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
82 lines
3.7 KiB
LLVM
82 lines
3.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple aarch64 -mcpu=cortex-a57 -mattr=+slow-paired-128 < %s | FileCheck %s --check-prefixes=DEFAULT
|
|
; RUN: llc -mtriple aarch64 -mcpu=cortex-a57 -mattr=+slow-paired-128 -mattr=+ascend-store-address < %s | FileCheck %s --check-prefixes=ASCEND
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
define dso_local void @memset_unroll2(ptr nocapture %array, i64 %size) {
|
|
; DEFAULT-LABEL: memset_unroll2:
|
|
; DEFAULT: // %bb.0: // %entry
|
|
; DEFAULT-NEXT: fmov v0.2d, #2.00000000
|
|
; DEFAULT-NEXT: add x8, x0, #64
|
|
; DEFAULT-NEXT: .p2align 4, , 8
|
|
; DEFAULT-NEXT: .LBB0_1: // %vector.body
|
|
; DEFAULT-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; DEFAULT-NEXT: stur q0, [x8, #-64]
|
|
; DEFAULT-NEXT: subs x1, x1, #4
|
|
; DEFAULT-NEXT: stur q0, [x8, #-48]
|
|
; DEFAULT-NEXT: str q0, [x8]
|
|
; DEFAULT-NEXT: str q0, [x8, #16]
|
|
; DEFAULT-NEXT: str q0, [x8, #32]
|
|
; DEFAULT-NEXT: str q0, [x8, #48]
|
|
; DEFAULT-NEXT: stur q0, [x8, #-32]
|
|
; DEFAULT-NEXT: stur q0, [x8, #-16]
|
|
; DEFAULT-NEXT: add x8, x8, #128
|
|
; DEFAULT-NEXT: b.ne .LBB0_1
|
|
; DEFAULT-NEXT: // %bb.2: // %cleanup
|
|
; DEFAULT-NEXT: ret
|
|
;
|
|
; ASCEND-LABEL: memset_unroll2:
|
|
; ASCEND: // %bb.0: // %entry
|
|
; ASCEND-NEXT: fmov v0.2d, #2.00000000
|
|
; ASCEND-NEXT: add x8, x0, #64
|
|
; ASCEND-NEXT: .p2align 4, , 8
|
|
; ASCEND-NEXT: .LBB0_1: // %vector.body
|
|
; ASCEND-NEXT: // =>This Inner Loop Header: Depth=1
|
|
; ASCEND-NEXT: stur q0, [x8, #-64]
|
|
; ASCEND-NEXT: subs x1, x1, #4
|
|
; ASCEND-NEXT: stur q0, [x8, #-48]
|
|
; ASCEND-NEXT: stur q0, [x8, #-32]
|
|
; ASCEND-NEXT: stur q0, [x8, #-16]
|
|
; ASCEND-NEXT: str q0, [x8]
|
|
; ASCEND-NEXT: str q0, [x8, #16]
|
|
; ASCEND-NEXT: str q0, [x8, #32]
|
|
; ASCEND-NEXT: str q0, [x8, #48]
|
|
; ASCEND-NEXT: add x8, x8, #128
|
|
; ASCEND-NEXT: b.ne .LBB0_1
|
|
; ASCEND-NEXT: // %bb.2: // %cleanup
|
|
; ASCEND-NEXT: ret
|
|
entry:
|
|
br label %vector.body
|
|
|
|
vector.body: ; preds = %vector.body, %entry
|
|
%index = phi i64 [ 0, %entry ], [ %index16, %vector.body ]
|
|
%niter = phi i64 [ %size, %entry ], [ %niter.nsub.3, %vector.body ]
|
|
%array0 = getelementptr inbounds double, ptr %array, i64 %index
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array0, align 8
|
|
%array2 = getelementptr inbounds double, ptr %array0, i64 2
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array2, align 8
|
|
%index4 = or disjoint i64 %index, 4
|
|
%array4 = getelementptr inbounds double, ptr %array, i64 %index4
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array4, align 8
|
|
%array6 = getelementptr inbounds double, ptr %array4, i64 2
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array6, align 8
|
|
%index8 = or disjoint i64 %index, 8
|
|
%array8 = getelementptr inbounds double, ptr %array, i64 %index8
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array8, align 8
|
|
%array10 = getelementptr inbounds double, ptr %array8, i64 2
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array10, align 8
|
|
%index12 = or disjoint i64 %index, 12
|
|
%array12 = getelementptr inbounds double, ptr %array, i64 %index12
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array12, align 8
|
|
%array14 = getelementptr inbounds double, ptr %array12, i64 2
|
|
store <2 x double> <double 2.000000e+00, double 2.000000e+00>, ptr %array14, align 8
|
|
%index16 = add i64 %index, 16
|
|
%niter.nsub.3 = add i64 %niter, -4
|
|
%niter.ncmp.3 = icmp eq i64 %niter.nsub.3, 0
|
|
br i1 %niter.ncmp.3, label %cleanup, label %vector.body
|
|
|
|
cleanup: ; preds = %vector.body
|
|
ret void
|
|
}
|