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
36 lines
1.3 KiB
LLVM
36 lines
1.3 KiB
LLVM
; RUN: llc < %s -mtriple=x86_64-pc-linux -mcpu=nocona | FileCheck %s --check-prefix=PRESCOTT
|
|
; RUN: llc < %s -mtriple=x86_64-pc-linux -mcpu=nehalem | FileCheck %s --check-prefix=NEHALEM
|
|
|
|
;;; TODO: (1) Some of the loads and stores are certainly unaligned and (2) the first load and first
|
|
;;; store overlap with the second load and second store respectively.
|
|
;;;
|
|
;;; Is either of these sequences ideal?
|
|
|
|
define float @foo(ptr nocapture %buf, float %a, float %b) nounwind uwtable {
|
|
; PRESCOTT-LABEL: foo:
|
|
; PRESCOTT: # %bb.0: # %entry
|
|
; PRESCOTT-NEXT: movq .Ltmp0+14(%rip), %rax
|
|
; PRESCOTT-NEXT: movq %rax, 14(%rdi)
|
|
; PRESCOTT-NEXT: movq .Ltmp0+8(%rip), %rax
|
|
; PRESCOTT-NEXT: movq %rax, 8(%rdi)
|
|
; PRESCOTT-NEXT: movq .Ltmp0(%rip), %rax
|
|
; PRESCOTT-NEXT: movq %rax, (%rdi)
|
|
;
|
|
; NEHALEM-LABEL: foo:
|
|
; NEHALEM: # %bb.0: # %entry
|
|
; NEHALEM-NEXT: movq .Ltmp0+14(%rip), %rax
|
|
; NEHALEM-NEXT: movq %rax, 14(%rdi)
|
|
; NEHALEM-NEXT: movups .Ltmp0(%rip), %xmm2
|
|
; NEHALEM-NEXT: movups %xmm2, (%rdi)
|
|
|
|
entry:
|
|
tail call void @llvm.memcpy.p0.p0.i64(ptr %buf, ptr blockaddress(@foo, %out), i64 22, i1 false)
|
|
br label %out
|
|
|
|
out: ; preds = %entry
|
|
%add = fadd float %a, %b
|
|
ret float %add
|
|
}
|
|
|
|
declare void @llvm.memcpy.p0.p0.i64(ptr nocapture, ptr nocapture, i64, i1) nounwind
|