[llvm] [AMDGPU] SIFoldOperands check that shrunk op is valid (PR #156298)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-backend-amdgpu

Author: David Stuttard (dstutt)

<details>
<summary>Changes</summary>



---
Full diff: https://github.com/llvm/llvm-project/pull/156298.diff


2 Files Affected:

- (modified) llvm/lib/Target/AMDGPU/SIFoldOperands.cpp (+2) 
- (added) llvm/test/CodeGen/AMDGPU/fold-abs64.mir (+41) 


``````````diff
diff --git a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
index 3979e1e0c44aa..9bb94e6dd2ad4 100644
--- a/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
+++ b/llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
@@ -868,6 +868,8 @@ bool SIFoldOperandsImpl::tryAddToFoldList(
       // Make sure to get the 32-bit version of the commuted opcode.
       unsigned MaybeCommutedOpc = MI->getOpcode();
       Op32 = AMDGPU::getVOPe32(MaybeCommutedOpc);
+      if (TII->pseudoToMCOpcode(Op32) == -1)
+        return false;
     }
 
     appendFoldCandidate(FoldList, MI, CommuteOpNo, OpToFold, /*Commuted=*/true,
diff --git a/llvm/test/CodeGen/AMDGPU/fold-abs64.mir b/llvm/test/CodeGen/AMDGPU/fold-abs64.mir
new file mode 100644
index 0000000000000..d78456afc2be2
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/fold-abs64.mir
@@ -0,0 +1,41 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn -mcpu=gfx1250 -run-pass=si-fold-operands %s -o - | FileCheck %s
+
+--- |
+  @sym = external constant i32
+  define void @fn() { ret void }
+  define void @fn2() { ret void }
+...
+
+---
+name: fn
+tracksRegLiveness: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: fn
+    ; CHECK: [[DEF:%[0-9]+]]:vreg_64 = IMPLICIT_DEF
+    ; CHECK-NEXT: [[S_MOV_B64_:%[0-9]+]]:sreg_64 = S_MOV_B64 target-flags(amdgpu-abs64) @sym
+    ; CHECK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 undef [[DEF]].sub0, undef [[S_MOV_B64_]].sub0, 0, implicit $exec
+    ; CHECK-NEXT: S_ENDPGM 0, implicit [[V_ADD_CO_U32_e64_]]
+    %0:vreg_64 = IMPLICIT_DEF
+    %1:sreg_64 = S_MOV_B64 target-flags(amdgpu-abs64) @sym
+    %2:vgpr_32, %3:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 undef %1.sub0, undef %0.sub0, 0, implicit $exec
+    S_ENDPGM 0, implicit %2
+...
+
+---
+name: fn2
+tracksRegLiveness: true
+body: |
+  bb.0:
+    ; CHECK-LABEL: name: fn2
+    ; CHECK: [[DEF:%[0-9]+]]:vreg_64 = IMPLICIT_DEF
+    ; CHECK-NEXT: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 591751049, undef [[DEF]].sub0, 0, implicit $exec
+    ; CHECK-NEXT: S_ENDPGM 0, implicit [[V_ADD_CO_U32_e64_]]
+    %0:vreg_64 = IMPLICIT_DEF
+    %1:sreg_64 = S_MOV_B64 4886718345
+    %2:vgpr_32, %3:sreg_32_xm0_xexec = V_ADD_CO_U32_e64 undef %1.sub0, undef %0.sub0, 0, implicit $exec
+    S_ENDPGM 0, implicit %2
+...
+## NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+# CHECK: {{.*}}

``````````

</details>


https://github.com/llvm/llvm-project/pull/156298