aboutsummaryrefslogtreecommitdiff
path: root/llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll')
-rw-r--r--llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll5
1 files changed, 5 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll b/llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll
index aa11574..a7e828c 100644
--- a/llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll
+++ b/llvm/test/CodeGen/AMDGPU/amdgpu-uniform-intrinsic-combine.ll
@@ -1,5 +1,6 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 6
; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -amdgpu-enable-uniform-intrinsic-combine=0 -O3 -S < %s | FileCheck %s -check-prefix=CURRENT-CHECK
+; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -amdgpu-uniform-intrinsic-combine -S < %s | FileCheck %s -check-prefix=PASS-CHECK
; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -passes=amdgpu-uniform-intrinsic-combine -S < %s | FileCheck %s -check-prefix=PASS-CHECK
; RUN: opt -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -passes=amdgpu-uniform-intrinsic-combine,dce -S < %s | FileCheck %s -check-prefix=DCE-CHECK
@@ -595,6 +596,8 @@ define amdgpu_kernel void @ballot_i32(i32 %v, ptr addrspace(1) %out) {
; PASS-CHECK-LABEL: define amdgpu_kernel void @ballot_i32(
; PASS-CHECK-SAME: i32 [[V:%.*]], ptr addrspace(1) [[OUT:%.*]]) #[[ATTR0]] {
; PASS-CHECK-NEXT: [[C:%.*]] = trunc i32 [[V]] to i1
+; PASS-CHECK-NEXT: [[BALLOT:%.*]] = call i32 @llvm.amdgcn.ballot.i32(i1 [[C]])
+; PASS-CHECK-NEXT: [[BALLOT_NE_ZERO:%.*]] = icmp ne i32 [[BALLOT]], 0
; PASS-CHECK-NEXT: store i1 [[C]], ptr addrspace(1) [[OUT]], align 1
; PASS-CHECK-NEXT: ret void
;
@@ -623,6 +626,8 @@ define amdgpu_kernel void @ballot_i64(i32 %v, ptr addrspace(1) %out) {
; PASS-CHECK-LABEL: define amdgpu_kernel void @ballot_i64(
; PASS-CHECK-SAME: i32 [[V:%.*]], ptr addrspace(1) [[OUT:%.*]]) #[[ATTR0]] {
; PASS-CHECK-NEXT: [[C:%.*]] = trunc i32 [[V]] to i1
+; PASS-CHECK-NEXT: [[BALLOT:%.*]] = call i64 @llvm.amdgcn.ballot.i64(i1 [[C]])
+; PASS-CHECK-NEXT: [[BALLOT_NE_ZERO:%.*]] = icmp ne i64 [[BALLOT]], 0
; PASS-CHECK-NEXT: store i1 [[C]], ptr addrspace(1) [[OUT]], align 1
; PASS-CHECK-NEXT: ret void
;