SelectionDAG: Teach ComputeKnownBits about VSCALE

This reverts commit 9b92f70d4758f75903ce93feaba5098130820d40.  The issue
with the re-applied change was an implicit truncation due to the
multiplication.  Although the operations were converted to `APInt`, the
values were implicitly converted to `long` due to the typing rules.

Fixes: #59594

Differential Revision: https://reviews.llvm.org/D140347

diff --git a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
index 473497a..cad9417 100644 (file)
--- a/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
@@ -3095,6 +3095,12 @@ KnownBits SelectionDAG::computeKnownBits(SDValue Op, const APInt &DemandedElts,
     }
     break;
   }
+  case ISD::VSCALE: {
+    const Function &F = getMachineFunction().getFunction();
+    const APInt &Multiplier = Op.getConstantOperandAPInt(0);
+    Known = getVScaleRange(&F, BitWidth).multiply(Multiplier).toKnownBits();
+    break;
+  }
   case ISD::CONCAT_VECTORS: {
     if (Op.getValueType().isScalableVector())
       break;

diff --git a/llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll b/llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll
index 895f5da..dbdab79 100644 (file)
--- a/llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll
+++ b/llvm/test/CodeGen/AArch64/vscale-and-sve-cnt-demandedbits.ll
@@ -14,9 +14,8 @@ define i32 @vscale_and_elimination() vscale_range(1,16) {
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    rdvl x8, #1
 ; CHECK-NEXT:    lsr x8, x8, #4
-; CHECK-NEXT:    and w9, w8, #0x1f
-; CHECK-NEXT:    and w8, w8, #0xfffffffc
-; CHECK-NEXT:    add w0, w9, w8
+; CHECK-NEXT:    and w9, w8, #0x1c
+; CHECK-NEXT:    add w0, w8, w9
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %and_redundant = and i32 %vscale, 31
@@ -85,8 +84,7 @@ define i64 @vscale_trunc_zext() vscale_range(1,16) {
 ; CHECK-LABEL: vscale_trunc_zext:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    rdvl x8, #1
-; CHECK-NEXT:    lsr x8, x8, #4
-; CHECK-NEXT:    and x0, x8, #0xffffffff
+; CHECK-NEXT:    lsr x0, x8, #4
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %zext = zext i32 %vscale to i64
@@ -97,8 +95,7 @@ define i64 @vscale_trunc_sext() vscale_range(1,16) {
 ; CHECK-LABEL: vscale_trunc_sext:
 ; CHECK:       // %bb.0:
 ; CHECK-NEXT:    rdvl x8, #1
-; CHECK-NEXT:    lsr x8, x8, #4
-; CHECK-NEXT:    sxtw x0, w8
+; CHECK-NEXT:    lsr x0, x8, #4
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %sext = sext i32 %vscale to i64
@@ -200,9 +197,8 @@ define i32 @vscale_with_multiplier() vscale_range(1,16) {
 ; CHECK-NEXT:    mov w9, #5
 ; CHECK-NEXT:    lsr x8, x8, #4
 ; CHECK-NEXT:    mul x8, x8, x9
-; CHECK-NEXT:    and w9, w8, #0x7f
-; CHECK-NEXT:    and w8, w8, #0x3f
-; CHECK-NEXT:    add w0, w9, w8
+; CHECK-NEXT:    and w9, w8, #0x3f
+; CHECK-NEXT:    add w0, w8, w9
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %mul = mul i32 %vscale, 5
@@ -219,9 +215,8 @@ define i32 @vscale_with_negative_multiplier() vscale_range(1,16) {
 ; CHECK-NEXT:    mov x9, #-5
 ; CHECK-NEXT:    lsr x8, x8, #4
 ; CHECK-NEXT:    mul x8, x8, x9
-; CHECK-NEXT:    orr w9, w8, #0xffffff80
-; CHECK-NEXT:    and w8, w8, #0xffffffc0
-; CHECK-NEXT:    add w0, w9, w8
+; CHECK-NEXT:    and w9, w8, #0xffffffc0
+; CHECK-NEXT:    add w0, w8, w9
 ; CHECK-NEXT:    ret
   %vscale = call i32 @llvm.vscale.i32()
   %mul = mul i32 %vscale, -5
@@ -231,6 +226,22 @@ define i32 @vscale_with_negative_multiplier() vscale_range(1,16) {
   ret i32 %result
 }
 
+define i32 @pow2_vscale_with_negative_multiplier() vscale_range(1,16) {
+; CHECK-LABEL: pow2_vscale_with_negative_multiplier:
+; CHECK:       // %bb.0:
+; CHECK-NEXT:    cntd x8
+; CHECK-NEXT:    neg x8, x8
+; CHECK-NEXT:    orr w9, w8, #0xfffffff0
+; CHECK-NEXT:    add w0, w8, w9
+; CHECK-NEXT:    ret
+  %vscale = call i32 @llvm.vscale.i32()
+  %mul = mul i32 %vscale, -2
+  %or_redundant = or i32 %mul, 4294967264
+  %or_required = or i32 %mul, 4294967280
+  %result = add i32 %or_redundant, %or_required
+  ret i32 %result
+}
+
 declare i32 @llvm.vscale.i32()
 declare i64 @llvm.aarch64.sve.cntb(i32 %pattern)
 declare i64 @llvm.aarch64.sve.cnth(i32 %pattern)

diff --git a/llvm/test/CodeGen/RISCV/vscale-demanded-bits.ll b/llvm/test/CodeGen/RISCV/vscale-demanded-bits.ll
new file mode 100644 (file)
index 0000000..d010efc
--- /dev/null
+++ b/llvm/test/CodeGen/RISCV/vscale-demanded-bits.ll
@@ -0,0 +1,25 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple riscv64 -mattr +v -filetype asm -o - %s | FileCheck %s
+
+declare i8 @llvm.vscale.i8()
+declare <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
+
+define <vscale x 8 x i8> @f() #0 {
+; CHECK-LABEL: f:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    csrr a0, vlenb
+; CHECK-NEXT:    vsetvli a1, zero, e8, m1, ta, ma
+; CHECK-NEXT:    vid.v v8
+; CHECK-NEXT:    vadd.vx v8, v8, a0
+; CHECK-NEXT:    ret
+entry:
+  %0 = tail call i8 @llvm.vscale.i8()
+  %1 = shl i8 %0, 3
+  %.splat.insert = insertelement <vscale x 8 x i8> poison, i8 %1, i64 0
+  %.splat = shufflevector <vscale x 8 x i8> %.splat.insert, <vscale x 8 x i8> poison, <vscale x 8 x i32> zeroinitializer
+  %2 = tail call <vscale x 8 x i8> @llvm.experimental.stepvector.nxv8i8()
+  %3 = add <vscale x 8 x i8> %2, %.splat
+  ret <vscale x 8 x i8> %3
+}
+
+attributes #0 = { vscale_range(2,1024) }