[llvm] 42b0884 - [AMDGPU] Handle V_PERMLANE64_B32 in fixVcmpxPermlaneHazards (#79125)

[via llvm-commits]

Author: Pierre van Houtryve
Date: 2024-01-23T13:10:58+01:00
New Revision: 42b0884238aa3149785ac75fe983e3d6c7715a11

URL: https://github.com/llvm/llvm-project/commit/42b0884238aa3149785ac75fe983e3d6c7715a11
DIFF: https://github.com/llvm/llvm-project/commit/42b0884238aa3149785ac75fe983e3d6c7715a11.diff

LOG: [AMDGPU] Handle V_PERMLANE64_B32 in fixVcmpxPermlaneHazards (#79125)

Fixes #78856

Added: 
    

Modified: 
    llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
    llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard.mir

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
index ebad40b641820ed..b6e4e65ff5b03b5 100644
--- a/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
+++ b/llvm/lib/Target/AMDGPU/GCNHazardRecognizer.cpp
@@ -163,6 +163,7 @@ static bool isSendMsgTraceDataOrGDS(const SIInstrInfo &TII,
 static bool isPermlane(const MachineInstr &MI) {
   unsigned Opcode = MI.getOpcode();
   return Opcode == AMDGPU::V_PERMLANE16_B32_e64 ||
+         Opcode == AMDGPU::V_PERMLANE64_B32 ||
          Opcode == AMDGPU::V_PERMLANEX16_B32_e64 ||
          Opcode == AMDGPU::V_PERMLANE16_VAR_B32_e64 ||
          Opcode == AMDGPU::V_PERMLANEX16_VAR_B32_e64;

diff  --git a/llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard.mir b/llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard.mir
index c74d66239f22ca7..3f40a57ca1491e1 100644
--- a/llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard.mir
+++ b/llvm/test/CodeGen/AMDGPU/vcmpx-permlane-hazard.mir
@@ -168,3 +168,26 @@ body:            |
     $vgpr1 = V_PERMLANE16_B32_e64 0, killed $vgpr1, 0, killed $sgpr1, 0, killed $sgpr0, $vgpr1, 0, implicit $exec
     S_ENDPGM 0
 ...
+
+# GCN-LABEL: name: hazard_vcmpx_permlane64
+# GCN:      V_CMPX_LE_F32_nosdst_e32
+# GCN:      S_ADD_U32
+# GCN-NEXT: $vgpr1 = V_MOV_B32_e32 killed $vgpr1, implicit $exec
+# GCN-NEXT: V_PERMLANE64_B32
+---
+name:            hazard_vcmpx_permlane64
+body:            |
+  bb.0:
+    successors: %bb.1
+    $vgpr0 = V_MOV_B32_e32 0, implicit $exec
+    V_CMPX_LE_F32_nosdst_e32 0, $vgpr0, implicit-def $exec, implicit $mode, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1:
+    $vgpr1 = IMPLICIT_DEF
+    $vgpr2 = IMPLICIT_DEF
+    $sgpr0 = IMPLICIT_DEF
+    $sgpr1 = S_ADD_U32 $sgpr0, 0, implicit-def $scc
+    $vgpr1 = V_PERMLANE64_B32 killed $vgpr1, implicit $exec
+    S_ENDPGM 0
+...