derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
42 lines
1.7 KiB
LLVM
42 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
|
|
; RUN: opt < %s -passes=loop-vectorize -force-vector-width=4 -S | FileCheck %s
|
|
|
|
; Check that we don't unnecessarily broadcast %pow
|
|
define void @powi_only_first_lane_used_of_second_arg(ptr %p, i32 %pow) {
|
|
; CHECK-LABEL: define void @powi_only_first_lane_used_of_second_arg(
|
|
; CHECK-SAME: ptr [[P:%.*]], i32 [[POW:%.*]]) {
|
|
; CHECK-NEXT: [[ENTRY:.*:]]
|
|
; CHECK-NEXT: br label %[[VECTOR_PH:.*]]
|
|
; CHECK: [[VECTOR_PH]]:
|
|
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
|
|
; CHECK: [[VECTOR_BODY]]:
|
|
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
|
|
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr float, ptr [[P]], i32 [[INDEX]]
|
|
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <4 x float>, ptr [[TMP0]], align 4
|
|
; CHECK-NEXT: [[TMP2:%.*]] = call <4 x float> @llvm.powi.v4f32.i32(<4 x float> [[WIDE_LOAD]], i32 [[POW]])
|
|
; CHECK-NEXT: store <4 x float> [[TMP2]], ptr [[TMP0]], align 4
|
|
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
|
|
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1024
|
|
; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
|
|
; CHECK: [[MIDDLE_BLOCK]]:
|
|
; CHECK-NEXT: br label %[[EXIT:.*]]
|
|
; CHECK: [[EXIT]]:
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
br label %loop
|
|
|
|
loop:
|
|
%iv = phi i32 [0, %entry], [%iv.next, %loop]
|
|
%p.gep = getelementptr float, ptr %p, i32 %iv
|
|
%x = load float, ptr %p.gep
|
|
%y = call float @llvm.powi(float %x, i32 %pow)
|
|
store float %y, ptr %p.gep
|
|
%iv.next = add i32 %iv, 1
|
|
%done = icmp eq i32 %iv.next, 1024
|
|
br i1 %done, label %exit, label %loop
|
|
|
|
exit:
|
|
ret void
|
|
}
|