Reapply "[AMDGPU] Add InstCombine rule for ballot.i64 intrinsic in wave32 mode." (llvm#80303)

Reapply llvm#71556 with added lit test constraint: `REQUIRES: amdgpu-registered-target`.

This reverts commit 9791e54.

(cherry picked from commit b8025d1)
Change-Id: I03aafda08ca433456f6e82accd6b702a307bfd0b

Author: vpykhtin

clang/test/CodeGenOpenCL/builtins-amdgcn-wave32.cl

@@ -1,3 +1,4 @@
+// REQUIRES: amdgpu-registered-target
 // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -D__AMDGCN_WAVEFRONT_SIZE=32 -target-feature +wavefrontsize32 -S -emit-llvm -o - %s | FileCheck -enable-var-scope %s
 // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -S -emit-llvm -o - %s | FileCheck -enable-var-scope %s
 // RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -target-feature +wavefrontsize32 -S -emit-llvm -o - %s | FileCheck -enable-var-scope %s

llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp

@@ -915,6 +915,19 @@ GCNTTIImpl::instCombineIntrinsic(InstCombiner &IC, IntrinsicInst &II) const {
         return IC.replaceInstUsesWith(II, Constant::getNullValue(II.getType()));
       }
     }
+    if (ST->isWave32() && II.getType()->getIntegerBitWidth() == 64) {
+      // %b64 = call i64 ballot.i64(...)
+      // =>
+      // %b32 = call i32 ballot.i32(...)
+      // %b64 = zext i32 %b32 to i64
+      Value *Call = IC.Builder.CreateZExt(
+          IC.Builder.CreateIntrinsic(Intrinsic::amdgcn_ballot,
+                                     {IC.Builder.getInt32Ty()},
+                                     {II.getArgOperand(0)}),
+          II.getType());
+      Call->takeName(&II);
+      return IC.replaceInstUsesWith(II, Call);
+    }
     break;
   }
   case Intrinsic::amdgcn_wqm_vote: {

llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll

@@ -2565,7 +2565,8 @@ declare i32 @llvm.amdgcn.ballot.i32(i1) nounwind readnone convergent
 
 define i64 @ballot_nocombine_64(i1 %i) {
 ; CHECK-LABEL: @ballot_nocombine_64(
-; CHECK-NEXT:    [[B:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[I:%.*]])
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.ballot.i32(i1 [[I:%.*]])
+; CHECK-NEXT:    [[B:%.*]] = zext i32 [[TMP1]] to i64
 ; CHECK-NEXT:    ret i64 [[B]]
 ;
   %b = call i64 @llvm.amdgcn.ballot.i64(i1 %i)
@@ -2582,7 +2583,8 @@ define i64 @ballot_zero_64() {
 
 define i64 @ballot_one_64() {
 ; CHECK-LABEL: @ballot_one_64(
-; CHECK-NEXT:    [[B:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 true)
+; CHECK-NEXT:    [[TMP1:%.*]] = call i32 @llvm.amdgcn.ballot.i32(i1 true)
+; CHECK-NEXT:    [[B:%.*]] = zext i32 [[TMP1]] to i64
 ; CHECK-NEXT:    ret i64 [[B]]
 ;
   %b = call i64 @llvm.amdgcn.ballot.i64(i1 1)