[PATCH] D156077: [AMDGPU] Perform basic folds on llvm.amdgcn.wave.reduce.umin/umax.

[Pravin Jagtap via Phabricator via llvm-commits]

pravinjagtap updated this revision to Diff 543381.
pravinjagtap added a comment.

Formatting


Repository:
  rG LLVM Github Monorepo

CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D156077/new/

https://reviews.llvm.org/D156077

Files:
  llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
  llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll


Index: llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
===================================================================
--- llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
+++ llvm/test/Transforms/InstCombine/AMDGPU/amdgcn-intrinsics.ll
@@ -6194,3 +6194,61 @@
   %val = call half @llvm.amdgcn.exp2.f16(half 0xH83ff)
   ret half %val
 }
+
+; --------------------------------------------------------------------
+; llvm.amdgcn.wave.reduce.umin.i32
+; --------------------------------------------------------------------
+
+declare i32 @llvm.amdgcn.wave.reduce.umin.i32(i32, i32 immarg)
+
+define amdgpu_kernel void @test_constant_fold_wave_reduce_umin_poison(ptr addrspace(1) %out, i32 %in) {
+; CHECK-LABEL: @test_constant_fold_wave_reduce_umin_poison(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %result = call i32 @llvm.amdgcn.wave.reduce.umin.i32(i32 poison, i32 1)
+  store i32 %result, ptr addrspace(1) %out
+  ret void
+}
+
+define amdgpu_kernel void @test_constant_fold_wave_reduce_umin_const(ptr addrspace(1) %out) {
+; CHECK-LABEL: @test_constant_fold_wave_reduce_umin_const(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    store i32 123, ptr addrspace(1) [[OUT:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %result = call i32 @llvm.amdgcn.wave.reduce.umin.i32(i32 123, i32 1)
+  store i32 %result, ptr addrspace(1) %out
+  ret void
+}
+
+; --------------------------------------------------------------------
+; llvm.amdgcn.wave.reduce.umin.i32
+; --------------------------------------------------------------------
+
+declare i32 @llvm.amdgcn.wave.reduce.umax.i32(i32, i32 immarg)
+
+define amdgpu_kernel void @test_constant_fold_wave_reduce_umax_poison(ptr addrspace(1) %out, i32 %in) {
+; CHECK-LABEL: @test_constant_fold_wave_reduce_umax_poison(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    ret void
+;
+entry:
+  %result = call i32 @llvm.amdgcn.wave.reduce.umax.i32(i32 poison, i32 1)
+  store i32 %result, ptr addrspace(1) %out
+  ret void
+}
+
+define amdgpu_kernel void @test_constant_fold_wave_reduce_umax_const(ptr addrspace(1) %out) {
+; CHECK-LABEL: @test_constant_fold_wave_reduce_umax_const(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    store i32 123, ptr addrspace(1) [[OUT:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
+entry:
+  %result = call i32 @llvm.amdgcn.wave.reduce.umax.i32(i32 123, i32 1)
+  store i32 %result, ptr addrspace(1) %out
+  ret void
+}
Index: llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
+++ llvm/lib/Target/AMDGPU/AMDGPUInstCombineIntrinsic.cpp
@@ -1136,6 +1136,16 @@
 
     break;
   }
+  case Intrinsic::amdgcn_wave_reduce_umin:
+  case Intrinsic::amdgcn_wave_reduce_umax: {
+    Value *Src = II.getArgOperand(0);
+
+    // Propagate poison and constant value
+    if (isa<PoisonValue>(Src) || isa<Constant>(Src))
+      return IC.replaceInstUsesWith(II, Src);
+
+    break;
+  }
   }
   if (const AMDGPU::ImageDimIntrinsicInfo *ImageDimIntr =
             AMDGPU::getImageDimIntrinsicInfo(II.getIntrinsicID())) {


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D156077.543381.patch
Type: text/x-patch
Size: 3143 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20230724/e9428312/attachment.bin>