 51
-; RV32I-NEXT: slli a1, a1, 2
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: andi a0, a0, 51
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: andi a1, a0, 85
-; RV32I-NEXT: slli a1, a1, 1
-; RV32I-NEXT: srli a0, a0, 1
-; RV32I-NEXT: andi a0, a0, 85
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_i8:
-; RV64I: # %bb.0:
-; RV64I-NEXT: andi a1, a0, 15
-; RV64I-NEXT: slli a1, a1, 4
-; RV64I-NEXT: slli a0, a0, 56
-; RV64I-NEXT: srli a0, a0, 60
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: andi a1, a0, 51
-; RV64I-NEXT: slli a1, a1, 2
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: andi a0, a0, 51
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: andi a1, a0, 85
-; RV64I-NEXT: slli a1, a1, 1
-; RV64I-NEXT: srli a0, a0, 1
-; RV64I-NEXT: andi a0, a0, 85
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_i8:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: andi a1, a0, 15
-; RV32ZBB-NEXT: slli a1, a1, 4
-; RV32ZBB-NEXT: slli a0, a0, 24
-; RV32ZBB-NEXT: srli a0, a0, 28
-; RV32ZBB-NEXT: or a0, a0, a1
-; RV32ZBB-NEXT: andi a1, a0, 51
-; RV32ZBB-NEXT: slli a1, a1, 2
-; RV32ZBB-NEXT: srli a0, a0, 2
-; RV32ZBB-NEXT: andi a0, a0, 51
-; RV32ZBB-NEXT: or a0, a0, a1
-; RV32ZBB-NEXT: andi a1, a0, 85
-; RV32ZBB-NEXT: slli a1, a1, 1
-; RV32ZBB-NEXT: srli a0, a0, 1
-; RV32ZBB-NEXT: andi a0, a0, 85
-; RV32ZBB-NEXT: or a0, a0, a1
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_i8:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: andi a1, a0, 15
-; RV64ZBB-NEXT: slli a1, a1, 4
-; RV64ZBB-NEXT: slli a0, a0, 56
-; RV64ZBB-NEXT: srli a0, a0, 60
-; RV64ZBB-NEXT: or a0, a0, a1
-; RV64ZBB-NEXT: andi a1, a0, 51
-; RV64ZBB-NEXT: slli a1, a1, 2
-; RV64ZBB-NEXT: srli a0, a0, 2
-; RV64ZBB-NEXT: andi a0, a0, 51
-; RV64ZBB-NEXT: or a0, a0, a1
-; RV64ZBB-NEXT: andi a1, a0, 85
-; RV64ZBB-NEXT: slli a1, a1, 1
-; RV64ZBB-NEXT: srli a0, a0, 1
-; RV64ZBB-NEXT: andi a0, a0, 85
-; RV64ZBB-NEXT: or a0, a0, a1
-; RV64ZBB-NEXT: ret
- %tmp = call i8 @llvm.bitreverse.i8(i8 %a)
- ret i8 %tmp
-}
-
-define i16 @test_bitreverse_i16(i16 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_i16:
-; RV32I: # %bb.0:
-; RV32I-NEXT: slli a1, a0, 8
-; RV32I-NEXT: slli a0, a0, 16
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: lui a2, 1
-; RV32I-NEXT: addi a2, a2, -241
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: lui a2, 3
-; RV32I-NEXT: addi a2, a2, 819
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 5
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_i16:
-; RV64I: # %bb.0:
-; RV64I-NEXT: slli a1, a0, 8
-; RV64I-NEXT: slli a0, a0, 48
-; RV64I-NEXT: srli a0, a0, 56
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: lui a2, 1
-; RV64I-NEXT: addiw a2, a2, -241
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: lui a2, 3
-; RV64I-NEXT: addiw a2, a2, 819
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 5
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_i16:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: rev8 a0, a0
-; RV32ZBB-NEXT: srli a1, a0, 12
-; RV32ZBB-NEXT: lui a2, 15
-; RV32ZBB-NEXT: addi a2, a2, 240
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: srli a0, a0, 20
-; RV32ZBB-NEXT: andi a0, a0, -241
-; RV32ZBB-NEXT: or a0, a0, a1
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: lui a2, 3
-; RV32ZBB-NEXT: addi a2, a2, 819
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: lui a2, 5
-; RV32ZBB-NEXT: addi a2, a2, 1365
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_i16:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: rev8 a0, a0
-; RV64ZBB-NEXT: srli a1, a0, 44
-; RV64ZBB-NEXT: lui a2, 15
-; RV64ZBB-NEXT: addiw a2, a2, 240
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: srli a0, a0, 52
-; RV64ZBB-NEXT: andi a0, a0, -241
-; RV64ZBB-NEXT: or a0, a0, a1
-; RV64ZBB-NEXT: srli a1, a0, 2
-; RV64ZBB-NEXT: lui a2, 3
-; RV64ZBB-NEXT: addiw a2, a2, 819
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 2
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 1
-; RV64ZBB-NEXT: lui a2, 5
-; RV64ZBB-NEXT: addiw a2, a2, 1365
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 1
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i16 @llvm.bitreverse.i16(i16 %a)
- ret i16 %tmp
-}
-
-define i32 @test_bitreverse_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: lui a2, 16
-; RV32I-NEXT: addi a2, a2, -256
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: srli a2, a0, 24
-; RV32I-NEXT: or a1, a1, a2
-; RV32I-NEXT: slli a2, a0, 8
-; RV32I-NEXT: lui a3, 4080
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: slli a0, a0, 24
-; RV32I-NEXT: or a0, a0, a2
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: lui a2, 61681
-; RV32I-NEXT: addi a2, a2, -241
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: lui a2, 209715
-; RV32I-NEXT: addi a2, a2, 819
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srliw a1, a0, 8
-; RV64I-NEXT: lui a2, 16
-; RV64I-NEXT: addiw a2, a2, -256
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: srliw a2, a0, 24
-; RV64I-NEXT: or a1, a1, a2
-; RV64I-NEXT: slli a2, a0, 8
-; RV64I-NEXT: lui a3, 4080
-; RV64I-NEXT: and a2, a2, a3
-; RV64I-NEXT: slliw a0, a0, 24
-; RV64I-NEXT: or a0, a0, a2
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: lui a2, 61681
-; RV64I-NEXT: addiw a2, a2, -241
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: lui a2, 209715
-; RV64I-NEXT: addiw a2, a2, 819
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: rev8 a0, a0
-; RV32ZBB-NEXT: srli a1, a0, 4
-; RV32ZBB-NEXT: lui a2, 61681
-; RV32ZBB-NEXT: addi a2, a2, -241
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: lui a2, 209715
-; RV32ZBB-NEXT: addi a2, a2, 819
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: lui a2, 349525
-; RV32ZBB-NEXT: addi a2, a2, 1365
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: rev8 a0, a0
-; RV64ZBB-NEXT: srli a1, a0, 36
-; RV64ZBB-NEXT: lui a2, 61681
-; RV64ZBB-NEXT: addiw a2, a2, -241
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: srli a0, a0, 28
-; RV64ZBB-NEXT: lui a2, 986895
-; RV64ZBB-NEXT: addiw a2, a2, 240
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: sext.w a0, a0
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 2
-; RV64ZBB-NEXT: lui a2, 209715
-; RV64ZBB-NEXT: addiw a2, a2, 819
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 2
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 1
-; RV64ZBB-NEXT: lui a2, 349525
-; RV64ZBB-NEXT: addiw a2, a2, 1365
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 1
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.bitreverse.i32(i32 %a)
- ret i32 %tmp
-}
-
-define i64 @test_bitreverse_i64(i64 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a2, a1, 8
-; RV32I-NEXT: lui a3, 16
-; RV32I-NEXT: addi a3, a3, -256
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: srli a4, a1, 24
-; RV32I-NEXT: or a2, a2, a4
-; RV32I-NEXT: slli a4, a1, 8
-; RV32I-NEXT: lui a5, 4080
-; RV32I-NEXT: and a4, a4, a5
-; RV32I-NEXT: slli a1, a1, 24
-; RV32I-NEXT: or a1, a1, a4
-; RV32I-NEXT: or a1, a1, a2
-; RV32I-NEXT: srli a2, a1, 4
-; RV32I-NEXT: lui a4, 61681
-; RV32I-NEXT: addi a4, a4, -241
-; RV32I-NEXT: and a2, a2, a4
-; RV32I-NEXT: and a1, a1, a4
-; RV32I-NEXT: slli a1, a1, 4
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: srli a2, a1, 2
-; RV32I-NEXT: lui a6, 209715
-; RV32I-NEXT: addi a6, a6, 819
-; RV32I-NEXT: and a2, a2, a6
-; RV32I-NEXT: and a1, a1, a6
-; RV32I-NEXT: slli a1, a1, 2
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: srli a2, a1, 1
-; RV32I-NEXT: lui a7, 349525
-; RV32I-NEXT: addi a7, a7, 1365
-; RV32I-NEXT: and a2, a2, a7
-; RV32I-NEXT: and a1, a1, a7
-; RV32I-NEXT: slli a1, a1, 1
-; RV32I-NEXT: or a2, a2, a1
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: and a1, a1, a3
-; RV32I-NEXT: srli a3, a0, 24
-; RV32I-NEXT: or a1, a1, a3
-; RV32I-NEXT: slli a3, a0, 8
-; RV32I-NEXT: and a3, a3, a5
-; RV32I-NEXT: slli a0, a0, 24
-; RV32I-NEXT: or a0, a0, a3
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: and a1, a1, a4
-; RV32I-NEXT: and a0, a0, a4
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: and a1, a1, a6
-; RV32I-NEXT: and a0, a0, a6
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: and a1, a1, a7
-; RV32I-NEXT: and a0, a0, a7
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a1, a1, a0
-; RV32I-NEXT: mv a0, a2
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 24
-; RV64I-NEXT: lui a2, 4080
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: srli a2, a0, 8
-; RV64I-NEXT: li a3, 255
-; RV64I-NEXT: slli a4, a3, 24
-; RV64I-NEXT: and a2, a2, a4
-; RV64I-NEXT: or a1, a2, a1
-; RV64I-NEXT: srli a2, a0, 40
-; RV64I-NEXT: lui a4, 16
-; RV64I-NEXT: addiw a4, a4, -256
-; RV64I-NEXT: and a2, a2, a4
-; RV64I-NEXT: srli a4, a0, 56
-; RV64I-NEXT: or a2, a2, a4
-; RV64I-NEXT: or a1, a1, a2
-; RV64I-NEXT: slli a2, a0, 24
-; RV64I-NEXT: slli a4, a3, 40
-; RV64I-NEXT: and a2, a2, a4
-; RV64I-NEXT: srliw a4, a0, 24
-; RV64I-NEXT: slli a4, a4, 32
-; RV64I-NEXT: or a2, a2, a4
-; RV64I-NEXT: slli a4, a0, 40
-; RV64I-NEXT: slli a3, a3, 48
-; RV64I-NEXT: and a3, a4, a3
-; RV64I-NEXT: slli a0, a0, 56
-; RV64I-NEXT: or a0, a0, a3
-; RV64I-NEXT: lui a3, %hi(.LCPI6_0)
-; RV64I-NEXT: ld a3, %lo(.LCPI6_0)(a3)
-; RV64I-NEXT: or a0, a0, a2
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: and a1, a1, a3
-; RV64I-NEXT: and a0, a0, a3
-; RV64I-NEXT: lui a2, %hi(.LCPI6_1)
-; RV64I-NEXT: ld a2, %lo(.LCPI6_1)(a2)
-; RV64I-NEXT: slli a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a2, %hi(.LCPI6_2)
-; RV64I-NEXT: ld a2, %lo(.LCPI6_2)(a2)
-; RV64I-NEXT: slli a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: rev8 a1, a1
-; RV32ZBB-NEXT: srli a2, a1, 4
-; RV32ZBB-NEXT: lui a3, 61681
-; RV32ZBB-NEXT: addi a3, a3, -241
-; RV32ZBB-NEXT: and a2, a2, a3
-; RV32ZBB-NEXT: and a1, a1, a3
-; RV32ZBB-NEXT: slli a1, a1, 4
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: srli a2, a1, 2
-; RV32ZBB-NEXT: lui a4, 209715
-; RV32ZBB-NEXT: addi a4, a4, 819
-; RV32ZBB-NEXT: and a2, a2, a4
-; RV32ZBB-NEXT: and a1, a1, a4
-; RV32ZBB-NEXT: slli a1, a1, 2
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: srli a2, a1, 1
-; RV32ZBB-NEXT: lui a5, 349525
-; RV32ZBB-NEXT: addi a5, a5, 1365
-; RV32ZBB-NEXT: and a2, a2, a5
-; RV32ZBB-NEXT: and a1, a1, a5
-; RV32ZBB-NEXT: slli a1, a1, 1
-; RV32ZBB-NEXT: or a2, a2, a1
-; RV32ZBB-NEXT: rev8 a0, a0
-; RV32ZBB-NEXT: srli a1, a0, 4
-; RV32ZBB-NEXT: and a1, a1, a3
-; RV32ZBB-NEXT: and a0, a0, a3
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: and a1, a1, a4
-; RV32ZBB-NEXT: and a0, a0, a4
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: and a1, a1, a5
-; RV32ZBB-NEXT: and a0, a0, a5
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a1, a1, a0
-; RV32ZBB-NEXT: mv a0, a2
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI6_0)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI6_0)(a1)
-; RV64ZBB-NEXT: rev8 a0, a0
-; RV64ZBB-NEXT: srli a2, a0, 4
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI6_1)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI6_1)(a1)
-; RV64ZBB-NEXT: slli a0, a0, 4
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: srli a2, a0, 2
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI6_2)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI6_2)(a1)
-; RV64ZBB-NEXT: slli a0, a0, 2
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: srli a2, a0, 1
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: slli a0, a0, 1
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i64 @llvm.bitreverse.i64(i64 %a)
- ret i64 %tmp
-}
-
-define i16 @test_bswap_bitreverse_i16(i16 %a) nounwind {
-; RV32I-LABEL: test_bswap_bitreverse_i16:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: lui a2, 1
-; RV32I-NEXT: addi a2, a2, -241
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: lui a2, 3
-; RV32I-NEXT: addi a2, a2, 819
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 5
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bswap_bitreverse_i16:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: lui a2, 1
-; RV64I-NEXT: addiw a2, a2, -241
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: lui a2, 3
-; RV64I-NEXT: addiw a2, a2, 819
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 5
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bswap_bitreverse_i16:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: srli a1, a0, 4
-; RV32ZBB-NEXT: lui a2, 1
-; RV32ZBB-NEXT: addi a2, a2, -241
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: lui a2, 3
-; RV32ZBB-NEXT: addi a2, a2, 819
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: lui a2, 5
-; RV32ZBB-NEXT: addi a2, a2, 1365
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bswap_bitreverse_i16:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: srli a1, a0, 4
-; RV64ZBB-NEXT: lui a2, 1
-; RV64ZBB-NEXT: addiw a2, a2, -241
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 4
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 2
-; RV64ZBB-NEXT: lui a2, 3
-; RV64ZBB-NEXT: addiw a2, a2, 819
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 2
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 1
-; RV64ZBB-NEXT: lui a2, 5
-; RV64ZBB-NEXT: addiw a2, a2, 1365
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 1
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i16 @llvm.bswap.i16(i16 %a)
- %tmp2 = call i16 @llvm.bitreverse.i16(i16 %tmp)
- ret i16 %tmp2
-}
-
-define i32 @test_bswap_bitreverse_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_bswap_bitreverse_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: lui a2, 61681
-; RV32I-NEXT: addi a2, a2, -241
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: lui a2, 209715
-; RV32I-NEXT: addi a2, a2, 819
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bswap_bitreverse_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: lui a2, 61681
-; RV64I-NEXT: addiw a2, a2, -241
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: lui a2, 209715
-; RV64I-NEXT: addiw a2, a2, 819
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bswap_bitreverse_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: srli a1, a0, 4
-; RV32ZBB-NEXT: lui a2, 61681
-; RV32ZBB-NEXT: addi a2, a2, -241
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: lui a2, 209715
-; RV32ZBB-NEXT: addi a2, a2, 819
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: lui a2, 349525
-; RV32ZBB-NEXT: addi a2, a2, 1365
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bswap_bitreverse_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: srli a1, a0, 4
-; RV64ZBB-NEXT: lui a2, 61681
-; RV64ZBB-NEXT: addiw a2, a2, -241
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 4
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 2
-; RV64ZBB-NEXT: lui a2, 209715
-; RV64ZBB-NEXT: addiw a2, a2, 819
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 2
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 1
-; RV64ZBB-NEXT: lui a2, 349525
-; RV64ZBB-NEXT: addiw a2, a2, 1365
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 1
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.bswap.i32(i32 %a)
- %tmp2 = call i32 @llvm.bitreverse.i32(i32 %tmp)
- ret i32 %tmp2
-}
-
-define i64 @test_bswap_bitreverse_i64(i64 %a) nounwind {
-; RV32I-LABEL: test_bswap_bitreverse_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a2, a0, 4
-; RV32I-NEXT: lui a3, 61681
-; RV32I-NEXT: addi a3, a3, -241
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: and a0, a0, a3
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a2, a0
-; RV32I-NEXT: srli a2, a0, 2
-; RV32I-NEXT: lui a4, 209715
-; RV32I-NEXT: addi a4, a4, 819
-; RV32I-NEXT: and a2, a2, a4
-; RV32I-NEXT: and a0, a0, a4
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a2, a0
-; RV32I-NEXT: srli a2, a0, 1
-; RV32I-NEXT: lui a5, 349525
-; RV32I-NEXT: addi a5, a5, 1365
-; RV32I-NEXT: and a2, a2, a5
-; RV32I-NEXT: and a0, a0, a5
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a2, a0
-; RV32I-NEXT: srli a2, a1, 4
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: and a1, a1, a3
-; RV32I-NEXT: slli a1, a1, 4
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: srli a2, a1, 2
-; RV32I-NEXT: and a2, a2, a4
-; RV32I-NEXT: and a1, a1, a4
-; RV32I-NEXT: slli a1, a1, 2
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: srli a2, a1, 1
-; RV32I-NEXT: and a2, a2, a5
-; RV32I-NEXT: and a1, a1, a5
-; RV32I-NEXT: slli a1, a1, 1
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bswap_bitreverse_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: lui a1, %hi(.LCPI9_0)
-; RV64I-NEXT: ld a1, %lo(.LCPI9_0)(a1)
-; RV64I-NEXT: srli a2, a0, 4
-; RV64I-NEXT: and a2, a2, a1
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, %hi(.LCPI9_1)
-; RV64I-NEXT: ld a1, %lo(.LCPI9_1)(a1)
-; RV64I-NEXT: slli a0, a0, 4
-; RV64I-NEXT: or a0, a2, a0
-; RV64I-NEXT: srli a2, a0, 2
-; RV64I-NEXT: and a2, a2, a1
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, %hi(.LCPI9_2)
-; RV64I-NEXT: ld a1, %lo(.LCPI9_2)(a1)
-; RV64I-NEXT: slli a0, a0, 2
-; RV64I-NEXT: or a0, a2, a0
-; RV64I-NEXT: srli a2, a0, 1
-; RV64I-NEXT: and a2, a2, a1
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: slli a0, a0, 1
-; RV64I-NEXT: or a0, a2, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bswap_bitreverse_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: srli a2, a0, 4
-; RV32ZBB-NEXT: lui a3, 61681
-; RV32ZBB-NEXT: addi a3, a3, -241
-; RV32ZBB-NEXT: and a2, a2, a3
-; RV32ZBB-NEXT: and a0, a0, a3
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a2, a0
-; RV32ZBB-NEXT: srli a2, a0, 2
-; RV32ZBB-NEXT: lui a4, 209715
-; RV32ZBB-NEXT: addi a4, a4, 819
-; RV32ZBB-NEXT: and a2, a2, a4
-; RV32ZBB-NEXT: and a0, a0, a4
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a2, a0
-; RV32ZBB-NEXT: srli a2, a0, 1
-; RV32ZBB-NEXT: lui a5, 349525
-; RV32ZBB-NEXT: addi a5, a5, 1365
-; RV32ZBB-NEXT: and a2, a2, a5
-; RV32ZBB-NEXT: and a0, a0, a5
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a2, a0
-; RV32ZBB-NEXT: srli a2, a1, 4
-; RV32ZBB-NEXT: and a2, a2, a3
-; RV32ZBB-NEXT: and a1, a1, a3
-; RV32ZBB-NEXT: slli a1, a1, 4
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: srli a2, a1, 2
-; RV32ZBB-NEXT: and a2, a2, a4
-; RV32ZBB-NEXT: and a1, a1, a4
-; RV32ZBB-NEXT: slli a1, a1, 2
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: srli a2, a1, 1
-; RV32ZBB-NEXT: and a2, a2, a5
-; RV32ZBB-NEXT: and a1, a1, a5
-; RV32ZBB-NEXT: slli a1, a1, 1
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bswap_bitreverse_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI9_0)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI9_0)(a1)
-; RV64ZBB-NEXT: srli a2, a0, 4
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI9_1)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI9_1)(a1)
-; RV64ZBB-NEXT: slli a0, a0, 4
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: srli a2, a0, 2
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI9_2)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI9_2)(a1)
-; RV64ZBB-NEXT: slli a0, a0, 2
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: srli a2, a0, 1
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: slli a0, a0, 1
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i64 @llvm.bswap.i64(i64 %a)
- %tmp2 = call i64 @llvm.bitreverse.i64(i64 %tmp)
- ret i64 %tmp2
-}
-
-define i16 @test_bitreverse_bswap_i16(i16 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_bswap_i16:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: lui a2, 1
-; RV32I-NEXT: addi a2, a2, -241
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: lui a2, 3
-; RV32I-NEXT: addi a2, a2, 819
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 5
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_bswap_i16:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: lui a2, 1
-; RV64I-NEXT: addiw a2, a2, -241
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: lui a2, 3
-; RV64I-NEXT: addiw a2, a2, 819
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 5
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slli a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_bswap_i16:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: srli a1, a0, 4
-; RV32ZBB-NEXT: lui a2, 1
-; RV32ZBB-NEXT: addi a2, a2, -241
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: lui a2, 3
-; RV32ZBB-NEXT: addi a2, a2, 819
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: lui a2, 5
-; RV32ZBB-NEXT: addi a2, a2, 1365
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_bswap_i16:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: srli a1, a0, 4
-; RV64ZBB-NEXT: lui a2, 1
-; RV64ZBB-NEXT: addiw a2, a2, -241
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 4
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 2
-; RV64ZBB-NEXT: lui a2, 3
-; RV64ZBB-NEXT: addiw a2, a2, 819
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 2
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 1
-; RV64ZBB-NEXT: lui a2, 5
-; RV64ZBB-NEXT: addiw a2, a2, 1365
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slli a0, a0, 1
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i16 @llvm.bitreverse.i16(i16 %a)
- %tmp2 = call i16 @llvm.bswap.i16(i16 %tmp)
- ret i16 %tmp2
-}
-
-define i32 @test_bitreverse_bswap_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_bswap_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: lui a2, 61681
-; RV32I-NEXT: addi a2, a2, -241
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: lui a2, 209715
-; RV32I-NEXT: addi a2, a2, 819
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: and a0, a0, a2
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a1, a0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_bswap_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: lui a2, 61681
-; RV64I-NEXT: addiw a2, a2, -241
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 4
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: lui a2, 209715
-; RV64I-NEXT: addiw a2, a2, 819
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 2
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: slliw a0, a0, 1
-; RV64I-NEXT: or a0, a1, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_bswap_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: srli a1, a0, 4
-; RV32ZBB-NEXT: lui a2, 61681
-; RV32ZBB-NEXT: addi a2, a2, -241
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 2
-; RV32ZBB-NEXT: lui a2, 209715
-; RV32ZBB-NEXT: addi a2, a2, 819
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: srli a1, a0, 1
-; RV32ZBB-NEXT: lui a2, 349525
-; RV32ZBB-NEXT: addi a2, a2, 1365
-; RV32ZBB-NEXT: and a1, a1, a2
-; RV32ZBB-NEXT: and a0, a0, a2
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a1, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_bswap_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: srli a1, a0, 4
-; RV64ZBB-NEXT: lui a2, 61681
-; RV64ZBB-NEXT: addiw a2, a2, -241
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 4
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 2
-; RV64ZBB-NEXT: lui a2, 209715
-; RV64ZBB-NEXT: addiw a2, a2, 819
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 2
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: srli a1, a0, 1
-; RV64ZBB-NEXT: lui a2, 349525
-; RV64ZBB-NEXT: addiw a2, a2, 1365
-; RV64ZBB-NEXT: and a1, a1, a2
-; RV64ZBB-NEXT: and a0, a0, a2
-; RV64ZBB-NEXT: slliw a0, a0, 1
-; RV64ZBB-NEXT: or a0, a1, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.bitreverse.i32(i32 %a)
- %tmp2 = call i32 @llvm.bswap.i32(i32 %tmp)
- ret i32 %tmp2
-}
-
-define i64 @test_bitreverse_bswap_i64(i64 %a) nounwind {
-; RV32I-LABEL: test_bitreverse_bswap_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a2, a0, 4
-; RV32I-NEXT: lui a3, 61681
-; RV32I-NEXT: addi a3, a3, -241
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: and a0, a0, a3
-; RV32I-NEXT: slli a0, a0, 4
-; RV32I-NEXT: or a0, a2, a0
-; RV32I-NEXT: srli a2, a0, 2
-; RV32I-NEXT: lui a4, 209715
-; RV32I-NEXT: addi a4, a4, 819
-; RV32I-NEXT: and a2, a2, a4
-; RV32I-NEXT: and a0, a0, a4
-; RV32I-NEXT: slli a0, a0, 2
-; RV32I-NEXT: or a0, a2, a0
-; RV32I-NEXT: srli a2, a0, 1
-; RV32I-NEXT: lui a5, 349525
-; RV32I-NEXT: addi a5, a5, 1365
-; RV32I-NEXT: and a2, a2, a5
-; RV32I-NEXT: and a0, a0, a5
-; RV32I-NEXT: slli a0, a0, 1
-; RV32I-NEXT: or a0, a2, a0
-; RV32I-NEXT: srli a2, a1, 4
-; RV32I-NEXT: and a2, a2, a3
-; RV32I-NEXT: and a1, a1, a3
-; RV32I-NEXT: slli a1, a1, 4
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: srli a2, a1, 2
-; RV32I-NEXT: and a2, a2, a4
-; RV32I-NEXT: and a1, a1, a4
-; RV32I-NEXT: slli a1, a1, 2
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: srli a2, a1, 1
-; RV32I-NEXT: and a2, a2, a5
-; RV32I-NEXT: and a1, a1, a5
-; RV32I-NEXT: slli a1, a1, 1
-; RV32I-NEXT: or a1, a2, a1
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_bitreverse_bswap_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: lui a1, %hi(.LCPI12_0)
-; RV64I-NEXT: ld a1, %lo(.LCPI12_0)(a1)
-; RV64I-NEXT: srli a2, a0, 4
-; RV64I-NEXT: and a2, a2, a1
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, %hi(.LCPI12_1)
-; RV64I-NEXT: ld a1, %lo(.LCPI12_1)(a1)
-; RV64I-NEXT: slli a0, a0, 4
-; RV64I-NEXT: or a0, a2, a0
-; RV64I-NEXT: srli a2, a0, 2
-; RV64I-NEXT: and a2, a2, a1
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, %hi(.LCPI12_2)
-; RV64I-NEXT: ld a1, %lo(.LCPI12_2)(a1)
-; RV64I-NEXT: slli a0, a0, 2
-; RV64I-NEXT: or a0, a2, a0
-; RV64I-NEXT: srli a2, a0, 1
-; RV64I-NEXT: and a2, a2, a1
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: slli a0, a0, 1
-; RV64I-NEXT: or a0, a2, a0
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_bitreverse_bswap_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: srli a2, a0, 4
-; RV32ZBB-NEXT: lui a3, 61681
-; RV32ZBB-NEXT: addi a3, a3, -241
-; RV32ZBB-NEXT: and a2, a2, a3
-; RV32ZBB-NEXT: and a0, a0, a3
-; RV32ZBB-NEXT: slli a0, a0, 4
-; RV32ZBB-NEXT: or a0, a2, a0
-; RV32ZBB-NEXT: srli a2, a0, 2
-; RV32ZBB-NEXT: lui a4, 209715
-; RV32ZBB-NEXT: addi a4, a4, 819
-; RV32ZBB-NEXT: and a2, a2, a4
-; RV32ZBB-NEXT: and a0, a0, a4
-; RV32ZBB-NEXT: slli a0, a0, 2
-; RV32ZBB-NEXT: or a0, a2, a0
-; RV32ZBB-NEXT: srli a2, a0, 1
-; RV32ZBB-NEXT: lui a5, 349525
-; RV32ZBB-NEXT: addi a5, a5, 1365
-; RV32ZBB-NEXT: and a2, a2, a5
-; RV32ZBB-NEXT: and a0, a0, a5
-; RV32ZBB-NEXT: slli a0, a0, 1
-; RV32ZBB-NEXT: or a0, a2, a0
-; RV32ZBB-NEXT: srli a2, a1, 4
-; RV32ZBB-NEXT: and a2, a2, a3
-; RV32ZBB-NEXT: and a1, a1, a3
-; RV32ZBB-NEXT: slli a1, a1, 4
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: srli a2, a1, 2
-; RV32ZBB-NEXT: and a2, a2, a4
-; RV32ZBB-NEXT: and a1, a1, a4
-; RV32ZBB-NEXT: slli a1, a1, 2
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: srli a2, a1, 1
-; RV32ZBB-NEXT: and a2, a2, a5
-; RV32ZBB-NEXT: and a1, a1, a5
-; RV32ZBB-NEXT: slli a1, a1, 1
-; RV32ZBB-NEXT: or a1, a2, a1
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_bitreverse_bswap_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI12_0)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI12_0)(a1)
-; RV64ZBB-NEXT: srli a2, a0, 4
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI12_1)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI12_1)(a1)
-; RV64ZBB-NEXT: slli a0, a0, 4
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: srli a2, a0, 2
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: lui a1, %hi(.LCPI12_2)
-; RV64ZBB-NEXT: ld a1, %lo(.LCPI12_2)(a1)
-; RV64ZBB-NEXT: slli a0, a0, 2
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: srli a2, a0, 1
-; RV64ZBB-NEXT: and a2, a2, a1
-; RV64ZBB-NEXT: and a0, a0, a1
-; RV64ZBB-NEXT: slli a0, a0, 1
-; RV64ZBB-NEXT: or a0, a2, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i64 @llvm.bitreverse.i64(i64 %a)
- %tmp2 = call i64 @llvm.bswap.i64(i64 %tmp)
- ret i64 %tmp2
-}
-
-define i8 @test_cttz_i8(i8 %a) nounwind {
-; RV32I-LABEL: test_cttz_i8:
-; RV32I: # %bb.0:
-; RV32I-NEXT: andi a1, a0, 255
-; RV32I-NEXT: beqz a1, .LBB13_2
-; RV32I-NEXT: # %bb.1: # %cond.false
-; RV32I-NEXT: addi a1, a0, -1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: andi a1, a1, 85
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: andi a1, a0, 51
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: andi a0, a0, 51
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: andi a0, a0, 15
-; RV32I-NEXT: ret
-; RV32I-NEXT: .LBB13_2:
-; RV32I-NEXT: li a0, 8
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i8:
-; RV64I: # %bb.0:
-; RV64I-NEXT: andi a1, a0, 255
-; RV64I-NEXT: beqz a1, .LBB13_2
-; RV64I-NEXT: # %bb.1: # %cond.false
-; RV64I-NEXT: addi a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: andi a1, a1, 85
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: andi a1, a0, 51
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: andi a0, a0, 51
-; RV64I-NEXT: add a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: addw a0, a0, a1
-; RV64I-NEXT: andi a0, a0, 15
-; RV64I-NEXT: ret
-; RV64I-NEXT: .LBB13_2:
-; RV64I-NEXT: li a0, 8
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i8:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: ori a0, a0, 256
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i8:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ori a0, a0, 256
-; RV64ZBB-NEXT: ctz a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i8 @llvm.cttz.i8(i8 %a, i1 false)
- ret i8 %tmp
-}
-
-define i16 @test_cttz_i16(i16 %a) nounwind {
-; RV32I-LABEL: test_cttz_i16:
-; RV32I: # %bb.0:
-; RV32I-NEXT: slli a1, a0, 16
-; RV32I-NEXT: srli a1, a1, 16
-; RV32I-NEXT: beqz a1, .LBB14_2
-; RV32I-NEXT: # %bb.1: # %cond.false
-; RV32I-NEXT: addi a1, a0, -1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 5
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 3
-; RV32I-NEXT: addi a1, a1, 819
-; RV32I-NEXT: and a2, a0, a1
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: add a0, a2, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 1
-; RV32I-NEXT: addi a1, a1, -241
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: slli a1, a0, 8
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: slli a0, a0, 19
-; RV32I-NEXT: srli a0, a0, 27
-; RV32I-NEXT: ret
-; RV32I-NEXT: .LBB14_2:
-; RV32I-NEXT: li a0, 16
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i16:
-; RV64I: # %bb.0:
-; RV64I-NEXT: slli a1, a0, 48
-; RV64I-NEXT: srli a1, a1, 48
-; RV64I-NEXT: beqz a1, .LBB14_2
-; RV64I-NEXT: # %bb.1: # %cond.false
-; RV64I-NEXT: addi a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 5
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: lui a1, 3
-; RV64I-NEXT: addiw a1, a1, 819
-; RV64I-NEXT: and a2, a0, a1
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: add a0, a2, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: lui a1, 1
-; RV64I-NEXT: addiw a1, a1, -241
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: slliw a1, a0, 8
-; RV64I-NEXT: addw a0, a1, a0
-; RV64I-NEXT: slli a0, a0, 51
-; RV64I-NEXT: srli a0, a0, 59
-; RV64I-NEXT: ret
-; RV64I-NEXT: .LBB14_2:
-; RV64I-NEXT: li a0, 16
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i16:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: lui a1, 16
-; RV32ZBB-NEXT: or a0, a0, a1
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i16:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: lui a1, 16
-; RV64ZBB-NEXT: or a0, a0, a1
-; RV64ZBB-NEXT: ctz a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i16 @llvm.cttz.i16(i16 %a, i1 false)
- ret i16 %tmp
-}
-
-define i32 @test_cttz_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_cttz_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: beqz a0, .LBB15_2
-; RV32I-NEXT: # %bb.1: # %cond.false
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: addi a1, a0, -1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi a1, a1, 819
-; RV32I-NEXT: and a2, a0, a1
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: add a0, a2, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi a1, a1, -241
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi a1, a1, 257
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 16
-; RV32I-NEXT: ret
-; RV32I-NEXT: .LBB15_2:
-; RV32I-NEXT: li a0, 32
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: sext.w a1, a0
-; RV64I-NEXT: beqz a1, .LBB15_2
-; RV64I-NEXT: # %bb.1: # %cond.false
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: addiw a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: subw a0, a0, a1
-; RV64I-NEXT: lui a1, 209715
-; RV64I-NEXT: addiw a1, a1, 819
-; RV64I-NEXT: and a2, a0, a1
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: add a0, a2, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: lui a1, 61681
-; RV64I-NEXT: addiw a1, a1, -241
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, 4112
-; RV64I-NEXT: addiw a1, a1, 257
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srliw a0, a0, 24
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-; RV64I-NEXT: .LBB15_2:
-; RV64I-NEXT: li a0, 32
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ctzw a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.cttz.i32(i32 %a, i1 false)
- ret i32 %tmp
-}
-
-define i32 @test_ctlz_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_ctlz_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: beqz a0, .LBB16_2
-; RV32I-NEXT: # %bb.1: # %cond.false
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 16
-; RV32I-NEXT: or a0, a0, a1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi a1, a1, 819
-; RV32I-NEXT: and a2, a0, a1
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: add a0, a2, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi a1, a1, -241
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi a1, a1, 257
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 16
-; RV32I-NEXT: ret
-; RV32I-NEXT: .LBB16_2:
-; RV32I-NEXT: li a0, 32
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_ctlz_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: sext.w a1, a0
-; RV64I-NEXT: beqz a1, .LBB16_2
-; RV64I-NEXT: # %bb.1: # %cond.false
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: srliw a1, a0, 1
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: srliw a1, a0, 2
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: srliw a1, a0, 4
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: srliw a1, a0, 8
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: srliw a1, a0, 16
-; RV64I-NEXT: or a0, a0, a1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: subw a0, a0, a1
-; RV64I-NEXT: lui a1, 209715
-; RV64I-NEXT: addiw a1, a1, 819
-; RV64I-NEXT: and a2, a0, a1
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: add a0, a2, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: lui a1, 61681
-; RV64I-NEXT: addiw a1, a1, -241
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, 4112
-; RV64I-NEXT: addiw a1, a1, 257
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srliw a0, a0, 24
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-; RV64I-NEXT: .LBB16_2:
-; RV64I-NEXT: li a0, 32
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_ctlz_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: clz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_ctlz_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: clzw a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.ctlz.i32(i32 %a, i1 false)
- ret i32 %tmp
-}
-
-define i64 @test_cttz_i64(i64 %a) nounwind {
-; RV32I-LABEL: test_cttz_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -32
-; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s5, 4(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s6, 0(sp) # 4-byte Folded Spill
-; RV32I-NEXT: mv s1, a1
-; RV32I-NEXT: mv s2, a0
-; RV32I-NEXT: addi a0, a0, -1
-; RV32I-NEXT: not a1, s2
-; RV32I-NEXT: and a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi s4, a2, 1365
-; RV32I-NEXT: and a1, a1, s4
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi s5, a1, 819
-; RV32I-NEXT: and a1, a0, s5
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, s5
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi s6, a1, -241
-; RV32I-NEXT: and a0, a0, s6
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi s3, a1, 257
-; RV32I-NEXT: mv a1, s3
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: mv s0, a0
-; RV32I-NEXT: addi a0, s1, -1
-; RV32I-NEXT: not a1, s1
-; RV32I-NEXT: and a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: and a1, a1, s4
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: and a1, a0, s5
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, s5
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: and a0, a0, s6
-; RV32I-NEXT: mv a1, s3
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: bnez s2, .LBB17_2
-; RV32I-NEXT: # %bb.1:
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: addi a0, a0, 32
-; RV32I-NEXT: j .LBB17_3
-; RV32I-NEXT: .LBB17_2:
-; RV32I-NEXT: srli a0, s0, 24
-; RV32I-NEXT: .LBB17_3:
-; RV32I-NEXT: li a1, 0
-; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s6, 0(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 32
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: beqz a0, .LBB17_2
-; RV64I-NEXT: # %bb.1: # %cond.false
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: addi a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, %hi(.LCPI17_0)
-; RV64I-NEXT: ld a1, %lo(.LCPI17_0)(a1)
-; RV64I-NEXT: lui a2, %hi(.LCPI17_1)
-; RV64I-NEXT: ld a2, %lo(.LCPI17_1)(a2)
-; RV64I-NEXT: srli a3, a0, 1
-; RV64I-NEXT: and a1, a3, a1
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: and a1, a0, a2
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a2, %hi(.LCPI17_2)
-; RV64I-NEXT: ld a2, %lo(.LCPI17_2)(a2)
-; RV64I-NEXT: add a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a1, %hi(.LCPI17_3)
-; RV64I-NEXT: ld a1, %lo(.LCPI17_3)(a1)
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srli a0, a0, 56
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-; RV64I-NEXT: .LBB17_2:
-; RV64I-NEXT: li a0, 64
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: bnez a0, .LBB17_2
-; RV32ZBB-NEXT: # %bb.1:
-; RV32ZBB-NEXT: ctz a0, a1
-; RV32ZBB-NEXT: addi a0, a0, 32
-; RV32ZBB-NEXT: li a1, 0
-; RV32ZBB-NEXT: ret
-; RV32ZBB-NEXT: .LBB17_2:
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: li a1, 0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ctz a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i64 @llvm.cttz.i64(i64 %a, i1 false)
- ret i64 %tmp
-}
-
-define i8 @test_cttz_i8_zero_undef(i8 %a) nounwind {
-; RV32I-LABEL: test_cttz_i8_zero_undef:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi a1, a0, -1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: andi a1, a1, 85
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: andi a1, a0, 51
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: andi a0, a0, 51
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: andi a0, a0, 15
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i8_zero_undef:
-; RV64I: # %bb.0:
-; RV64I-NEXT: addi a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: andi a1, a1, 85
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: andi a1, a0, 51
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: andi a0, a0, 51
-; RV64I-NEXT: add a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: addw a0, a0, a1
-; RV64I-NEXT: andi a0, a0, 15
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i8_zero_undef:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i8_zero_undef:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ctz a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i8 @llvm.cttz.i8(i8 %a, i1 true)
- ret i8 %tmp
-}
-
-define i16 @test_cttz_i16_zero_undef(i16 %a) nounwind {
-; RV32I-LABEL: test_cttz_i16_zero_undef:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi a1, a0, -1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 5
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 3
-; RV32I-NEXT: addi a1, a1, 819
-; RV32I-NEXT: and a2, a0, a1
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: add a0, a2, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 1
-; RV32I-NEXT: addi a1, a1, -241
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: slli a1, a0, 8
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: slli a0, a0, 19
-; RV32I-NEXT: srli a0, a0, 27
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i16_zero_undef:
-; RV64I: # %bb.0:
-; RV64I-NEXT: addi a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 5
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: lui a1, 3
-; RV64I-NEXT: addiw a1, a1, 819
-; RV64I-NEXT: and a2, a0, a1
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: add a0, a2, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: lui a1, 1
-; RV64I-NEXT: addiw a1, a1, -241
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: slliw a1, a0, 8
-; RV64I-NEXT: addw a0, a1, a0
-; RV64I-NEXT: slli a0, a0, 51
-; RV64I-NEXT: srli a0, a0, 59
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i16_zero_undef:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i16_zero_undef:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ctz a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i16 @llvm.cttz.i16(i16 %a, i1 true)
- ret i16 %tmp
-}
-
-define i32 @test_cttz_i32_zero_undef(i32 %a) nounwind {
-; RV32I-LABEL: test_cttz_i32_zero_undef:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: addi a1, a0, -1
-; RV32I-NEXT: not a0, a0
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi a1, a1, 819
-; RV32I-NEXT: and a2, a0, a1
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: add a0, a2, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi a1, a1, -241
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi a1, a1, 257
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 16
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i32_zero_undef:
-; RV64I: # %bb.0:
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: addiw a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: subw a0, a0, a1
-; RV64I-NEXT: lui a1, 209715
-; RV64I-NEXT: addiw a1, a1, 819
-; RV64I-NEXT: and a2, a0, a1
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: add a0, a2, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: lui a1, 61681
-; RV64I-NEXT: addiw a1, a1, -241
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, 4112
-; RV64I-NEXT: addiw a1, a1, 257
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srliw a0, a0, 24
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i32_zero_undef:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i32_zero_undef:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ctzw a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i32 @llvm.cttz.i32(i32 %a, i1 true)
- ret i32 %tmp
-}
-
-define i64 @test_cttz_i64_zero_undef(i64 %a) nounwind {
-; RV32I-LABEL: test_cttz_i64_zero_undef:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -32
-; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s5, 4(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s6, 0(sp) # 4-byte Folded Spill
-; RV32I-NEXT: mv s1, a1
-; RV32I-NEXT: mv s2, a0
-; RV32I-NEXT: addi a0, a0, -1
-; RV32I-NEXT: not a1, s2
-; RV32I-NEXT: and a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi s4, a2, 1365
-; RV32I-NEXT: and a1, a1, s4
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi s5, a1, 819
-; RV32I-NEXT: and a1, a0, s5
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, s5
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi s6, a1, -241
-; RV32I-NEXT: and a0, a0, s6
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi s3, a1, 257
-; RV32I-NEXT: mv a1, s3
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: mv s0, a0
-; RV32I-NEXT: addi a0, s1, -1
-; RV32I-NEXT: not a1, s1
-; RV32I-NEXT: and a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: and a1, a1, s4
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: and a1, a0, s5
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, s5
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: and a0, a0, s6
-; RV32I-NEXT: mv a1, s3
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: bnez s2, .LBB21_2
-; RV32I-NEXT: # %bb.1:
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: addi a0, a0, 32
-; RV32I-NEXT: j .LBB21_3
-; RV32I-NEXT: .LBB21_2:
-; RV32I-NEXT: srli a0, s0, 24
-; RV32I-NEXT: .LBB21_3:
-; RV32I-NEXT: li a1, 0
-; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s6, 0(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 32
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_cttz_i64_zero_undef:
-; RV64I: # %bb.0:
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: addi a1, a0, -1
-; RV64I-NEXT: not a0, a0
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, %hi(.LCPI21_0)
-; RV64I-NEXT: ld a1, %lo(.LCPI21_0)(a1)
-; RV64I-NEXT: lui a2, %hi(.LCPI21_1)
-; RV64I-NEXT: ld a2, %lo(.LCPI21_1)(a2)
-; RV64I-NEXT: srli a3, a0, 1
-; RV64I-NEXT: and a1, a3, a1
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: and a1, a0, a2
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a2, %hi(.LCPI21_2)
-; RV64I-NEXT: ld a2, %lo(.LCPI21_2)(a2)
-; RV64I-NEXT: add a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a1, %hi(.LCPI21_3)
-; RV64I-NEXT: ld a1, %lo(.LCPI21_3)(a1)
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srli a0, a0, 56
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_cttz_i64_zero_undef:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: bnez a0, .LBB21_2
-; RV32ZBB-NEXT: # %bb.1:
-; RV32ZBB-NEXT: ctz a0, a1
-; RV32ZBB-NEXT: addi a0, a0, 32
-; RV32ZBB-NEXT: li a1, 0
-; RV32ZBB-NEXT: ret
-; RV32ZBB-NEXT: .LBB21_2:
-; RV32ZBB-NEXT: ctz a0, a0
-; RV32ZBB-NEXT: li a1, 0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_cttz_i64_zero_undef:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: ctz a0, a0
-; RV64ZBB-NEXT: ret
- %tmp = call i64 @llvm.cttz.i64(i64 %a, i1 true)
- ret i64 %tmp
-}
-
-define i32 @test_ctpop_i32(i32 %a) nounwind {
-; RV32I-LABEL: test_ctpop_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -16
-; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi a2, a2, 1365
-; RV32I-NEXT: and a1, a1, a2
-; RV32I-NEXT: sub a0, a0, a1
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi a1, a1, 819
-; RV32I-NEXT: and a2, a0, a1
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: add a0, a2, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi a1, a1, -241
-; RV32I-NEXT: and a0, a0, a1
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi a1, a1, 257
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 16
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_ctpop_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: lui a2, 349525
-; RV64I-NEXT: addiw a2, a2, 1365
-; RV64I-NEXT: and a1, a1, a2
-; RV64I-NEXT: subw a0, a0, a1
-; RV64I-NEXT: lui a1, 209715
-; RV64I-NEXT: addiw a1, a1, 819
-; RV64I-NEXT: and a2, a0, a1
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: add a0, a2, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: lui a1, 61681
-; RV64I-NEXT: addiw a1, a1, -241
-; RV64I-NEXT: and a0, a0, a1
-; RV64I-NEXT: lui a1, 4112
-; RV64I-NEXT: addiw a1, a1, 257
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srliw a0, a0, 24
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_ctpop_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: cpop a0, a0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_ctpop_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: cpopw a0, a0
-; RV64ZBB-NEXT: ret
- %1 = call i32 @llvm.ctpop.i32(i32 %a)
- ret i32 %1
-}
-
-define i64 @test_ctpop_i64(i64 %a) nounwind {
-; RV32I-LABEL: test_ctpop_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: addi sp, sp, -32
-; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
-; RV32I-NEXT: sw s5, 4(sp) # 4-byte Folded Spill
-; RV32I-NEXT: mv s0, a0
-; RV32I-NEXT: srli a0, a1, 1
-; RV32I-NEXT: lui a2, 349525
-; RV32I-NEXT: addi s2, a2, 1365
-; RV32I-NEXT: and a0, a0, s2
-; RV32I-NEXT: sub a0, a1, a0
-; RV32I-NEXT: lui a1, 209715
-; RV32I-NEXT: addi s3, a1, 819
-; RV32I-NEXT: and a1, a0, s3
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, s3
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: lui a1, 61681
-; RV32I-NEXT: addi s4, a1, -241
-; RV32I-NEXT: and a0, a0, s4
-; RV32I-NEXT: lui a1, 4112
-; RV32I-NEXT: addi s1, a1, 257
-; RV32I-NEXT: mv a1, s1
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: srli s5, a0, 24
-; RV32I-NEXT: srli a0, s0, 1
-; RV32I-NEXT: and a0, a0, s2
-; RV32I-NEXT: sub a0, s0, a0
-; RV32I-NEXT: and a1, a0, s3
-; RV32I-NEXT: srli a0, a0, 2
-; RV32I-NEXT: and a0, a0, s3
-; RV32I-NEXT: add a0, a1, a0
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: add a0, a0, a1
-; RV32I-NEXT: and a0, a0, s4
-; RV32I-NEXT: mv a1, s1
-; RV32I-NEXT: call __mulsi3@plt
-; RV32I-NEXT: srli a0, a0, 24
-; RV32I-NEXT: add a0, a0, s5
-; RV32I-NEXT: li a1, 0
-; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
-; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
-; RV32I-NEXT: addi sp, sp, 32
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_ctpop_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: addi sp, sp, -16
-; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
-; RV64I-NEXT: lui a1, %hi(.LCPI23_0)
-; RV64I-NEXT: ld a1, %lo(.LCPI23_0)(a1)
-; RV64I-NEXT: lui a2, %hi(.LCPI23_1)
-; RV64I-NEXT: ld a2, %lo(.LCPI23_1)(a2)
-; RV64I-NEXT: srli a3, a0, 1
-; RV64I-NEXT: and a1, a3, a1
-; RV64I-NEXT: sub a0, a0, a1
-; RV64I-NEXT: and a1, a0, a2
-; RV64I-NEXT: srli a0, a0, 2
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a2, %hi(.LCPI23_2)
-; RV64I-NEXT: ld a2, %lo(.LCPI23_2)(a2)
-; RV64I-NEXT: add a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: add a0, a0, a1
-; RV64I-NEXT: and a0, a0, a2
-; RV64I-NEXT: lui a1, %hi(.LCPI23_3)
-; RV64I-NEXT: ld a1, %lo(.LCPI23_3)(a1)
-; RV64I-NEXT: call __muldi3@plt
-; RV64I-NEXT: srli a0, a0, 56
-; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
-; RV64I-NEXT: addi sp, sp, 16
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_ctpop_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: cpop a1, a1
-; RV32ZBB-NEXT: cpop a0, a0
-; RV32ZBB-NEXT: add a0, a0, a1
-; RV32ZBB-NEXT: li a1, 0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_ctpop_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: cpop a0, a0
-; RV64ZBB-NEXT: ret
- %1 = call i64 @llvm.ctpop.i64(i64 %a)
- ret i64 %1
-}
-
-define i32 @test_parity_i32(i32 %a) {
-; RV32I-LABEL: test_parity_i32:
-; RV32I: # %bb.0:
-; RV32I-NEXT: srli a1, a0, 16
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: andi a0, a0, 1
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_parity_i32:
-; RV64I: # %bb.0:
-; RV64I-NEXT: slli a1, a0, 32
-; RV64I-NEXT: srli a1, a1, 32
-; RV64I-NEXT: srliw a0, a0, 16
-; RV64I-NEXT: xor a0, a1, a0
-; RV64I-NEXT: srli a1, a0, 8
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: andi a0, a0, 1
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_parity_i32:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: cpop a0, a0
-; RV32ZBB-NEXT: andi a0, a0, 1
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_parity_i32:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: cpopw a0, a0
-; RV64ZBB-NEXT: andi a0, a0, 1
-; RV64ZBB-NEXT: ret
- %1 = call i32 @llvm.ctpop.i32(i32 %a)
- %2 = and i32 %1, 1
- ret i32 %2
-}
-
-define i64 @test_parity_i64(i64 %a) {
-; RV32I-LABEL: test_parity_i64:
-; RV32I: # %bb.0:
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 16
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 8
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 4
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 2
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: srli a1, a0, 1
-; RV32I-NEXT: xor a0, a0, a1
-; RV32I-NEXT: andi a0, a0, 1
-; RV32I-NEXT: li a1, 0
-; RV32I-NEXT: ret
-;
-; RV64I-LABEL: test_parity_i64:
-; RV64I: # %bb.0:
-; RV64I-NEXT: srli a1, a0, 32
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 16
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 8
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 4
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 2
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: srli a1, a0, 1
-; RV64I-NEXT: xor a0, a0, a1
-; RV64I-NEXT: andi a0, a0, 1
-; RV64I-NEXT: ret
-;
-; RV32ZBB-LABEL: test_parity_i64:
-; RV32ZBB: # %bb.0:
-; RV32ZBB-NEXT: xor a0, a0, a1
-; RV32ZBB-NEXT: cpop a0, a0
-; RV32ZBB-NEXT: andi a0, a0, 1
-; RV32ZBB-NEXT: li a1, 0
-; RV32ZBB-NEXT: ret
-;
-; RV64ZBB-LABEL: test_parity_i64:
-; RV64ZBB: # %bb.0:
-; RV64ZBB-NEXT: cpop a0, a0
-; RV64ZBB-NEXT: andi a0, a0, 1
-; RV64ZBB-NEXT: ret
- %1 = call i64 @llvm.ctpop.i64(i64 %a)
- %2 = and i64 %1, 1
- ret i64 %2
-}
--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV32I
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV64I
+; RUN: llc -mtriple=riscv32 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefixes=RV32ZB
+; RUN: llc -mtriple=riscv64 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefixes=RV64ZB
+; RUN: llc -mtriple=riscv32 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefixes=RV32ZB
+; RUN: llc -mtriple=riscv64 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefixes=RV64ZB
+
+declare i16 @llvm.bswap.i16(i16)
+declare i32 @llvm.bswap.i32(i32)
+declare i64 @llvm.bswap.i64(i64)
+declare i8 @llvm.bitreverse.i8(i8)
+declare i16 @llvm.bitreverse.i16(i16)
+declare i32 @llvm.bitreverse.i32(i32)
+declare i64 @llvm.bitreverse.i64(i64)
+
+define i16 @test_bswap_i16(i16 %a) nounwind {
+; RV32I-LABEL: test_bswap_i16:
+; RV32I: # %bb.0:
+; RV32I-NEXT: slli a1, a0, 8
+; RV32I-NEXT: slli a0, a0, 16
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bswap_i16:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a1, a0, 8
+; RV64I-NEXT: slli a0, a0, 48
+; RV64I-NEXT: srli a0, a0, 56
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bswap_i16:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: rev8 a0, a0
+; RV32ZB-NEXT: srli a0, a0, 16
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bswap_i16:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: rev8 a0, a0
+; RV64ZB-NEXT: srli a0, a0, 48
+; RV64ZB-NEXT: ret
+ %tmp = call i16 @llvm.bswap.i16(i16 %a)
+ ret i16 %tmp
+}
+
+define i32 @test_bswap_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_bswap_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: lui a2, 16
+; RV32I-NEXT: addi a2, a2, -256
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: srli a2, a0, 24
+; RV32I-NEXT: or a1, a1, a2
+; RV32I-NEXT: slli a2, a0, 8
+; RV32I-NEXT: lui a3, 4080
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: slli a0, a0, 24
+; RV32I-NEXT: or a0, a0, a2
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bswap_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srliw a1, a0, 8
+; RV64I-NEXT: lui a2, 16
+; RV64I-NEXT: addiw a2, a2, -256
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: srliw a2, a0, 24
+; RV64I-NEXT: or a1, a1, a2
+; RV64I-NEXT: slli a2, a0, 8
+; RV64I-NEXT: lui a3, 4080
+; RV64I-NEXT: and a2, a2, a3
+; RV64I-NEXT: slliw a0, a0, 24
+; RV64I-NEXT: or a0, a0, a2
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bswap_i32:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: rev8 a0, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bswap_i32:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: rev8 a0, a0
+; RV64ZB-NEXT: srli a0, a0, 32
+; RV64ZB-NEXT: ret
+ %tmp = call i32 @llvm.bswap.i32(i32 %a)
+ ret i32 %tmp
+}
+
+define i64 @test_bswap_i64(i64 %a) nounwind {
+; RV32I-LABEL: test_bswap_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a2, a1, 8
+; RV32I-NEXT: lui a3, 16
+; RV32I-NEXT: addi a3, a3, -256
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: srli a4, a1, 24
+; RV32I-NEXT: or a2, a2, a4
+; RV32I-NEXT: slli a4, a1, 8
+; RV32I-NEXT: lui a5, 4080
+; RV32I-NEXT: and a4, a4, a5
+; RV32I-NEXT: slli a1, a1, 24
+; RV32I-NEXT: or a1, a1, a4
+; RV32I-NEXT: or a2, a1, a2
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: and a1, a1, a3
+; RV32I-NEXT: srli a3, a0, 24
+; RV32I-NEXT: or a1, a1, a3
+; RV32I-NEXT: slli a3, a0, 8
+; RV32I-NEXT: and a3, a3, a5
+; RV32I-NEXT: slli a0, a0, 24
+; RV32I-NEXT: or a0, a0, a3
+; RV32I-NEXT: or a1, a0, a1
+; RV32I-NEXT: mv a0, a2
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bswap_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 24
+; RV64I-NEXT: lui a2, 4080
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: srli a2, a0, 8
+; RV64I-NEXT: li a3, 255
+; RV64I-NEXT: slli a4, a3, 24
+; RV64I-NEXT: and a2, a2, a4
+; RV64I-NEXT: or a1, a2, a1
+; RV64I-NEXT: srli a2, a0, 40
+; RV64I-NEXT: lui a4, 16
+; RV64I-NEXT: addiw a4, a4, -256
+; RV64I-NEXT: and a2, a2, a4
+; RV64I-NEXT: srli a4, a0, 56
+; RV64I-NEXT: or a2, a2, a4
+; RV64I-NEXT: or a1, a1, a2
+; RV64I-NEXT: slli a2, a0, 24
+; RV64I-NEXT: slli a4, a3, 40
+; RV64I-NEXT: and a2, a2, a4
+; RV64I-NEXT: srliw a4, a0, 24
+; RV64I-NEXT: slli a4, a4, 32
+; RV64I-NEXT: or a2, a2, a4
+; RV64I-NEXT: slli a4, a0, 40
+; RV64I-NEXT: slli a3, a3, 48
+; RV64I-NEXT: and a3, a4, a3
+; RV64I-NEXT: slli a0, a0, 56
+; RV64I-NEXT: or a0, a0, a3
+; RV64I-NEXT: or a0, a0, a2
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bswap_i64:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: rev8 a2, a1
+; RV32ZB-NEXT: rev8 a1, a0
+; RV32ZB-NEXT: mv a0, a2
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bswap_i64:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: rev8 a0, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i64 @llvm.bswap.i64(i64 %a)
+ ret i64 %tmp
+}
+
+define i8 @test_bitreverse_i8(i8 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_i8:
+; RV32I: # %bb.0:
+; RV32I-NEXT: andi a1, a0, 15
+; RV32I-NEXT: slli a1, a1, 4
+; RV32I-NEXT: slli a0, a0, 24
+; RV32I-NEXT: srli a0, a0, 28
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: andi a1, a0, 51
+; RV32I-NEXT: slli a1, a1, 2
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: andi a0, a0, 51
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: andi a1, a0, 85
+; RV32I-NEXT: slli a1, a1, 1
+; RV32I-NEXT: srli a0, a0, 1
+; RV32I-NEXT: andi a0, a0, 85
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_i8:
+; RV64I: # %bb.0:
+; RV64I-NEXT: andi a1, a0, 15
+; RV64I-NEXT: slli a1, a1, 4
+; RV64I-NEXT: slli a0, a0, 56
+; RV64I-NEXT: srli a0, a0, 60
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: andi a1, a0, 51
+; RV64I-NEXT: slli a1, a1, 2
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: andi a0, a0, 51
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: andi a1, a0, 85
+; RV64I-NEXT: slli a1, a1, 1
+; RV64I-NEXT: srli a0, a0, 1
+; RV64I-NEXT: andi a0, a0, 85
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_i8:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: andi a1, a0, 15
+; RV32ZB-NEXT: slli a1, a1, 4
+; RV32ZB-NEXT: slli a0, a0, 24
+; RV32ZB-NEXT: srli a0, a0, 28
+; RV32ZB-NEXT: or a0, a0, a1
+; RV32ZB-NEXT: andi a1, a0, 51
+; RV32ZB-NEXT: slli a1, a1, 2
+; RV32ZB-NEXT: srli a0, a0, 2
+; RV32ZB-NEXT: andi a0, a0, 51
+; RV32ZB-NEXT: or a0, a0, a1
+; RV32ZB-NEXT: andi a1, a0, 85
+; RV32ZB-NEXT: slli a1, a1, 1
+; RV32ZB-NEXT: srli a0, a0, 1
+; RV32ZB-NEXT: andi a0, a0, 85
+; RV32ZB-NEXT: or a0, a0, a1
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_i8:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: andi a1, a0, 15
+; RV64ZB-NEXT: slli a1, a1, 4
+; RV64ZB-NEXT: slli a0, a0, 56
+; RV64ZB-NEXT: srli a0, a0, 60
+; RV64ZB-NEXT: or a0, a0, a1
+; RV64ZB-NEXT: andi a1, a0, 51
+; RV64ZB-NEXT: slli a1, a1, 2
+; RV64ZB-NEXT: srli a0, a0, 2
+; RV64ZB-NEXT: andi a0, a0, 51
+; RV64ZB-NEXT: or a0, a0, a1
+; RV64ZB-NEXT: andi a1, a0, 85
+; RV64ZB-NEXT: slli a1, a1, 1
+; RV64ZB-NEXT: srli a0, a0, 1
+; RV64ZB-NEXT: andi a0, a0, 85
+; RV64ZB-NEXT: or a0, a0, a1
+; RV64ZB-NEXT: ret
+ %tmp = call i8 @llvm.bitreverse.i8(i8 %a)
+ ret i8 %tmp
+}
+
+define i16 @test_bitreverse_i16(i16 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_i16:
+; RV32I: # %bb.0:
+; RV32I-NEXT: slli a1, a0, 8
+; RV32I-NEXT: slli a0, a0, 16
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: lui a2, 1
+; RV32I-NEXT: addi a2, a2, -241
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: lui a2, 3
+; RV32I-NEXT: addi a2, a2, 819
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 5
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_i16:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a1, a0, 8
+; RV64I-NEXT: slli a0, a0, 48
+; RV64I-NEXT: srli a0, a0, 56
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: lui a2, 1
+; RV64I-NEXT: addiw a2, a2, -241
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: lui a2, 3
+; RV64I-NEXT: addiw a2, a2, 819
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 5
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_i16:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: rev8 a0, a0
+; RV32ZB-NEXT: srli a1, a0, 12
+; RV32ZB-NEXT: lui a2, 15
+; RV32ZB-NEXT: addi a2, a2, 240
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: srli a0, a0, 20
+; RV32ZB-NEXT: andi a0, a0, -241
+; RV32ZB-NEXT: or a0, a0, a1
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: lui a2, 3
+; RV32ZB-NEXT: addi a2, a2, 819
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: lui a2, 5
+; RV32ZB-NEXT: addi a2, a2, 1365
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_i16:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: rev8 a0, a0
+; RV64ZB-NEXT: srli a1, a0, 44
+; RV64ZB-NEXT: lui a2, 15
+; RV64ZB-NEXT: addiw a2, a2, 240
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: srli a0, a0, 52
+; RV64ZB-NEXT: andi a0, a0, -241
+; RV64ZB-NEXT: or a0, a0, a1
+; RV64ZB-NEXT: srli a1, a0, 2
+; RV64ZB-NEXT: lui a2, 3
+; RV64ZB-NEXT: addiw a2, a2, 819
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 2
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 1
+; RV64ZB-NEXT: lui a2, 5
+; RV64ZB-NEXT: addiw a2, a2, 1365
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 1
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i16 @llvm.bitreverse.i16(i16 %a)
+ ret i16 %tmp
+}
+
+define i32 @test_bitreverse_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: lui a2, 16
+; RV32I-NEXT: addi a2, a2, -256
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: srli a2, a0, 24
+; RV32I-NEXT: or a1, a1, a2
+; RV32I-NEXT: slli a2, a0, 8
+; RV32I-NEXT: lui a3, 4080
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: slli a0, a0, 24
+; RV32I-NEXT: or a0, a0, a2
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: lui a2, 61681
+; RV32I-NEXT: addi a2, a2, -241
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: lui a2, 209715
+; RV32I-NEXT: addi a2, a2, 819
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srliw a1, a0, 8
+; RV64I-NEXT: lui a2, 16
+; RV64I-NEXT: addiw a2, a2, -256
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: srliw a2, a0, 24
+; RV64I-NEXT: or a1, a1, a2
+; RV64I-NEXT: slli a2, a0, 8
+; RV64I-NEXT: lui a3, 4080
+; RV64I-NEXT: and a2, a2, a3
+; RV64I-NEXT: slliw a0, a0, 24
+; RV64I-NEXT: or a0, a0, a2
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: lui a2, 61681
+; RV64I-NEXT: addiw a2, a2, -241
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: lui a2, 209715
+; RV64I-NEXT: addiw a2, a2, 819
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_i32:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: rev8 a0, a0
+; RV32ZB-NEXT: srli a1, a0, 4
+; RV32ZB-NEXT: lui a2, 61681
+; RV32ZB-NEXT: addi a2, a2, -241
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: lui a2, 209715
+; RV32ZB-NEXT: addi a2, a2, 819
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: lui a2, 349525
+; RV32ZB-NEXT: addi a2, a2, 1365
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_i32:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: rev8 a0, a0
+; RV64ZB-NEXT: srli a1, a0, 36
+; RV64ZB-NEXT: lui a2, 61681
+; RV64ZB-NEXT: addiw a2, a2, -241
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: srli a0, a0, 28
+; RV64ZB-NEXT: lui a2, 986895
+; RV64ZB-NEXT: addiw a2, a2, 240
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: sext.w a0, a0
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 2
+; RV64ZB-NEXT: lui a2, 209715
+; RV64ZB-NEXT: addiw a2, a2, 819
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 2
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 1
+; RV64ZB-NEXT: lui a2, 349525
+; RV64ZB-NEXT: addiw a2, a2, 1365
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 1
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i32 @llvm.bitreverse.i32(i32 %a)
+ ret i32 %tmp
+}
+
+define i64 @test_bitreverse_i64(i64 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a2, a1, 8
+; RV32I-NEXT: lui a3, 16
+; RV32I-NEXT: addi a3, a3, -256
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: srli a4, a1, 24
+; RV32I-NEXT: or a2, a2, a4
+; RV32I-NEXT: slli a4, a1, 8
+; RV32I-NEXT: lui a5, 4080
+; RV32I-NEXT: and a4, a4, a5
+; RV32I-NEXT: slli a1, a1, 24
+; RV32I-NEXT: or a1, a1, a4
+; RV32I-NEXT: or a1, a1, a2
+; RV32I-NEXT: srli a2, a1, 4
+; RV32I-NEXT: lui a4, 61681
+; RV32I-NEXT: addi a4, a4, -241
+; RV32I-NEXT: and a2, a2, a4
+; RV32I-NEXT: and a1, a1, a4
+; RV32I-NEXT: slli a1, a1, 4
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: srli a2, a1, 2
+; RV32I-NEXT: lui a6, 209715
+; RV32I-NEXT: addi a6, a6, 819
+; RV32I-NEXT: and a2, a2, a6
+; RV32I-NEXT: and a1, a1, a6
+; RV32I-NEXT: slli a1, a1, 2
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: srli a2, a1, 1
+; RV32I-NEXT: lui a7, 349525
+; RV32I-NEXT: addi a7, a7, 1365
+; RV32I-NEXT: and a2, a2, a7
+; RV32I-NEXT: and a1, a1, a7
+; RV32I-NEXT: slli a1, a1, 1
+; RV32I-NEXT: or a2, a2, a1
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: and a1, a1, a3
+; RV32I-NEXT: srli a3, a0, 24
+; RV32I-NEXT: or a1, a1, a3
+; RV32I-NEXT: slli a3, a0, 8
+; RV32I-NEXT: and a3, a3, a5
+; RV32I-NEXT: slli a0, a0, 24
+; RV32I-NEXT: or a0, a0, a3
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: and a1, a1, a4
+; RV32I-NEXT: and a0, a0, a4
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: and a1, a1, a6
+; RV32I-NEXT: and a0, a0, a6
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: and a1, a1, a7
+; RV32I-NEXT: and a0, a0, a7
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a1, a1, a0
+; RV32I-NEXT: mv a0, a2
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 24
+; RV64I-NEXT: lui a2, 4080
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: srli a2, a0, 8
+; RV64I-NEXT: li a3, 255
+; RV64I-NEXT: slli a4, a3, 24
+; RV64I-NEXT: and a2, a2, a4
+; RV64I-NEXT: or a1, a2, a1
+; RV64I-NEXT: srli a2, a0, 40
+; RV64I-NEXT: lui a4, 16
+; RV64I-NEXT: addiw a4, a4, -256
+; RV64I-NEXT: and a2, a2, a4
+; RV64I-NEXT: srli a4, a0, 56
+; RV64I-NEXT: or a2, a2, a4
+; RV64I-NEXT: or a1, a1, a2
+; RV64I-NEXT: slli a2, a0, 24
+; RV64I-NEXT: slli a4, a3, 40
+; RV64I-NEXT: and a2, a2, a4
+; RV64I-NEXT: srliw a4, a0, 24
+; RV64I-NEXT: slli a4, a4, 32
+; RV64I-NEXT: or a2, a2, a4
+; RV64I-NEXT: slli a4, a0, 40
+; RV64I-NEXT: slli a3, a3, 48
+; RV64I-NEXT: and a3, a4, a3
+; RV64I-NEXT: slli a0, a0, 56
+; RV64I-NEXT: or a0, a0, a3
+; RV64I-NEXT: lui a3, %hi(.LCPI6_0)
+; RV64I-NEXT: ld a3, %lo(.LCPI6_0)(a3)
+; RV64I-NEXT: or a0, a0, a2
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: and a1, a1, a3
+; RV64I-NEXT: and a0, a0, a3
+; RV64I-NEXT: lui a2, %hi(.LCPI6_1)
+; RV64I-NEXT: ld a2, %lo(.LCPI6_1)(a2)
+; RV64I-NEXT: slli a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a2, %hi(.LCPI6_2)
+; RV64I-NEXT: ld a2, %lo(.LCPI6_2)(a2)
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_i64:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: rev8 a1, a1
+; RV32ZB-NEXT: srli a2, a1, 4
+; RV32ZB-NEXT: lui a3, 61681
+; RV32ZB-NEXT: addi a3, a3, -241
+; RV32ZB-NEXT: and a2, a2, a3
+; RV32ZB-NEXT: and a1, a1, a3
+; RV32ZB-NEXT: slli a1, a1, 4
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: srli a2, a1, 2
+; RV32ZB-NEXT: lui a4, 209715
+; RV32ZB-NEXT: addi a4, a4, 819
+; RV32ZB-NEXT: and a2, a2, a4
+; RV32ZB-NEXT: and a1, a1, a4
+; RV32ZB-NEXT: slli a1, a1, 2
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: srli a2, a1, 1
+; RV32ZB-NEXT: lui a5, 349525
+; RV32ZB-NEXT: addi a5, a5, 1365
+; RV32ZB-NEXT: and a2, a2, a5
+; RV32ZB-NEXT: and a1, a1, a5
+; RV32ZB-NEXT: slli a1, a1, 1
+; RV32ZB-NEXT: or a2, a2, a1
+; RV32ZB-NEXT: rev8 a0, a0
+; RV32ZB-NEXT: srli a1, a0, 4
+; RV32ZB-NEXT: and a1, a1, a3
+; RV32ZB-NEXT: and a0, a0, a3
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: and a1, a1, a4
+; RV32ZB-NEXT: and a0, a0, a4
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: and a1, a1, a5
+; RV32ZB-NEXT: and a0, a0, a5
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a1, a1, a0
+; RV32ZB-NEXT: mv a0, a2
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_i64:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: lui a1, %hi(.LCPI6_0)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI6_0)(a1)
+; RV64ZB-NEXT: rev8 a0, a0
+; RV64ZB-NEXT: srli a2, a0, 4
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: lui a1, %hi(.LCPI6_1)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI6_1)(a1)
+; RV64ZB-NEXT: slli a0, a0, 4
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: srli a2, a0, 2
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: lui a1, %hi(.LCPI6_2)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI6_2)(a1)
+; RV64ZB-NEXT: slli a0, a0, 2
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: srli a2, a0, 1
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: slli a0, a0, 1
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i64 @llvm.bitreverse.i64(i64 %a)
+ ret i64 %tmp
+}
+
+define i16 @test_bswap_bitreverse_i16(i16 %a) nounwind {
+; RV32I-LABEL: test_bswap_bitreverse_i16:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: lui a2, 1
+; RV32I-NEXT: addi a2, a2, -241
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: lui a2, 3
+; RV32I-NEXT: addi a2, a2, 819
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 5
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bswap_bitreverse_i16:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: lui a2, 1
+; RV64I-NEXT: addiw a2, a2, -241
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: lui a2, 3
+; RV64I-NEXT: addiw a2, a2, 819
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 5
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bswap_bitreverse_i16:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: srli a1, a0, 4
+; RV32ZB-NEXT: lui a2, 1
+; RV32ZB-NEXT: addi a2, a2, -241
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: lui a2, 3
+; RV32ZB-NEXT: addi a2, a2, 819
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: lui a2, 5
+; RV32ZB-NEXT: addi a2, a2, 1365
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bswap_bitreverse_i16:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: srli a1, a0, 4
+; RV64ZB-NEXT: lui a2, 1
+; RV64ZB-NEXT: addiw a2, a2, -241
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 4
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 2
+; RV64ZB-NEXT: lui a2, 3
+; RV64ZB-NEXT: addiw a2, a2, 819
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 2
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 1
+; RV64ZB-NEXT: lui a2, 5
+; RV64ZB-NEXT: addiw a2, a2, 1365
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 1
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i16 @llvm.bswap.i16(i16 %a)
+ %tmp2 = call i16 @llvm.bitreverse.i16(i16 %tmp)
+ ret i16 %tmp2
+}
+
+define i32 @test_bswap_bitreverse_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_bswap_bitreverse_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: lui a2, 61681
+; RV32I-NEXT: addi a2, a2, -241
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: lui a2, 209715
+; RV32I-NEXT: addi a2, a2, 819
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bswap_bitreverse_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: lui a2, 61681
+; RV64I-NEXT: addiw a2, a2, -241
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: lui a2, 209715
+; RV64I-NEXT: addiw a2, a2, 819
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bswap_bitreverse_i32:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: srli a1, a0, 4
+; RV32ZB-NEXT: lui a2, 61681
+; RV32ZB-NEXT: addi a2, a2, -241
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: lui a2, 209715
+; RV32ZB-NEXT: addi a2, a2, 819
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: lui a2, 349525
+; RV32ZB-NEXT: addi a2, a2, 1365
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bswap_bitreverse_i32:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: srli a1, a0, 4
+; RV64ZB-NEXT: lui a2, 61681
+; RV64ZB-NEXT: addiw a2, a2, -241
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 4
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 2
+; RV64ZB-NEXT: lui a2, 209715
+; RV64ZB-NEXT: addiw a2, a2, 819
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 2
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 1
+; RV64ZB-NEXT: lui a2, 349525
+; RV64ZB-NEXT: addiw a2, a2, 1365
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 1
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i32 @llvm.bswap.i32(i32 %a)
+ %tmp2 = call i32 @llvm.bitreverse.i32(i32 %tmp)
+ ret i32 %tmp2
+}
+
+define i64 @test_bswap_bitreverse_i64(i64 %a) nounwind {
+; RV32I-LABEL: test_bswap_bitreverse_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a2, a0, 4
+; RV32I-NEXT: lui a3, 61681
+; RV32I-NEXT: addi a3, a3, -241
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: and a0, a0, a3
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a2, a0
+; RV32I-NEXT: srli a2, a0, 2
+; RV32I-NEXT: lui a4, 209715
+; RV32I-NEXT: addi a4, a4, 819
+; RV32I-NEXT: and a2, a2, a4
+; RV32I-NEXT: and a0, a0, a4
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a2, a0
+; RV32I-NEXT: srli a2, a0, 1
+; RV32I-NEXT: lui a5, 349525
+; RV32I-NEXT: addi a5, a5, 1365
+; RV32I-NEXT: and a2, a2, a5
+; RV32I-NEXT: and a0, a0, a5
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a2, a0
+; RV32I-NEXT: srli a2, a1, 4
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: and a1, a1, a3
+; RV32I-NEXT: slli a1, a1, 4
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: srli a2, a1, 2
+; RV32I-NEXT: and a2, a2, a4
+; RV32I-NEXT: and a1, a1, a4
+; RV32I-NEXT: slli a1, a1, 2
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: srli a2, a1, 1
+; RV32I-NEXT: and a2, a2, a5
+; RV32I-NEXT: and a1, a1, a5
+; RV32I-NEXT: slli a1, a1, 1
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bswap_bitreverse_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: lui a1, %hi(.LCPI9_0)
+; RV64I-NEXT: ld a1, %lo(.LCPI9_0)(a1)
+; RV64I-NEXT: srli a2, a0, 4
+; RV64I-NEXT: and a2, a2, a1
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, %hi(.LCPI9_1)
+; RV64I-NEXT: ld a1, %lo(.LCPI9_1)(a1)
+; RV64I-NEXT: slli a0, a0, 4
+; RV64I-NEXT: or a0, a2, a0
+; RV64I-NEXT: srli a2, a0, 2
+; RV64I-NEXT: and a2, a2, a1
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, %hi(.LCPI9_2)
+; RV64I-NEXT: ld a1, %lo(.LCPI9_2)(a1)
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: or a0, a2, a0
+; RV64I-NEXT: srli a2, a0, 1
+; RV64I-NEXT: and a2, a2, a1
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: or a0, a2, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bswap_bitreverse_i64:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: srli a2, a0, 4
+; RV32ZB-NEXT: lui a3, 61681
+; RV32ZB-NEXT: addi a3, a3, -241
+; RV32ZB-NEXT: and a2, a2, a3
+; RV32ZB-NEXT: and a0, a0, a3
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a2, a0
+; RV32ZB-NEXT: srli a2, a0, 2
+; RV32ZB-NEXT: lui a4, 209715
+; RV32ZB-NEXT: addi a4, a4, 819
+; RV32ZB-NEXT: and a2, a2, a4
+; RV32ZB-NEXT: and a0, a0, a4
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a2, a0
+; RV32ZB-NEXT: srli a2, a0, 1
+; RV32ZB-NEXT: lui a5, 349525
+; RV32ZB-NEXT: addi a5, a5, 1365
+; RV32ZB-NEXT: and a2, a2, a5
+; RV32ZB-NEXT: and a0, a0, a5
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a2, a0
+; RV32ZB-NEXT: srli a2, a1, 4
+; RV32ZB-NEXT: and a2, a2, a3
+; RV32ZB-NEXT: and a1, a1, a3
+; RV32ZB-NEXT: slli a1, a1, 4
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: srli a2, a1, 2
+; RV32ZB-NEXT: and a2, a2, a4
+; RV32ZB-NEXT: and a1, a1, a4
+; RV32ZB-NEXT: slli a1, a1, 2
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: srli a2, a1, 1
+; RV32ZB-NEXT: and a2, a2, a5
+; RV32ZB-NEXT: and a1, a1, a5
+; RV32ZB-NEXT: slli a1, a1, 1
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bswap_bitreverse_i64:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: lui a1, %hi(.LCPI9_0)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI9_0)(a1)
+; RV64ZB-NEXT: srli a2, a0, 4
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: lui a1, %hi(.LCPI9_1)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI9_1)(a1)
+; RV64ZB-NEXT: slli a0, a0, 4
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: srli a2, a0, 2
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: lui a1, %hi(.LCPI9_2)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI9_2)(a1)
+; RV64ZB-NEXT: slli a0, a0, 2
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: srli a2, a0, 1
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: slli a0, a0, 1
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i64 @llvm.bswap.i64(i64 %a)
+ %tmp2 = call i64 @llvm.bitreverse.i64(i64 %tmp)
+ ret i64 %tmp2
+}
+
+define i16 @test_bitreverse_bswap_i16(i16 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_bswap_i16:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: lui a2, 1
+; RV32I-NEXT: addi a2, a2, -241
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: lui a2, 3
+; RV32I-NEXT: addi a2, a2, 819
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 5
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_bswap_i16:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: lui a2, 1
+; RV64I-NEXT: addiw a2, a2, -241
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: lui a2, 3
+; RV64I-NEXT: addiw a2, a2, 819
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 5
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_bswap_i16:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: srli a1, a0, 4
+; RV32ZB-NEXT: lui a2, 1
+; RV32ZB-NEXT: addi a2, a2, -241
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: lui a2, 3
+; RV32ZB-NEXT: addi a2, a2, 819
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: lui a2, 5
+; RV32ZB-NEXT: addi a2, a2, 1365
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_bswap_i16:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: srli a1, a0, 4
+; RV64ZB-NEXT: lui a2, 1
+; RV64ZB-NEXT: addiw a2, a2, -241
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 4
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 2
+; RV64ZB-NEXT: lui a2, 3
+; RV64ZB-NEXT: addiw a2, a2, 819
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 2
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 1
+; RV64ZB-NEXT: lui a2, 5
+; RV64ZB-NEXT: addiw a2, a2, 1365
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slli a0, a0, 1
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i16 @llvm.bitreverse.i16(i16 %a)
+ %tmp2 = call i16 @llvm.bswap.i16(i16 %tmp)
+ ret i16 %tmp2
+}
+
+define i32 @test_bitreverse_bswap_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_bswap_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: lui a2, 61681
+; RV32I-NEXT: addi a2, a2, -241
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: lui a2, 209715
+; RV32I-NEXT: addi a2, a2, 819
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: and a0, a0, a2
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a1, a0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_bswap_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: lui a2, 61681
+; RV64I-NEXT: addiw a2, a2, -241
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 4
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: lui a2, 209715
+; RV64I-NEXT: addiw a2, a2, 819
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 2
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: slliw a0, a0, 1
+; RV64I-NEXT: or a0, a1, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_bswap_i32:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: srli a1, a0, 4
+; RV32ZB-NEXT: lui a2, 61681
+; RV32ZB-NEXT: addi a2, a2, -241
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 2
+; RV32ZB-NEXT: lui a2, 209715
+; RV32ZB-NEXT: addi a2, a2, 819
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: srli a1, a0, 1
+; RV32ZB-NEXT: lui a2, 349525
+; RV32ZB-NEXT: addi a2, a2, 1365
+; RV32ZB-NEXT: and a1, a1, a2
+; RV32ZB-NEXT: and a0, a0, a2
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a1, a0
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_bswap_i32:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: srli a1, a0, 4
+; RV64ZB-NEXT: lui a2, 61681
+; RV64ZB-NEXT: addiw a2, a2, -241
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 4
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 2
+; RV64ZB-NEXT: lui a2, 209715
+; RV64ZB-NEXT: addiw a2, a2, 819
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 2
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: srli a1, a0, 1
+; RV64ZB-NEXT: lui a2, 349525
+; RV64ZB-NEXT: addiw a2, a2, 1365
+; RV64ZB-NEXT: and a1, a1, a2
+; RV64ZB-NEXT: and a0, a0, a2
+; RV64ZB-NEXT: slliw a0, a0, 1
+; RV64ZB-NEXT: or a0, a1, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i32 @llvm.bitreverse.i32(i32 %a)
+ %tmp2 = call i32 @llvm.bswap.i32(i32 %tmp)
+ ret i32 %tmp2
+}
+
+define i64 @test_bitreverse_bswap_i64(i64 %a) nounwind {
+; RV32I-LABEL: test_bitreverse_bswap_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a2, a0, 4
+; RV32I-NEXT: lui a3, 61681
+; RV32I-NEXT: addi a3, a3, -241
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: and a0, a0, a3
+; RV32I-NEXT: slli a0, a0, 4
+; RV32I-NEXT: or a0, a2, a0
+; RV32I-NEXT: srli a2, a0, 2
+; RV32I-NEXT: lui a4, 209715
+; RV32I-NEXT: addi a4, a4, 819
+; RV32I-NEXT: and a2, a2, a4
+; RV32I-NEXT: and a0, a0, a4
+; RV32I-NEXT: slli a0, a0, 2
+; RV32I-NEXT: or a0, a2, a0
+; RV32I-NEXT: srli a2, a0, 1
+; RV32I-NEXT: lui a5, 349525
+; RV32I-NEXT: addi a5, a5, 1365
+; RV32I-NEXT: and a2, a2, a5
+; RV32I-NEXT: and a0, a0, a5
+; RV32I-NEXT: slli a0, a0, 1
+; RV32I-NEXT: or a0, a2, a0
+; RV32I-NEXT: srli a2, a1, 4
+; RV32I-NEXT: and a2, a2, a3
+; RV32I-NEXT: and a1, a1, a3
+; RV32I-NEXT: slli a1, a1, 4
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: srli a2, a1, 2
+; RV32I-NEXT: and a2, a2, a4
+; RV32I-NEXT: and a1, a1, a4
+; RV32I-NEXT: slli a1, a1, 2
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: srli a2, a1, 1
+; RV32I-NEXT: and a2, a2, a5
+; RV32I-NEXT: and a1, a1, a5
+; RV32I-NEXT: slli a1, a1, 1
+; RV32I-NEXT: or a1, a2, a1
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_bitreverse_bswap_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: lui a1, %hi(.LCPI12_0)
+; RV64I-NEXT: ld a1, %lo(.LCPI12_0)(a1)
+; RV64I-NEXT: srli a2, a0, 4
+; RV64I-NEXT: and a2, a2, a1
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, %hi(.LCPI12_1)
+; RV64I-NEXT: ld a1, %lo(.LCPI12_1)(a1)
+; RV64I-NEXT: slli a0, a0, 4
+; RV64I-NEXT: or a0, a2, a0
+; RV64I-NEXT: srli a2, a0, 2
+; RV64I-NEXT: and a2, a2, a1
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, %hi(.LCPI12_2)
+; RV64I-NEXT: ld a1, %lo(.LCPI12_2)(a1)
+; RV64I-NEXT: slli a0, a0, 2
+; RV64I-NEXT: or a0, a2, a0
+; RV64I-NEXT: srli a2, a0, 1
+; RV64I-NEXT: and a2, a2, a1
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: slli a0, a0, 1
+; RV64I-NEXT: or a0, a2, a0
+; RV64I-NEXT: ret
+;
+; RV32ZB-LABEL: test_bitreverse_bswap_i64:
+; RV32ZB: # %bb.0:
+; RV32ZB-NEXT: srli a2, a0, 4
+; RV32ZB-NEXT: lui a3, 61681
+; RV32ZB-NEXT: addi a3, a3, -241
+; RV32ZB-NEXT: and a2, a2, a3
+; RV32ZB-NEXT: and a0, a0, a3
+; RV32ZB-NEXT: slli a0, a0, 4
+; RV32ZB-NEXT: or a0, a2, a0
+; RV32ZB-NEXT: srli a2, a0, 2
+; RV32ZB-NEXT: lui a4, 209715
+; RV32ZB-NEXT: addi a4, a4, 819
+; RV32ZB-NEXT: and a2, a2, a4
+; RV32ZB-NEXT: and a0, a0, a4
+; RV32ZB-NEXT: slli a0, a0, 2
+; RV32ZB-NEXT: or a0, a2, a0
+; RV32ZB-NEXT: srli a2, a0, 1
+; RV32ZB-NEXT: lui a5, 349525
+; RV32ZB-NEXT: addi a5, a5, 1365
+; RV32ZB-NEXT: and a2, a2, a5
+; RV32ZB-NEXT: and a0, a0, a5
+; RV32ZB-NEXT: slli a0, a0, 1
+; RV32ZB-NEXT: or a0, a2, a0
+; RV32ZB-NEXT: srli a2, a1, 4
+; RV32ZB-NEXT: and a2, a2, a3
+; RV32ZB-NEXT: and a1, a1, a3
+; RV32ZB-NEXT: slli a1, a1, 4
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: srli a2, a1, 2
+; RV32ZB-NEXT: and a2, a2, a4
+; RV32ZB-NEXT: and a1, a1, a4
+; RV32ZB-NEXT: slli a1, a1, 2
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: srli a2, a1, 1
+; RV32ZB-NEXT: and a2, a2, a5
+; RV32ZB-NEXT: and a1, a1, a5
+; RV32ZB-NEXT: slli a1, a1, 1
+; RV32ZB-NEXT: or a1, a2, a1
+; RV32ZB-NEXT: ret
+;
+; RV64ZB-LABEL: test_bitreverse_bswap_i64:
+; RV64ZB: # %bb.0:
+; RV64ZB-NEXT: lui a1, %hi(.LCPI12_0)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI12_0)(a1)
+; RV64ZB-NEXT: srli a2, a0, 4
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: lui a1, %hi(.LCPI12_1)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI12_1)(a1)
+; RV64ZB-NEXT: slli a0, a0, 4
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: srli a2, a0, 2
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: lui a1, %hi(.LCPI12_2)
+; RV64ZB-NEXT: ld a1, %lo(.LCPI12_2)(a1)
+; RV64ZB-NEXT: slli a0, a0, 2
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: srli a2, a0, 1
+; RV64ZB-NEXT: and a2, a2, a1
+; RV64ZB-NEXT: and a0, a0, a1
+; RV64ZB-NEXT: slli a0, a0, 1
+; RV64ZB-NEXT: or a0, a2, a0
+; RV64ZB-NEXT: ret
+ %tmp = call i64 @llvm.bitreverse.i64(i64 %a)
+ %tmp2 = call i64 @llvm.bswap.i64(i64 %tmp)
+ ret i64 %tmp2
+}
--- /dev/null
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV32I
+; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV64I
+; RUN: llc -mtriple=riscv32 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV32ZBB
+; RUN: llc -mtriple=riscv64 -mattr=+zbb -verify-machineinstrs < %s \
+; RUN: | FileCheck %s -check-prefix=RV64ZBB
+
+declare i8 @llvm.cttz.i8(i8, i1)
+declare i16 @llvm.cttz.i16(i16, i1)
+declare i32 @llvm.cttz.i32(i32, i1)
+declare i64 @llvm.cttz.i64(i64, i1)
+declare i32 @llvm.ctlz.i32(i32, i1)
+declare i32 @llvm.ctpop.i32(i32)
+declare i64 @llvm.ctpop.i64(i64)
+
+define i8 @test_cttz_i8(i8 %a) nounwind {
+; RV32I-LABEL: test_cttz_i8:
+; RV32I: # %bb.0:
+; RV32I-NEXT: andi a1, a0, 255
+; RV32I-NEXT: beqz a1, .LBB0_2
+; RV32I-NEXT: # %bb.1: # %cond.false
+; RV32I-NEXT: addi a1, a0, -1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: andi a1, a1, 85
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: andi a1, a0, 51
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: andi a0, a0, 51
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: andi a0, a0, 15
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB0_2:
+; RV32I-NEXT: li a0, 8
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i8:
+; RV64I: # %bb.0:
+; RV64I-NEXT: andi a1, a0, 255
+; RV64I-NEXT: beqz a1, .LBB0_2
+; RV64I-NEXT: # %bb.1: # %cond.false
+; RV64I-NEXT: addi a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: andi a1, a1, 85
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: andi a1, a0, 51
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: andi a0, a0, 51
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: addw a0, a0, a1
+; RV64I-NEXT: andi a0, a0, 15
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB0_2:
+; RV64I-NEXT: li a0, 8
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i8:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: ori a0, a0, 256
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i8:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ori a0, a0, 256
+; RV64ZBB-NEXT: ctz a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i8 @llvm.cttz.i8(i8 %a, i1 false)
+ ret i8 %tmp
+}
+
+define i16 @test_cttz_i16(i16 %a) nounwind {
+; RV32I-LABEL: test_cttz_i16:
+; RV32I: # %bb.0:
+; RV32I-NEXT: slli a1, a0, 16
+; RV32I-NEXT: srli a1, a1, 16
+; RV32I-NEXT: beqz a1, .LBB1_2
+; RV32I-NEXT: # %bb.1: # %cond.false
+; RV32I-NEXT: addi a1, a0, -1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 5
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 3
+; RV32I-NEXT: addi a1, a1, 819
+; RV32I-NEXT: and a2, a0, a1
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: add a0, a2, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 1
+; RV32I-NEXT: addi a1, a1, -241
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: slli a1, a0, 8
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: slli a0, a0, 19
+; RV32I-NEXT: srli a0, a0, 27
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB1_2:
+; RV32I-NEXT: li a0, 16
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i16:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a1, a0, 48
+; RV64I-NEXT: srli a1, a1, 48
+; RV64I-NEXT: beqz a1, .LBB1_2
+; RV64I-NEXT: # %bb.1: # %cond.false
+; RV64I-NEXT: addi a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 5
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: lui a1, 3
+; RV64I-NEXT: addiw a1, a1, 819
+; RV64I-NEXT: and a2, a0, a1
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: add a0, a2, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: lui a1, 1
+; RV64I-NEXT: addiw a1, a1, -241
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: slliw a1, a0, 8
+; RV64I-NEXT: addw a0, a1, a0
+; RV64I-NEXT: slli a0, a0, 51
+; RV64I-NEXT: srli a0, a0, 59
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB1_2:
+; RV64I-NEXT: li a0, 16
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i16:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: lui a1, 16
+; RV32ZBB-NEXT: or a0, a0, a1
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i16:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: lui a1, 16
+; RV64ZBB-NEXT: or a0, a0, a1
+; RV64ZBB-NEXT: ctz a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i16 @llvm.cttz.i16(i16 %a, i1 false)
+ ret i16 %tmp
+}
+
+define i32 @test_cttz_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_cttz_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: beqz a0, .LBB2_2
+; RV32I-NEXT: # %bb.1: # %cond.false
+; RV32I-NEXT: addi sp, sp, -16
+; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: addi a1, a0, -1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi a1, a1, 819
+; RV32I-NEXT: and a2, a0, a1
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: add a0, a2, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi a1, a1, -241
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi a1, a1, 257
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB2_2:
+; RV32I-NEXT: li a0, 32
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: sext.w a1, a0
+; RV64I-NEXT: beqz a1, .LBB2_2
+; RV64I-NEXT: # %bb.1: # %cond.false
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: addiw a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: subw a0, a0, a1
+; RV64I-NEXT: lui a1, 209715
+; RV64I-NEXT: addiw a1, a1, 819
+; RV64I-NEXT: and a2, a0, a1
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: add a0, a2, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: lui a1, 61681
+; RV64I-NEXT: addiw a1, a1, -241
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, 4112
+; RV64I-NEXT: addiw a1, a1, 257
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srliw a0, a0, 24
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB2_2:
+; RV64I-NEXT: li a0, 32
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i32:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i32:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ctzw a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i32 @llvm.cttz.i32(i32 %a, i1 false)
+ ret i32 %tmp
+}
+
+define i32 @test_ctlz_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_ctlz_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: beqz a0, .LBB3_2
+; RV32I-NEXT: # %bb.1: # %cond.false
+; RV32I-NEXT: addi sp, sp, -16
+; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 16
+; RV32I-NEXT: or a0, a0, a1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi a1, a1, 819
+; RV32I-NEXT: and a2, a0, a1
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: add a0, a2, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi a1, a1, -241
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi a1, a1, 257
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+; RV32I-NEXT: .LBB3_2:
+; RV32I-NEXT: li a0, 32
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_ctlz_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: sext.w a1, a0
+; RV64I-NEXT: beqz a1, .LBB3_2
+; RV64I-NEXT: # %bb.1: # %cond.false
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: srliw a1, a0, 1
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: srliw a1, a0, 2
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: srliw a1, a0, 4
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: srliw a1, a0, 8
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: srliw a1, a0, 16
+; RV64I-NEXT: or a0, a0, a1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: subw a0, a0, a1
+; RV64I-NEXT: lui a1, 209715
+; RV64I-NEXT: addiw a1, a1, 819
+; RV64I-NEXT: and a2, a0, a1
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: add a0, a2, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: lui a1, 61681
+; RV64I-NEXT: addiw a1, a1, -241
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, 4112
+; RV64I-NEXT: addiw a1, a1, 257
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srliw a0, a0, 24
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB3_2:
+; RV64I-NEXT: li a0, 32
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_ctlz_i32:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: clz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_ctlz_i32:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: clzw a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i32 @llvm.ctlz.i32(i32 %a, i1 false)
+ ret i32 %tmp
+}
+
+define i64 @test_cttz_i64(i64 %a) nounwind {
+; RV32I-LABEL: test_cttz_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -32
+; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s5, 4(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s6, 0(sp) # 4-byte Folded Spill
+; RV32I-NEXT: mv s1, a1
+; RV32I-NEXT: mv s2, a0
+; RV32I-NEXT: addi a0, a0, -1
+; RV32I-NEXT: not a1, s2
+; RV32I-NEXT: and a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi s4, a2, 1365
+; RV32I-NEXT: and a1, a1, s4
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi s5, a1, 819
+; RV32I-NEXT: and a1, a0, s5
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, s5
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi s6, a1, -241
+; RV32I-NEXT: and a0, a0, s6
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi s3, a1, 257
+; RV32I-NEXT: mv a1, s3
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: mv s0, a0
+; RV32I-NEXT: addi a0, s1, -1
+; RV32I-NEXT: not a1, s1
+; RV32I-NEXT: and a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: and a1, a1, s4
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: and a1, a0, s5
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, s5
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: and a0, a0, s6
+; RV32I-NEXT: mv a1, s3
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: bnez s2, .LBB4_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: addi a0, a0, 32
+; RV32I-NEXT: j .LBB4_3
+; RV32I-NEXT: .LBB4_2:
+; RV32I-NEXT: srli a0, s0, 24
+; RV32I-NEXT: .LBB4_3:
+; RV32I-NEXT: li a1, 0
+; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s6, 0(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 32
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: beqz a0, .LBB4_2
+; RV64I-NEXT: # %bb.1: # %cond.false
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: addi a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, %hi(.LCPI4_0)
+; RV64I-NEXT: ld a1, %lo(.LCPI4_0)(a1)
+; RV64I-NEXT: lui a2, %hi(.LCPI4_1)
+; RV64I-NEXT: ld a2, %lo(.LCPI4_1)(a2)
+; RV64I-NEXT: srli a3, a0, 1
+; RV64I-NEXT: and a1, a3, a1
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: and a1, a0, a2
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a2, %hi(.LCPI4_2)
+; RV64I-NEXT: ld a2, %lo(.LCPI4_2)(a2)
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a1, %hi(.LCPI4_3)
+; RV64I-NEXT: ld a1, %lo(.LCPI4_3)(a1)
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srli a0, a0, 56
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+; RV64I-NEXT: .LBB4_2:
+; RV64I-NEXT: li a0, 64
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i64:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: bnez a0, .LBB4_2
+; RV32ZBB-NEXT: # %bb.1:
+; RV32ZBB-NEXT: ctz a0, a1
+; RV32ZBB-NEXT: addi a0, a0, 32
+; RV32ZBB-NEXT: li a1, 0
+; RV32ZBB-NEXT: ret
+; RV32ZBB-NEXT: .LBB4_2:
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: li a1, 0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i64:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ctz a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i64 @llvm.cttz.i64(i64 %a, i1 false)
+ ret i64 %tmp
+}
+
+define i8 @test_cttz_i8_zero_undef(i8 %a) nounwind {
+; RV32I-LABEL: test_cttz_i8_zero_undef:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi a1, a0, -1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: andi a1, a1, 85
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: andi a1, a0, 51
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: andi a0, a0, 51
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: andi a0, a0, 15
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i8_zero_undef:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: andi a1, a1, 85
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: andi a1, a0, 51
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: andi a0, a0, 51
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: addw a0, a0, a1
+; RV64I-NEXT: andi a0, a0, 15
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i8_zero_undef:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i8_zero_undef:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ctz a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i8 @llvm.cttz.i8(i8 %a, i1 true)
+ ret i8 %tmp
+}
+
+define i16 @test_cttz_i16_zero_undef(i16 %a) nounwind {
+; RV32I-LABEL: test_cttz_i16_zero_undef:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi a1, a0, -1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 5
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 3
+; RV32I-NEXT: addi a1, a1, 819
+; RV32I-NEXT: and a2, a0, a1
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: add a0, a2, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 1
+; RV32I-NEXT: addi a1, a1, -241
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: slli a1, a0, 8
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: slli a0, a0, 19
+; RV32I-NEXT: srli a0, a0, 27
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i16_zero_undef:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 5
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: lui a1, 3
+; RV64I-NEXT: addiw a1, a1, 819
+; RV64I-NEXT: and a2, a0, a1
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: add a0, a2, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: lui a1, 1
+; RV64I-NEXT: addiw a1, a1, -241
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: slliw a1, a0, 8
+; RV64I-NEXT: addw a0, a1, a0
+; RV64I-NEXT: slli a0, a0, 51
+; RV64I-NEXT: srli a0, a0, 59
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i16_zero_undef:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i16_zero_undef:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ctz a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i16 @llvm.cttz.i16(i16 %a, i1 true)
+ ret i16 %tmp
+}
+
+define i32 @test_cttz_i32_zero_undef(i32 %a) nounwind {
+; RV32I-LABEL: test_cttz_i32_zero_undef:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -16
+; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: addi a1, a0, -1
+; RV32I-NEXT: not a0, a0
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi a1, a1, 819
+; RV32I-NEXT: and a2, a0, a1
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: add a0, a2, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi a1, a1, -241
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi a1, a1, 257
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i32_zero_undef:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: addiw a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: subw a0, a0, a1
+; RV64I-NEXT: lui a1, 209715
+; RV64I-NEXT: addiw a1, a1, 819
+; RV64I-NEXT: and a2, a0, a1
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: add a0, a2, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: lui a1, 61681
+; RV64I-NEXT: addiw a1, a1, -241
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, 4112
+; RV64I-NEXT: addiw a1, a1, 257
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srliw a0, a0, 24
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i32_zero_undef:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i32_zero_undef:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ctzw a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i32 @llvm.cttz.i32(i32 %a, i1 true)
+ ret i32 %tmp
+}
+
+define i64 @test_cttz_i64_zero_undef(i64 %a) nounwind {
+; RV32I-LABEL: test_cttz_i64_zero_undef:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -32
+; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s5, 4(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s6, 0(sp) # 4-byte Folded Spill
+; RV32I-NEXT: mv s1, a1
+; RV32I-NEXT: mv s2, a0
+; RV32I-NEXT: addi a0, a0, -1
+; RV32I-NEXT: not a1, s2
+; RV32I-NEXT: and a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi s4, a2, 1365
+; RV32I-NEXT: and a1, a1, s4
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi s5, a1, 819
+; RV32I-NEXT: and a1, a0, s5
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, s5
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi s6, a1, -241
+; RV32I-NEXT: and a0, a0, s6
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi s3, a1, 257
+; RV32I-NEXT: mv a1, s3
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: mv s0, a0
+; RV32I-NEXT: addi a0, s1, -1
+; RV32I-NEXT: not a1, s1
+; RV32I-NEXT: and a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: and a1, a1, s4
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: and a1, a0, s5
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, s5
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: and a0, a0, s6
+; RV32I-NEXT: mv a1, s3
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: bnez s2, .LBB8_2
+; RV32I-NEXT: # %bb.1:
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: addi a0, a0, 32
+; RV32I-NEXT: j .LBB8_3
+; RV32I-NEXT: .LBB8_2:
+; RV32I-NEXT: srli a0, s0, 24
+; RV32I-NEXT: .LBB8_3:
+; RV32I-NEXT: li a1, 0
+; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s6, 0(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 32
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_cttz_i64_zero_undef:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: addi a1, a0, -1
+; RV64I-NEXT: not a0, a0
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, %hi(.LCPI8_0)
+; RV64I-NEXT: ld a1, %lo(.LCPI8_0)(a1)
+; RV64I-NEXT: lui a2, %hi(.LCPI8_1)
+; RV64I-NEXT: ld a2, %lo(.LCPI8_1)(a2)
+; RV64I-NEXT: srli a3, a0, 1
+; RV64I-NEXT: and a1, a3, a1
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: and a1, a0, a2
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a2, %hi(.LCPI8_2)
+; RV64I-NEXT: ld a2, %lo(.LCPI8_2)(a2)
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a1, %hi(.LCPI8_3)
+; RV64I-NEXT: ld a1, %lo(.LCPI8_3)(a1)
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srli a0, a0, 56
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_cttz_i64_zero_undef:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: bnez a0, .LBB8_2
+; RV32ZBB-NEXT: # %bb.1:
+; RV32ZBB-NEXT: ctz a0, a1
+; RV32ZBB-NEXT: addi a0, a0, 32
+; RV32ZBB-NEXT: li a1, 0
+; RV32ZBB-NEXT: ret
+; RV32ZBB-NEXT: .LBB8_2:
+; RV32ZBB-NEXT: ctz a0, a0
+; RV32ZBB-NEXT: li a1, 0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_cttz_i64_zero_undef:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: ctz a0, a0
+; RV64ZBB-NEXT: ret
+ %tmp = call i64 @llvm.cttz.i64(i64 %a, i1 true)
+ ret i64 %tmp
+}
+
+define i32 @test_ctpop_i32(i32 %a) nounwind {
+; RV32I-LABEL: test_ctpop_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -16
+; RV32I-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi a2, a2, 1365
+; RV32I-NEXT: and a1, a1, a2
+; RV32I-NEXT: sub a0, a0, a1
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi a1, a1, 819
+; RV32I-NEXT: and a2, a0, a1
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: add a0, a2, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi a1, a1, -241
+; RV32I-NEXT: and a0, a0, a1
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi a1, a1, 257
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 16
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_ctpop_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: lui a2, 349525
+; RV64I-NEXT: addiw a2, a2, 1365
+; RV64I-NEXT: and a1, a1, a2
+; RV64I-NEXT: subw a0, a0, a1
+; RV64I-NEXT: lui a1, 209715
+; RV64I-NEXT: addiw a1, a1, 819
+; RV64I-NEXT: and a2, a0, a1
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: add a0, a2, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: lui a1, 61681
+; RV64I-NEXT: addiw a1, a1, -241
+; RV64I-NEXT: and a0, a0, a1
+; RV64I-NEXT: lui a1, 4112
+; RV64I-NEXT: addiw a1, a1, 257
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srliw a0, a0, 24
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_ctpop_i32:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: cpop a0, a0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_ctpop_i32:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: cpopw a0, a0
+; RV64ZBB-NEXT: ret
+ %1 = call i32 @llvm.ctpop.i32(i32 %a)
+ ret i32 %1
+}
+
+define i64 @test_ctpop_i64(i64 %a) nounwind {
+; RV32I-LABEL: test_ctpop_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: addi sp, sp, -32
+; RV32I-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
+; RV32I-NEXT: sw s5, 4(sp) # 4-byte Folded Spill
+; RV32I-NEXT: mv s0, a0
+; RV32I-NEXT: srli a0, a1, 1
+; RV32I-NEXT: lui a2, 349525
+; RV32I-NEXT: addi s2, a2, 1365
+; RV32I-NEXT: and a0, a0, s2
+; RV32I-NEXT: sub a0, a1, a0
+; RV32I-NEXT: lui a1, 209715
+; RV32I-NEXT: addi s3, a1, 819
+; RV32I-NEXT: and a1, a0, s3
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, s3
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: lui a1, 61681
+; RV32I-NEXT: addi s4, a1, -241
+; RV32I-NEXT: and a0, a0, s4
+; RV32I-NEXT: lui a1, 4112
+; RV32I-NEXT: addi s1, a1, 257
+; RV32I-NEXT: mv a1, s1
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: srli s5, a0, 24
+; RV32I-NEXT: srli a0, s0, 1
+; RV32I-NEXT: and a0, a0, s2
+; RV32I-NEXT: sub a0, s0, a0
+; RV32I-NEXT: and a1, a0, s3
+; RV32I-NEXT: srli a0, a0, 2
+; RV32I-NEXT: and a0, a0, s3
+; RV32I-NEXT: add a0, a1, a0
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: add a0, a0, a1
+; RV32I-NEXT: and a0, a0, s4
+; RV32I-NEXT: mv a1, s1
+; RV32I-NEXT: call __mulsi3@plt
+; RV32I-NEXT: srli a0, a0, 24
+; RV32I-NEXT: add a0, a0, s5
+; RV32I-NEXT: li a1, 0
+; RV32I-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
+; RV32I-NEXT: lw s5, 4(sp) # 4-byte Folded Reload
+; RV32I-NEXT: addi sp, sp, 32
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_ctpop_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: addi sp, sp, -16
+; RV64I-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
+; RV64I-NEXT: lui a1, %hi(.LCPI10_0)
+; RV64I-NEXT: ld a1, %lo(.LCPI10_0)(a1)
+; RV64I-NEXT: lui a2, %hi(.LCPI10_1)
+; RV64I-NEXT: ld a2, %lo(.LCPI10_1)(a2)
+; RV64I-NEXT: srli a3, a0, 1
+; RV64I-NEXT: and a1, a3, a1
+; RV64I-NEXT: sub a0, a0, a1
+; RV64I-NEXT: and a1, a0, a2
+; RV64I-NEXT: srli a0, a0, 2
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a2, %hi(.LCPI10_2)
+; RV64I-NEXT: ld a2, %lo(.LCPI10_2)(a2)
+; RV64I-NEXT: add a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: add a0, a0, a1
+; RV64I-NEXT: and a0, a0, a2
+; RV64I-NEXT: lui a1, %hi(.LCPI10_3)
+; RV64I-NEXT: ld a1, %lo(.LCPI10_3)(a1)
+; RV64I-NEXT: call __muldi3@plt
+; RV64I-NEXT: srli a0, a0, 56
+; RV64I-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
+; RV64I-NEXT: addi sp, sp, 16
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_ctpop_i64:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: cpop a1, a1
+; RV32ZBB-NEXT: cpop a0, a0
+; RV32ZBB-NEXT: add a0, a0, a1
+; RV32ZBB-NEXT: li a1, 0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_ctpop_i64:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: cpop a0, a0
+; RV64ZBB-NEXT: ret
+ %1 = call i64 @llvm.ctpop.i64(i64 %a)
+ ret i64 %1
+}
+
+define i32 @test_parity_i32(i32 %a) {
+; RV32I-LABEL: test_parity_i32:
+; RV32I: # %bb.0:
+; RV32I-NEXT: srli a1, a0, 16
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: andi a0, a0, 1
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_parity_i32:
+; RV64I: # %bb.0:
+; RV64I-NEXT: slli a1, a0, 32
+; RV64I-NEXT: srli a1, a1, 32
+; RV64I-NEXT: srliw a0, a0, 16
+; RV64I-NEXT: xor a0, a1, a0
+; RV64I-NEXT: srli a1, a0, 8
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: andi a0, a0, 1
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_parity_i32:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: cpop a0, a0
+; RV32ZBB-NEXT: andi a0, a0, 1
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_parity_i32:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: cpopw a0, a0
+; RV64ZBB-NEXT: andi a0, a0, 1
+; RV64ZBB-NEXT: ret
+ %1 = call i32 @llvm.ctpop.i32(i32 %a)
+ %2 = and i32 %1, 1
+ ret i32 %2
+}
+
+define i64 @test_parity_i64(i64 %a) {
+; RV32I-LABEL: test_parity_i64:
+; RV32I: # %bb.0:
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 16
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 8
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 4
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 2
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: srli a1, a0, 1
+; RV32I-NEXT: xor a0, a0, a1
+; RV32I-NEXT: andi a0, a0, 1
+; RV32I-NEXT: li a1, 0
+; RV32I-NEXT: ret
+;
+; RV64I-LABEL: test_parity_i64:
+; RV64I: # %bb.0:
+; RV64I-NEXT: srli a1, a0, 32
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 16
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 8
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 4
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 2
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: srli a1, a0, 1
+; RV64I-NEXT: xor a0, a0, a1
+; RV64I-NEXT: andi a0, a0, 1
+; RV64I-NEXT: ret
+;
+; RV32ZBB-LABEL: test_parity_i64:
+; RV32ZBB: # %bb.0:
+; RV32ZBB-NEXT: xor a0, a0, a1
+; RV32ZBB-NEXT: cpop a0, a0
+; RV32ZBB-NEXT: andi a0, a0, 1
+; RV32ZBB-NEXT: li a1, 0
+; RV32ZBB-NEXT: ret
+;
+; RV64ZBB-LABEL: test_parity_i64:
+; RV64ZBB: # %bb.0:
+; RV64ZBB-NEXT: cpop a0, a0
+; RV64ZBB-NEXT: andi a0, a0, 1
+; RV64ZBB-NEXT: ret
+ %1 = call i64 @llvm.ctpop.i64(i64 %a)
+ %2 = and i64 %1, 1
+ ret i64 %2
+}