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
91 lines
3.2 KiB
LLVM
91 lines
3.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
|
|
|
|
; fpext <vscale x 2 x half> -> <vscale x 2 x double>
|
|
define <vscale x 2 x double> @ext2_f16_f64(ptr %ptr, i64 %index) {
|
|
; CHECK-LABEL: ext2_f16_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x0]
|
|
; CHECK-NEXT: fcvt z0.d, p0/m, z0.h
|
|
; CHECK-NEXT: ret
|
|
%load = load <vscale x 2 x half>, ptr %ptr, align 4
|
|
%load.ext = fpext <vscale x 2 x half> %load to <vscale x 2 x double>
|
|
ret <vscale x 2 x double> %load.ext
|
|
}
|
|
|
|
; fpext <vscale x 4 x half> -> <vscale x 4 x double>
|
|
define <vscale x 4 x double> @ext4_f16_f64(ptr %ptr, i64 %index) {
|
|
; CHECK-LABEL: ext4_f16_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.s
|
|
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: uunpklo z1.d, z0.s
|
|
; CHECK-NEXT: uunpkhi z2.d, z0.s
|
|
; CHECK-NEXT: movprfx z0, z1
|
|
; CHECK-NEXT: fcvt z0.d, p0/m, z1.h
|
|
; CHECK-NEXT: movprfx z1, z2
|
|
; CHECK-NEXT: fcvt z1.d, p0/m, z2.h
|
|
; CHECK-NEXT: ret
|
|
%load = load <vscale x 4 x half>, ptr %ptr, align 4
|
|
%load.ext = fpext <vscale x 4 x half> %load to <vscale x 4 x double>
|
|
ret <vscale x 4 x double> %load.ext
|
|
}
|
|
|
|
; fpext <vscale x 8 x half> -> <vscale x 8 x double>
|
|
define <vscale x 8 x double> @ext8_f16_f64(ptr %ptr, i64 %index) {
|
|
; CHECK-LABEL: ext8_f16_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ldr z0, [x0]
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: uunpklo z1.s, z0.h
|
|
; CHECK-NEXT: uunpkhi z0.s, z0.h
|
|
; CHECK-NEXT: uunpklo z2.d, z1.s
|
|
; CHECK-NEXT: uunpkhi z1.d, z1.s
|
|
; CHECK-NEXT: uunpklo z3.d, z0.s
|
|
; CHECK-NEXT: uunpkhi z4.d, z0.s
|
|
; CHECK-NEXT: fcvt z1.d, p0/m, z1.h
|
|
; CHECK-NEXT: movprfx z0, z2
|
|
; CHECK-NEXT: fcvt z0.d, p0/m, z2.h
|
|
; CHECK-NEXT: movprfx z2, z3
|
|
; CHECK-NEXT: fcvt z2.d, p0/m, z3.h
|
|
; CHECK-NEXT: movprfx z3, z4
|
|
; CHECK-NEXT: fcvt z3.d, p0/m, z4.h
|
|
; CHECK-NEXT: ret
|
|
%load = load <vscale x 8 x half>, ptr %ptr, align 4
|
|
%load.ext = fpext <vscale x 8 x half> %load to <vscale x 8 x double>
|
|
ret <vscale x 8 x double> %load.ext
|
|
}
|
|
|
|
; fpext <vscale x 2 x float> -> <vscale x 2 x double>
|
|
define <vscale x 2 x double> @ext2_f32_f64(ptr %ptr, i64 %index) {
|
|
; CHECK-LABEL: ext2_f32_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0]
|
|
; CHECK-NEXT: fcvt z0.d, p0/m, z0.s
|
|
; CHECK-NEXT: ret
|
|
%load = load <vscale x 2 x float>, ptr %ptr, align 4
|
|
%load.ext = fpext <vscale x 2 x float> %load to <vscale x 2 x double>
|
|
ret <vscale x 2 x double> %load.ext
|
|
}
|
|
|
|
; fpext <vscale x 4 x float> -> <vscale x 4 x double>
|
|
define <vscale x 4 x double> @ext4_f32_f64(ptr %ptr, i64 %index) {
|
|
; CHECK-LABEL: ext4_f32_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ldr z0, [x0]
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: uunpklo z1.d, z0.s
|
|
; CHECK-NEXT: uunpkhi z2.d, z0.s
|
|
; CHECK-NEXT: movprfx z0, z1
|
|
; CHECK-NEXT: fcvt z0.d, p0/m, z1.s
|
|
; CHECK-NEXT: movprfx z1, z2
|
|
; CHECK-NEXT: fcvt z1.d, p0/m, z2.s
|
|
; CHECK-NEXT: ret
|
|
%load = load <vscale x 4 x float>, ptr %ptr, align 4
|
|
%load.ext = fpext <vscale x 4 x float> %load to <vscale x 4 x double>
|
|
ret <vscale x 4 x double> %load.ext
|
|
}
|