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
62 lines
1.8 KiB
LLVM
62 lines
1.8 KiB
LLVM
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+lob,+mve.fp -disable-arm-loloops=true %s -o - | FileCheck %s --check-prefix=DISABLED
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+lob,+mve.fp %s -o - | FileCheck %s
|
|
|
|
; DISABLED-NOT: dls lr,
|
|
|
|
; CHECK-LABEL: test_target_specific:
|
|
; CHECK: mov.w lr, #50
|
|
; CHECK-NOT: dls lr, lr
|
|
; CHECK-NOT: mov lr,
|
|
; CHECK: [[LOOP_HEADER:\.LBB[0-9_]+]]:
|
|
; CHECK: le lr, [[LOOP_HEADER]]
|
|
; CHECK-NOT: b .
|
|
; CHECK: @ %exit
|
|
|
|
define i32 @test_target_specific(ptr %a, ptr %b) {
|
|
entry:
|
|
br label %loop
|
|
loop:
|
|
%acc = phi i32 [ 0, %entry ], [ %res, %loop ]
|
|
%count = phi i32 [ 0, %entry ], [ %count.next, %loop ]
|
|
%addr.a = getelementptr i32, ptr %a, i32 %count
|
|
%addr.b = getelementptr i32, ptr %b, i32 %count
|
|
%load.a = load i32, ptr %addr.a
|
|
%load.b = load i32, ptr %addr.b
|
|
%res = call i32 @llvm.arm.smlad(i32 %load.a, i32 %load.b, i32 %acc)
|
|
%count.next = add nuw i32 %count, 2
|
|
%cmp = icmp ne i32 %count.next, 100
|
|
br i1 %cmp, label %loop, label %exit
|
|
exit:
|
|
ret i32 %res
|
|
}
|
|
|
|
; CHECK-LABEL: test_fabs:
|
|
; CHECK: mov.w lr, #100
|
|
; CHECK-NOT: dls lr, lr
|
|
; CHECK-NOT: mov lr,
|
|
; CHECK: [[LOOP_HEADER:\.LBB[0-9_]+]]:
|
|
; CHECK-NOT: bl
|
|
; CHECK: le lr, [[LOOP_HEADER]]
|
|
; CHECK-NOT: b .
|
|
; CHECK: @ %exit
|
|
|
|
define float @test_fabs(ptr %a) {
|
|
entry:
|
|
br label %loop
|
|
loop:
|
|
%acc = phi float [ 0.0, %entry ], [ %res, %loop ]
|
|
%count = phi i32 [ 0, %entry ], [ %count.next, %loop ]
|
|
%addr.a = getelementptr float, ptr %a, i32 %count
|
|
%load.a = load float, ptr %addr.a
|
|
%abs = call float @llvm.fabs.f32(float %load.a)
|
|
%res = fadd float %abs, %acc
|
|
%count.next = add nuw i32 %count, 1
|
|
%cmp = icmp ne i32 %count.next, 100
|
|
br i1 %cmp, label %loop, label %exit
|
|
exit:
|
|
ret float %res
|
|
}
|
|
|
|
declare i32 @llvm.arm.smlad(i32, i32, i32)
|
|
declare float @llvm.fabs.f32(float)
|