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
2.5 KiB
LLVM
62 lines
2.5 KiB
LLVM
; Test conversions between different-sized float elements.
|
|
;
|
|
; RUN: llc < %s -mtriple=s390x-linux-gnu -mcpu=z13 | FileCheck %s
|
|
|
|
declare <2 x float> @llvm.experimental.constrained.fptrunc.v2f32.v2f64(<2 x double>, metadata, metadata)
|
|
declare float @llvm.experimental.constrained.fptrunc.f32.f64(double, metadata, metadata)
|
|
|
|
declare <2 x double> @llvm.experimental.constrained.fpext.v2f64.v2f32(<2 x float>, metadata)
|
|
declare double @llvm.experimental.constrained.fpext.f64.f32(float, metadata)
|
|
|
|
; Test cases where both elements of a v2f64 are converted to f32s.
|
|
define void @f1(<2 x double> %val, ptr %ptr) #0 {
|
|
; CHECK-LABEL: f1:
|
|
; CHECK: vledb {{%v[0-9]+}}, %v24, 0, 0
|
|
; CHECK: br %r14
|
|
%res = call <2 x float> @llvm.experimental.constrained.fptrunc.v2f32.v2f64(
|
|
<2 x double> %val,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
store <2 x float> %res, ptr %ptr
|
|
ret void
|
|
}
|
|
|
|
; Test conversion of an f64 in a vector register to an f32.
|
|
define float @f2(<2 x double> %vec) #0 {
|
|
; CHECK-LABEL: f2:
|
|
; CHECK: wledb %f0, %v24, 0, 0
|
|
; CHECK: br %r14
|
|
%scalar = extractelement <2 x double> %vec, i32 0
|
|
%ret = call float @llvm.experimental.constrained.fptrunc.f32.f64(
|
|
double %scalar,
|
|
metadata !"round.dynamic",
|
|
metadata !"fpexcept.strict") #0
|
|
ret float %ret
|
|
}
|
|
|
|
; Test cases where even elements of a v4f32 are converted to f64s.
|
|
define <2 x double> @f3(<4 x float> %vec) #0 {
|
|
; CHECK-LABEL: f3:
|
|
; CHECK: vldeb %v24, {{%v[0-9]+}}
|
|
; CHECK: br %r14
|
|
%shuffle = shufflevector <4 x float> %vec, <4 x float> undef, <2 x i32> <i32 0, i32 2>
|
|
%res = call <2 x double> @llvm.experimental.constrained.fpext.v2f64.v2f32(
|
|
<2 x float> %shuffle,
|
|
metadata !"fpexcept.strict") #0
|
|
ret <2 x double> %res
|
|
}
|
|
|
|
; Test conversion of an f32 in a vector register to an f64.
|
|
define double @f4(<4 x float> %vec) #0 {
|
|
; CHECK-LABEL: f4:
|
|
; CHECK: wldeb %f0, %v24
|
|
; CHECK: br %r14
|
|
%scalar = extractelement <4 x float> %vec, i32 0
|
|
%ret = call double @llvm.experimental.constrained.fpext.f64.f32(
|
|
float %scalar,
|
|
metadata !"fpexcept.strict") #0
|
|
ret double %ret
|
|
}
|
|
|
|
attributes #0 = { strictfp }
|