[llvm] 9ca1323 - [AMDGPU] Fix crash due to missing check for FLAT instructions that dont use vector registers when computing VALU hazard (#123627)
via llvm-commits
llvm-commits at lists.llvm.org
Tue Jan 21 05:51:03 PST 2025
Author: Chinmay Deshpande
Date: 2025-01-21T05:50:58-08:00
New Revision: 9ca1323de1ad2583b02930d2ee5721c96f2d3a51
URL: https://github.com/llvm/llvm-project/commit/9ca1323de1ad2583b02930d2ee5721c96f2d3a51
DIFF: https://github.com/llvm/llvm-project/commit/9ca1323de1ad2583b02930d2ee5721c96f2d3a51.diff
LOG: [AMDGPU] Fix crash due to missing check for FLAT instructions that dont use vector registers when computing VALU hazard (#123627)
Added:
llvm/test/CodeGen/AMDGPU/fix-crash-valu-hazard.ll
llvm/test/CodeGen/AMDGPU/hazard-flat-instruction-valu-check.mir
Modified:
llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
Removed:
################################################################################
diff --git a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
index 6baef137df5e16..873d18e30a430a 100644
--- a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -858,9 +858,12 @@ int GCNHazardRecognizer::createsVALUHazard(const MachineInstr &MI) {
}
if (TII->isFLAT(MI)) {
- int DataIdx = AMDGPU::getNamedOperandIdx(Opcode, AMDGPU::OpName::vdata);
- if (AMDGPU::getRegBitWidth(Desc.operands()[DataIdx].RegClass) > 64)
- return DataIdx;
+ // There is no hazard if the instruction does not use vector regs
+ if (VDataIdx == -1)
+ return -1;
+
+ if (AMDGPU::getRegBitWidth(VDataRCID) > 64)
+ return VDataIdx;
}
return -1;
diff --git a/llvm/test/CodeGen/AMDGPU/fix-crash-valu-hazard.ll b/llvm/test/CodeGen/AMDGPU/fix-crash-valu-hazard.ll
new file mode 100644
index 00000000000000..87811968c78711
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/fix-crash-valu-hazard.ll
@@ -0,0 +1,67 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple=amdgcn -mcpu=gfx942 < %s | FileCheck -check-prefix=GFX942 %s
+; RUN: llc -mtriple=amdgcn -mcpu=gfx90a -O0 < %s | FileCheck -check-prefix=GFX90A %s
+
+ at G = addrspace(1) global <2 x i32> splat (i32 5)
+
+define amdgpu_ps void @global_load_lds_dword_saddr(ptr addrspace(1) inreg nocapture %gptr, ptr addrspace(3) nocapture %lptr) {
+; GFX942-LABEL: global_load_lds_dword_saddr:
+; GFX942: ; %bb.0: ; %main_body
+; GFX942-NEXT: v_readfirstlane_b32 s2, v0
+; GFX942-NEXT: v_mov_b32_e32 v2, 0
+; GFX942-NEXT: s_mov_b32 m0, s2
+; GFX942-NEXT: s_nop 0
+; GFX942-NEXT: global_load_lds_dword v2, s[0:1] offset:32 nt
+; GFX942-NEXT: s_getpc_b64 s[0:1]
+; GFX942-NEXT: s_add_u32 s0, s0, G at gotpcrel32@lo+4
+; GFX942-NEXT: s_addc_u32 s1, s1, G at gotpcrel32@hi+12
+; GFX942-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
+; GFX942-NEXT: s_load_dwordx2 s[2:3], s[0:1], 0x0
+; GFX942-NEXT: s_waitcnt lgkmcnt(0)
+; GFX942-NEXT: s_mul_i32 s3, s3, 10
+; GFX942-NEXT: s_mul_i32 s2, s2, 10
+; GFX942-NEXT: v_mov_b32_e32 v0, s2
+; GFX942-NEXT: v_mov_b32_e32 v1, s3
+; GFX942-NEXT: global_store_dwordx2 v2, v[0:1], s[0:1]
+; GFX942-NEXT: s_endpgm
+;
+; GFX90A-LABEL: global_load_lds_dword_saddr:
+; GFX90A: ; %bb.0: ; %main_body
+; GFX90A-NEXT: v_mov_b32_e32 v1, v0
+; GFX90A-NEXT: s_mov_b32 s2, s0
+; GFX90A-NEXT: ; kill: def $sgpr2 killed $sgpr2 def $sgpr2_sgpr3
+; GFX90A-NEXT: s_mov_b32 s3, s1
+; GFX90A-NEXT: ; kill: def $sgpr0_sgpr1 killed $sgpr2_sgpr3
+; GFX90A-NEXT: s_getpc_b64 s[0:1]
+; GFX90A-NEXT: s_add_u32 s0, s0, G at gotpcrel32@lo+4
+; GFX90A-NEXT: s_addc_u32 s1, s1, G at gotpcrel32@hi+12
+; GFX90A-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x0
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
+; GFX90A-NEXT: s_load_dwordx2 s[8:9], s[0:1], 0x0
+; GFX90A-NEXT: v_mov_b32_e32 v0, 0
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
+; GFX90A-NEXT: s_mov_b32 s4, s9
+; GFX90A-NEXT: s_mov_b32 s6, 10
+; GFX90A-NEXT: s_mul_i32 s4, s4, s6
+; GFX90A-NEXT: s_mov_b32 s5, s8
+; GFX90A-NEXT: s_mul_i32 s5, s5, s6
+; GFX90A-NEXT: v_mov_b32_e32 v2, s5
+; GFX90A-NEXT: v_mov_b32_e32 v4, s4
+; GFX90A-NEXT: ; kill: def $vgpr2 killed $vgpr2 def $vgpr2_vgpr3 killed $exec
+; GFX90A-NEXT: v_mov_b32_e32 v3, v4
+; GFX90A-NEXT: ; implicit-def: $sgpr4
+; GFX90A-NEXT: v_readfirstlane_b32 s4, v1
+; GFX90A-NEXT: s_mov_b32 m0, s4
+; GFX90A-NEXT: s_nop 0
+; GFX90A-NEXT: global_load_dword v0, s[2:3] offset:32 slc lds
+; GFX90A-NEXT: s_waitcnt lgkmcnt(0)
+; GFX90A-NEXT: global_store_dwordx2 v0, v[2:3], s[0:1]
+; GFX90A-NEXT: s_endpgm
+main_body:
+ %LGV = load <2 x i32>, ptr addrspace(1) @G, align 8
+ %B = mul <2 x i32> %LGV, splat (i32 10)
+ call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) %gptr, ptr addrspace(3) %lptr, i32 4, i32 32, i32 2)
+ store <2 x i32> %B, ptr addrspace(1) @G, align 8
+ ret void
+}
diff --git a/llvm/test/CodeGen/AMDGPU/hazard-flat-instruction-valu-check.mir b/llvm/test/CodeGen/AMDGPU/hazard-flat-instruction-valu-check.mir
new file mode 100644
index 00000000000000..9a284258bc9f9f
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/hazard-flat-instruction-valu-check.mir
@@ -0,0 +1,20 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx942 -verify-machineinstrs -run-pass=post-RA-hazard-rec %s -o - | FileCheck -check-prefix=GCN %s
+
+---
+name: test_flat_valu_hazard
+noVRegs: true
+body: |
+ bb.0:
+ liveins: $vgpr0, $vgpr1
+
+ ; GCN-LABEL: name: test_flat_valu_hazard
+ ; GCN: liveins: $vgpr0, $vgpr1
+ ; GCN-NEXT: {{ $}}
+ ; GCN-NEXT: GLOBAL_LOAD_LDS_DWORD_SADDR killed $sgpr0_sgpr1, killed $vgpr0, 32, 2, implicit $m0, implicit $exec
+ ; GCN-NEXT: $vgpr0 = V_MOV_B32_e32 killed $vgpr1, implicit $exec, implicit $exec
+ ; GCN-NEXT: FLAT_STORE_DWORDX2 killed renamable $vgpr2_vgpr3, killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+ GLOBAL_LOAD_LDS_DWORD_SADDR killed $sgpr0_sgpr1, killed $vgpr0, 32, 2, implicit $m0, implicit $exec
+ $vgpr0 = V_MOV_B32_e32 killed $vgpr1, implicit $exec, implicit $exec
+ FLAT_STORE_DWORDX2 killed renamable $vgpr2_vgpr3, killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr
+...
More information about the llvm-commits
mailing list