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
63 lines
3.4 KiB
LLVM
63 lines
3.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
|
|
; RUN: opt < %s -passes=memcpyopt -S -verify-memoryssa | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
|
|
|
|
; Verify that we don't combine nontemporal stores into memset calls.
|
|
|
|
define void @nontemporal_stores_1(ptr nocapture %dst) {
|
|
; CHECK-LABEL: @nontemporal_stores_1(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[DST:%.*]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR1:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 1
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR1]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR2:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 2
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR2]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR3:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 3
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR3]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR4:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 4
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR4]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR5:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 5
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR5]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR6:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 6
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR6]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR7:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 7
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR7]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
store <4 x float> zeroinitializer, ptr %dst, align 16, !nontemporal !0
|
|
%ptr1 = getelementptr inbounds <4 x float>, ptr %dst, i64 1
|
|
store <4 x float> zeroinitializer, ptr %ptr1, align 16, !nontemporal !0
|
|
%ptr2 = getelementptr inbounds <4 x float>, ptr %dst, i64 2
|
|
store <4 x float> zeroinitializer, ptr %ptr2, align 16, !nontemporal !0
|
|
%ptr3 = getelementptr inbounds <4 x float>, ptr %dst, i64 3
|
|
store <4 x float> zeroinitializer, ptr %ptr3, align 16, !nontemporal !0
|
|
%ptr4 = getelementptr inbounds <4 x float>, ptr %dst, i64 4
|
|
store <4 x float> zeroinitializer, ptr %ptr4, align 16, !nontemporal !0
|
|
%ptr5 = getelementptr inbounds <4 x float>, ptr %dst, i64 5
|
|
store <4 x float> zeroinitializer, ptr %ptr5, align 16, !nontemporal !0
|
|
%ptr6 = getelementptr inbounds <4 x float>, ptr %dst, i64 6
|
|
store <4 x float> zeroinitializer, ptr %ptr6, align 16, !nontemporal !0
|
|
%ptr7 = getelementptr inbounds <4 x float>, ptr %dst, i64 7
|
|
store <4 x float> zeroinitializer, ptr %ptr7, align 16, !nontemporal !0
|
|
ret void
|
|
}
|
|
|
|
define void @nontemporal_stores_2(ptr nocapture %dst) {
|
|
; CHECK-LABEL: @nontemporal_stores_2(
|
|
; CHECK-NEXT: entry:
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[DST:%.*]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: [[PTR1:%.*]] = getelementptr inbounds <4 x float>, ptr [[DST]], i64 1
|
|
; CHECK-NEXT: store <4 x float> zeroinitializer, ptr [[PTR1]], align 16, !nontemporal !0
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
entry:
|
|
store <4 x float> zeroinitializer, ptr %dst, align 16, !nontemporal !0
|
|
%ptr1 = getelementptr inbounds <4 x float>, ptr %dst, i64 1
|
|
store <4 x float> zeroinitializer, ptr %ptr1, align 16, !nontemporal !0
|
|
ret void
|
|
}
|
|
|
|
!0 = !{i32 1}
|