From: Thomas Symalla Date: Tue, 9 May 2023 15:24:00 +0000 (+0200) Subject: [NFC][AMDGPU] Add option to test. X-Git-Tag: upstream/17.0.6~9006 X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=60a4cb707658b6b99d9263cae9957a4c64ad96d3;p=platform%2Fupstream%2Fllvm.git [NFC][AMDGPU] Add option to test. --- diff --git a/llvm/test/CodeGen/AMDGPU/fold-fabs.ll b/llvm/test/CodeGen/AMDGPU/fold-fabs.ll index 6171d9c..cd3cbb4 100644 --- a/llvm/test/CodeGen/AMDGPU/fold-fabs.ll +++ b/llvm/test/CodeGen/AMDGPU/fold-fabs.ll @@ -1,5 +1,5 @@ ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2 -; RUN: llc -march=amdgcn -mcpu=gfx1030 -verify-machineinstrs -start-before=amdgpu-late-codegenprepare < %s | FileCheck -check-prefix=GFX10 %s +; RUN: llc -march=amdgcn -mcpu=gfx1030 -verify-machineinstrs -disable-machine-sink=1 -start-before=amdgpu-late-codegenprepare < %s | FileCheck -check-prefix=GFX10 %s define float @fold_abs_in_branch(float %arg1, float %arg2) { ; GFX10-LABEL: fold_abs_in_branch: @@ -10,10 +10,10 @@ define float @fold_abs_in_branch(float %arg1, float %arg2) { ; GFX10-NEXT: s_mov_b32 s4, exec_lo ; GFX10-NEXT: v_add_f32_e32 v1, v0, v1 ; GFX10-NEXT: v_add_f32_e64 v0, |v1|, |v1| +; GFX10-NEXT: v_and_b32_e32 v1, 0x7fffffff, v1 ; GFX10-NEXT: v_cmpx_nlt_f32_e32 1.0, v0 ; GFX10-NEXT: ; %bb.1: ; %if -; GFX10-NEXT: v_and_b32_e32 v0, 0x7fffffff, v1 -; GFX10-NEXT: v_mul_f32_e32 v0, 0x3e4ccccd, v0 +; GFX10-NEXT: v_mul_f32_e32 v0, 0x3e4ccccd, v1 ; GFX10-NEXT: ; %bb.2: ; %exit ; GFX10-NEXT: s_or_b32 exec_lo, exec_lo, s4 ; GFX10-NEXT: s_setpc_b64 s[30:31] @@ -40,10 +40,10 @@ define float @fold_abs_in_branch_undef(float %arg1, float %arg2) { ; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX10-NEXT: s_waitcnt_vscnt null, 0x0 ; GFX10-NEXT: v_add_f32_e64 v0, |s4|, |s4| +; GFX10-NEXT: s_bitset0_b32 s4, 31 ; GFX10-NEXT: v_cmp_lt_f32_e32 vcc_lo, 1.0, v0 ; GFX10-NEXT: s_cbranch_vccnz .LBB1_2 ; GFX10-NEXT: ; %bb.1: ; %if -; GFX10-NEXT: s_bitset0_b32 s4, 31 ; GFX10-NEXT: v_mul_f32_e64 v0, 0x3e4ccccd, s4 ; GFX10-NEXT: .LBB1_2: ; %exit ; GFX10-NEXT: s_setpc_b64 s[30:31] @@ -70,10 +70,10 @@ define float @fold_abs_in_branch_poison(float %arg1, float %arg2) { ; GFX10-NEXT: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0) ; GFX10-NEXT: s_waitcnt_vscnt null, 0x0 ; GFX10-NEXT: v_add_f32_e64 v0, |s4|, |s4| +; GFX10-NEXT: s_bitset0_b32 s4, 31 ; GFX10-NEXT: v_cmp_lt_f32_e32 vcc_lo, 1.0, v0 ; GFX10-NEXT: s_cbranch_vccnz .LBB2_2 ; GFX10-NEXT: ; %bb.1: ; %if -; GFX10-NEXT: s_bitset0_b32 s4, 31 ; GFX10-NEXT: v_mul_f32_e64 v0, 0x3e4ccccd, s4 ; GFX10-NEXT: .LBB2_2: ; %exit ; GFX10-NEXT: s_setpc_b64 s[30:31] @@ -103,10 +103,10 @@ define float @fold_abs_in_branch_fabs(float %arg1, float %arg2) { ; GFX10-NEXT: s_mov_b32 s4, exec_lo ; GFX10-NEXT: v_add_f32_e32 v1, v0, v1 ; GFX10-NEXT: v_add_f32_e64 v0, |v1|, |v1| +; GFX10-NEXT: v_and_b32_e32 v1, 0x7fffffff, v1 ; GFX10-NEXT: v_cmpx_nlt_f32_e32 1.0, v0 ; GFX10-NEXT: ; %bb.1: ; %if -; GFX10-NEXT: v_and_b32_e32 v0, 0x7fffffff, v1 -; GFX10-NEXT: v_mul_f32_e64 v0, 0x3e4ccccd, |v0| +; GFX10-NEXT: v_mul_f32_e64 v0, 0x3e4ccccd, |v1| ; GFX10-NEXT: ; %bb.2: ; %exit ; GFX10-NEXT: s_or_b32 exec_lo, exec_lo, s4 ; GFX10-NEXT: s_setpc_b64 s[30:31]