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
72 lines
2.5 KiB
LLVM
72 lines
2.5 KiB
LLVM
; RUN: llc -verify-machineinstrs -mcpu=pwr6 -mattr=+altivec,+fsqrt < %s | FileCheck %s
|
|
|
|
; Check for vector sqrt expansion using floating-point types, since altivec
|
|
; does not provide an fsqrt instruction for vector.
|
|
|
|
target datalayout = "E-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v128:128:128-n32:64"
|
|
target triple = "powerpc64-unknown-linux-gnu"
|
|
|
|
declare <2 x float> @llvm.sqrt.v2f32(<2 x float> %val)
|
|
declare <4 x float> @llvm.sqrt.v4f32(<4 x float> %val)
|
|
declare <8 x float> @llvm.sqrt.v8f32(<8 x float> %val)
|
|
declare <2 x double> @llvm.sqrt.v2f64(<2 x double> %val)
|
|
declare <4 x double> @llvm.sqrt.v4f64(<4 x double> %val)
|
|
|
|
define <2 x float> @v2f32_sqrt(<2 x float> %x) nounwind readnone {
|
|
entry:
|
|
%sqrt = call <2 x float> @llvm.sqrt.v2f32 (<2 x float> %x)
|
|
ret <2 x float> %sqrt
|
|
}
|
|
; sqrt (<2 x float>) is promoted to sqrt (<4 x float>)
|
|
; CHECK-LABEL: v2f32_sqrt:
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
|
|
define <4 x float> @v4f32_sqrt(<4 x float> %x) nounwind readnone {
|
|
entry:
|
|
%sqrt = call <4 x float> @llvm.sqrt.v4f32 (<4 x float> %x)
|
|
ret <4 x float> %sqrt
|
|
}
|
|
; CHECK-LABEL: v4f32_sqrt:
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
|
|
define <8 x float> @v8f32_sqrt(<8 x float> %x) nounwind readnone {
|
|
entry:
|
|
%sqrt = call <8 x float> @llvm.sqrt.v8f32 (<8 x float> %x)
|
|
ret <8 x float> %sqrt
|
|
}
|
|
; CHECK-LABEL: v8f32_sqrt:
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrts {{[0-9]+}}, {{[0-9]+}}
|
|
|
|
define <2 x double> @v2f64_sqrt(<2 x double> %x) nounwind readnone {
|
|
entry:
|
|
%sqrt = call <2 x double> @llvm.sqrt.v2f64 (<2 x double> %x)
|
|
ret <2 x double> %sqrt
|
|
}
|
|
; CHECK-LABEL: v2f64_sqrt:
|
|
; CHECK: fsqrt {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrt {{[0-9]+}}, {{[0-9]+}}
|
|
|
|
define <4 x double> @v4f64_sqrt(<4 x double> %x) nounwind readnone {
|
|
entry:
|
|
%sqrt = call <4 x double> @llvm.sqrt.v4f64 (<4 x double> %x)
|
|
ret <4 x double> %sqrt
|
|
}
|
|
; CHECK-LABEL: v4f64_sqrt:
|
|
; CHECK: fsqrt {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrt {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrt {{[0-9]+}}, {{[0-9]+}}
|
|
; CHECK: fsqrt {{[0-9]+}}, {{[0-9]+}}
|