From 9602c7a0817f34fb4d01194119fe4b75c00ea5ed Mon Sep 17 00:00:00 2001 From: Carl Ritson Date: Thu, 18 May 2023 13:27:58 +0900 Subject: [PATCH] [AMDGPU][Uniformity] V_MBCNT* is never uniform Mark V_MBCNT instructions add thread/lane position so will never be uniform. Reviewed By: foad Differential Revision: https://reviews.llvm.org/D150759 --- llvm/lib/Target/AMDGPU/VOP2Instructions.td | 2 ++ .../AMDGPU/MIR/never-uniform.mir | 23 ++++++++++++++++++++++ 2 files changed, 25 insertions(+) diff --git a/llvm/lib/Target/AMDGPU/VOP2Instructions.td b/llvm/lib/Target/AMDGPU/VOP2Instructions.td index 446e7d0..9442b1f 100644 --- a/llvm/lib/Target/AMDGPU/VOP2Instructions.td +++ b/llvm/lib/Target/AMDGPU/VOP2Instructions.td @@ -773,8 +773,10 @@ def V_WRITELANE_B32 : VOP2_Pseudo<"v_writelane_b32", VOP_WRITELANE, let isReMaterializable = 1 in { defm V_BFM_B32 : VOP2Inst <"v_bfm_b32", VOP_I32_I32_I32>; defm V_BCNT_U32_B32 : VOP2Inst <"v_bcnt_u32_b32", VOP_I32_I32_I32, add_ctpop>; +let IsNeverUniform = 1 in { defm V_MBCNT_LO_U32_B32 : VOP2Inst <"v_mbcnt_lo_u32_b32", VOP_I32_I32_I32, int_amdgcn_mbcnt_lo>; defm V_MBCNT_HI_U32_B32 : VOP2Inst <"v_mbcnt_hi_u32_b32", VOP_I32_I32_I32, int_amdgcn_mbcnt_hi>; +} // End IsNeverUniform = 1 defm V_LDEXP_F32 : VOP2Inst <"v_ldexp_f32", VOP_F32_F32_I32, AMDGPUldexp>; let ReadsModeReg = 0, mayRaiseFPException = 0 in { diff --git a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/never-uniform.mir b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/never-uniform.mir index fa22890..9a7e755 100644 --- a/llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/never-uniform.mir +++ b/llvm/test/Analysis/UniformityAnalysis/AMDGPU/MIR/never-uniform.mir @@ -140,3 +140,26 @@ body: | %5:vgpr_32 = V_AND_B32_e32 $vgpr4, $vgpr5, implicit $exec S_ENDPGM 0 ... +# mbcnt instructions are not uniform +--- +name: mbcnt_lo +machineFunctionInfo: + isEntryFunction: true +body: | + bb.0: + ; CHECK-LABEL: MachineUniformityInfo for function: mbcnt_lo + ; CHECK: DIVERGENT: %0 + %0:vgpr_32 = V_MBCNT_LO_U32_B32_e64 -1, 0, implicit $exec + S_ENDPGM 0 +... +--- +name: mbcnt_hi +machineFunctionInfo: + isEntryFunction: true +body: | + bb.0: + ; CHECK-LABEL: MachineUniformityInfo for function: mbcnt_hi + ; CHECK: DIVERGENT: %0 + %0:vgpr_32 = V_MBCNT_HI_U32_B32_e64 -1, 0, implicit $exec + S_ENDPGM 0 +... -- 2.7.4