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
76 lines
1.7 KiB
LLVM
76 lines
1.7 KiB
LLVM
; RUN: llc -mtriple armv7 %s -o - | FileCheck %s
|
|
|
|
; CHECK-LABEL: f:
|
|
define float @f(ptr nocapture %in) {
|
|
; CHECK: vld1
|
|
; CHECK: vmovl.u16
|
|
%1 = load <4 x i16>, ptr %in
|
|
; CHECK: vcvt.f32.u32
|
|
%2 = uitofp <4 x i16> %1 to <4 x float>
|
|
%3 = extractelement <4 x float> %2, i32 0
|
|
%4 = extractelement <4 x float> %2, i32 1
|
|
%5 = extractelement <4 x float> %2, i32 2
|
|
|
|
; CHECK: vadd.f32
|
|
%6 = fadd float %3, %4
|
|
%7 = fadd float %6, %5
|
|
|
|
ret float %7
|
|
}
|
|
|
|
; CHECK-LABEL: g:
|
|
define float @g(ptr nocapture %in) {
|
|
; Note: vld1 here is reasonably important. Mixing VFP and NEON
|
|
; instructions is bad on some cores
|
|
; CHECK: vld1
|
|
; CHECK: vmovl.u8
|
|
; CHECK: vmovl.u16
|
|
%1 = load <4 x i8>, ptr %in
|
|
; CHECK: vcvt.f32.u32
|
|
%2 = uitofp <4 x i8> %1 to <4 x float>
|
|
%3 = extractelement <4 x float> %2, i32 0
|
|
%4 = extractelement <4 x float> %2, i32 1
|
|
%5 = extractelement <4 x float> %2, i32 2
|
|
|
|
; CHECK: vadd.f32
|
|
%6 = fadd float %3, %4
|
|
%7 = fadd float %6, %5
|
|
|
|
ret float %7
|
|
}
|
|
|
|
; CHECK-LABEL: h:
|
|
define <4 x i8> @h(<4 x float> %v) {
|
|
; CHECK: vcvt.{{[us]}}32.f32
|
|
; CHECK: vmovn.i32
|
|
%1 = fptoui <4 x float> %v to <4 x i8>
|
|
ret <4 x i8> %1
|
|
}
|
|
|
|
; CHECK-LABEL: i:
|
|
define <4 x i8> @i(ptr %x, <4 x i8> %y) {
|
|
; Note: vld1 here is reasonably important. Mixing VFP and NEON
|
|
; instructions is bad on some cores
|
|
; CHECK: vld1
|
|
; CHECK: vmovl.s8
|
|
; CHECK: vmovl.s16
|
|
; CHECK: vrecpe
|
|
; CHECK: vrecps
|
|
; CHECK: vmul
|
|
; CHECK: vmovn
|
|
%1 = load <4 x i8>, ptr %x, align 4
|
|
%2 = sdiv <4 x i8> %y, %1
|
|
ret <4 x i8> %2
|
|
}
|
|
; CHECK-LABEL: j:
|
|
define <4 x i32> @j(ptr %in) nounwind {
|
|
; CHECK: vld1
|
|
; CHECK: vmovl.u8
|
|
; CHECK: vmovl.u16
|
|
; CHECK-NOT: vand
|
|
%1 = load <4 x i8>, ptr %in, align 4
|
|
%2 = zext <4 x i8> %1 to <4 x i32>
|
|
ret <4 x i32> %2
|
|
}
|
|
|