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
46 lines
1.7 KiB
LLVM
46 lines
1.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: opt < %s -passes=instcombine -S | FileCheck %s
|
|
|
|
define i32 @reduce_add_eliminate_mask(ptr %p) {
|
|
; CHECK-LABEL: define i32 @reduce_add_eliminate_mask(
|
|
; CHECK-SAME: ptr [[P:%.*]]) {
|
|
; CHECK-NEXT: [[VEC:%.*]] = load <4 x i32>, ptr [[P]], align 16
|
|
; CHECK-NEXT: [[AND:%.*]] = and <4 x i32> [[VEC]], splat (i32 268435455)
|
|
; CHECK-NEXT: [[SUM:%.*]] = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> [[AND]])
|
|
; CHECK-NEXT: ret i32 [[SUM]]
|
|
;
|
|
%vec = load <4 x i32>, ptr %p
|
|
%and = and <4 x i32> %vec, splat (i32 268435455)
|
|
%sum = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %and)
|
|
%masked = and i32 %sum, 1073741823
|
|
ret i32 %masked
|
|
}
|
|
|
|
define i1 @reduce_add_simplify_comparison(ptr %p) {
|
|
; CHECK-LABEL: define i1 @reduce_add_simplify_comparison(
|
|
; CHECK-SAME: ptr [[P:%.*]]) {
|
|
; CHECK-NEXT: ret i1 true
|
|
;
|
|
%vec = load <8 x i32>, ptr %p
|
|
%and = and <8 x i32> %vec, splat (i32 16777215)
|
|
%sum = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> %and)
|
|
%cmp = icmp ult i32 %sum, 134217728
|
|
ret i1 %cmp
|
|
}
|
|
|
|
define i64 @reduce_add_sext(ptr %p) {
|
|
; CHECK-LABEL: define i64 @reduce_add_sext(
|
|
; CHECK-SAME: ptr [[P:%.*]]) {
|
|
; CHECK-NEXT: [[VEC:%.*]] = load <2 x i32>, ptr [[P]], align 8
|
|
; CHECK-NEXT: [[AND:%.*]] = and <2 x i32> [[VEC]], splat (i32 4194303)
|
|
; CHECK-NEXT: [[SUM:%.*]] = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> [[AND]])
|
|
; CHECK-NEXT: [[EXT:%.*]] = zext nneg i32 [[SUM]] to i64
|
|
; CHECK-NEXT: ret i64 [[EXT]]
|
|
;
|
|
%vec = load <2 x i32>, ptr %p
|
|
%and = and <2 x i32> %vec, splat (i32 4194303)
|
|
%sum = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> %and)
|
|
%ext = sext i32 %sum to i64
|
|
ret i64 %ext
|
|
}
|