[PATCH] D132978: [IRTranslator] Using ZExt for extractelement indices.

[Peter Rong via Phabricator via llvm-commits]

Peter created this revision.
Herald added subscribers: kosarev, kerbowa, arphaman, hiraditya, kristof.beyls, tpr, jvesely.
Herald added a project: All.
Peter requested review of this revision.
Herald added a project: LLVM.
Herald added a subscriber: llvm-commits.

In https://github.com/llvm/llvm-project/issues/57452, we found that IRTranslator is translating `i1 true` into `i32 -1`.
This is because IRTranslator uses SExt for indices.
In this fix, we move from SExt to ZExt. We also included a test for AMDGPU, an updated test for AArch64

This patch fixes this issue.


Repository:
  rG LLVM Github Monorepo

https://reviews.llvm.org/D132978

Files:
  llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
  llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
  llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-zext-vec-index.ll


Index: llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-zext-vec-index.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/GlobalISel/irtranslator-zext-vec-index.ll
@@ -0,0 +1,28 @@
+; NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+; RUN: llc -march=amdgcn -O0 -stop-after=irtranslator -global-isel -verify-machineinstrs %s -o - | FileCheck %s
+
+define i8 @f_i1_1() {
+  ; CHECK-LABEL: name: f_i1_1
+  ; CHECK: bb.1 (%ir-block.0):
+  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:_(<256 x s8>) = G_IMPLICIT_DEF
+  ; CHECK-NEXT:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
+  ; CHECK-NEXT:   [[EVEC:%[0-9]+]]:_(s8) = G_EXTRACT_VECTOR_ELT [[DEF]](<256 x s8>), [[C]](s32)
+  ; CHECK-NEXT:   [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[EVEC]](s8)
+  ; CHECK-NEXT:   $vgpr0 = COPY [[ANYEXT]](s32)
+  ; CHECK-NEXT:   SI_RETURN implicit $vgpr0
+  %E1 = extractelement <256 x i8> undef, i1 true
+  ret i8 %E1
+}
+
+define i8 @f_i8_255() {
+  ; CHECK-LABEL: name: f_i8_255
+  ; CHECK: bb.1 (%ir-block.0):
+  ; CHECK-NEXT:   [[DEF:%[0-9]+]]:_(<256 x s8>) = G_IMPLICIT_DEF
+  ; CHECK-NEXT:   [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
+  ; CHECK-NEXT:   [[EVEC:%[0-9]+]]:_(s8) = G_EXTRACT_VECTOR_ELT [[DEF]](<256 x s8>), [[C]](s32)
+  ; CHECK-NEXT:   [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[EVEC]](s8)
+  ; CHECK-NEXT:   $vgpr0 = COPY [[ANYEXT]](s32)
+  ; CHECK-NEXT:   SI_RETURN implicit $vgpr0
+  %E1 = extractelement <256 x i8> undef, i8 255
+  ret i8 %E1
+}
Index: llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
===================================================================
--- llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
+++ llvm/test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll
@@ -1549,7 +1549,7 @@
 ; CHECK-LABEL: name: test_extractelement
 ; CHECK: [[VEC:%[0-9]+]]:_(<2 x s32>) = COPY $d0
 ; CHECK: [[IDX:%[0-9]+]]:_(s32) = COPY $w0
-; CHECK: [[IDXEXT:%[0-9]+]]:_(s64) = G_SEXT [[IDX]]
+; CHECK: [[IDXEXT:%[0-9]+]]:_(s64) = G_ZEXT [[IDX]]
 ; CHECK: [[RES:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[VEC]](<2 x s32>), [[IDXEXT]](s64)
 ; CHECK: $w0 = COPY [[RES]](s32)
   %res = extractelement <2 x i32> %vec, i32 %idx
@@ -1566,6 +1566,27 @@
   ret i32 %res
 }
 
+define i32 @test_extractelement_const_idx_zext_i1(<2 x i32> %vec) {
+; CHECK-LABEL: name: test_extractelement
+; CHECK: [[VEC:%[0-9]+]]:_(<2 x s32>) = COPY $d0
+; CHECK: [[IDX:%[0-9]+]]:_(s64) = G_CONSTANT i64 1
+; CHECK: [[RES:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[VEC]](<2 x s32>), [[IDX]](s64)
+; CHECK: $w0 = COPY [[RES]](s32)
+  %res = extractelement <2 x i32> %vec, i1 true
+  ret i32 %res
+}
+
+define i32 @test_extractelement_const_idx_zext_i8(<2 x i32> %vec) {
+; CHECK-LABEL: name: test_extractelement
+; CHECK: [[VEC:%[0-9]+]]:_(<2 x s32>) = COPY $d0
+; CHECK: [[IDX:%[0-9]+]]:_(s64) = G_CONSTANT i64 255
+; CHECK: [[RES:%[0-9]+]]:_(s32) = G_EXTRACT_VECTOR_ELT [[VEC]](<2 x s32>), [[IDX]](s64)
+; CHECK: $w0 = COPY [[RES]](s32)
+  %res = extractelement <2 x i32> %vec, i8 255
+  ret i32 %res
+}
+
+
 define i32 @test_singleelementvector(i32 %elt){
 ; CHECK-LABEL: name: test_singleelementvector
 ; CHECK: [[ELT:%[0-9]+]]:_(s32) = COPY $w0
Index: llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
===================================================================
--- llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
+++ llvm/lib/CodeGen/GlobalISel/IRTranslator.cpp
@@ -2808,7 +2808,7 @@
   Register Idx;
   if (auto *CI = dyn_cast<ConstantInt>(U.getOperand(1))) {
     if (CI->getBitWidth() != PreferredVecIdxWidth) {
-      APInt NewIdx = CI->getValue().sextOrTrunc(PreferredVecIdxWidth);
+      APInt NewIdx = CI->getValue().zextOrTrunc(PreferredVecIdxWidth);
       auto *NewIdxCI = ConstantInt::get(CI->getContext(), NewIdx);
       Idx = getOrCreateVReg(*NewIdxCI);
     }
@@ -2817,7 +2817,7 @@
     Idx = getOrCreateVReg(*U.getOperand(1));
   if (MRI->getType(Idx).getSizeInBits() != PreferredVecIdxWidth) {
     const LLT VecIdxTy = LLT::scalar(PreferredVecIdxWidth);
-    Idx = MIRBuilder.buildSExtOrTrunc(VecIdxTy, Idx).getReg(0);
+    Idx = MIRBuilder.buildZExtOrTrunc(VecIdxTy, Idx).getReg(0);
   }
   MIRBuilder.buildExtractVectorElement(Res, Val, Idx);
   return true;


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D132978.456802.patch
Type: text/x-patch
Size: 4255 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20220830/5a58a887/attachment.bin>