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
85 lines
4.9 KiB
LLVM
85 lines
4.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s --mattr=+sve -o - | FileCheck %s
|
|
|
|
target triple = "aarch64"
|
|
|
|
; Expected to transform
|
|
define <vscale x 2 x double> @complex_add_v2f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) {
|
|
; CHECK-LABEL: complex_add_v2f64:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fcadd z1.d, p0/m, z1.d, z0.d, #90
|
|
; CHECK-NEXT: mov z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.deinterleaved = tail call { <vscale x 1 x double>, <vscale x 1 x double> } @llvm.vector.deinterleave2.nxv2f64(<vscale x 2 x double> %a)
|
|
%a.real = extractvalue { <vscale x 1 x double>, <vscale x 1 x double> } %a.deinterleaved, 0
|
|
%a.imag = extractvalue { <vscale x 1 x double>, <vscale x 1 x double> } %a.deinterleaved, 1
|
|
%b.deinterleaved = tail call { <vscale x 1 x double>, <vscale x 1 x double> } @llvm.vector.deinterleave2.nxv2f64(<vscale x 2 x double> %b)
|
|
%b.real = extractvalue { <vscale x 1 x double>, <vscale x 1 x double> } %b.deinterleaved, 0
|
|
%b.imag = extractvalue { <vscale x 1 x double>, <vscale x 1 x double> } %b.deinterleaved, 1
|
|
%0 = fsub fast <vscale x 1 x double> %b.real, %a.imag
|
|
%1 = fadd fast <vscale x 1 x double> %b.imag, %a.real
|
|
%interleaved.vec = tail call <vscale x 2 x double> @llvm.vector.interleave2.nxv2f64(<vscale x 1 x double> %0, <vscale x 1 x double> %1)
|
|
ret <vscale x 2 x double> %interleaved.vec
|
|
}
|
|
|
|
; Expected to transform
|
|
define <vscale x 4 x double> @complex_add_v4f64(<vscale x 4 x double> %a, <vscale x 4 x double> %b) {
|
|
; CHECK-LABEL: complex_add_v4f64:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fcadd z2.d, p0/m, z2.d, z0.d, #90
|
|
; CHECK-NEXT: fcadd z3.d, p0/m, z3.d, z1.d, #90
|
|
; CHECK-NEXT: mov z0.d, z2.d
|
|
; CHECK-NEXT: mov z1.d, z3.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.deinterleaved = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
|
|
%a.real = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %a.deinterleaved, 0
|
|
%a.imag = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %a.deinterleaved, 1
|
|
%b.deinterleaved = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
|
|
%b.real = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %b.deinterleaved, 0
|
|
%b.imag = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %b.deinterleaved, 1
|
|
%0 = fsub fast <vscale x 2 x double> %b.real, %a.imag
|
|
%1 = fadd fast <vscale x 2 x double> %b.imag, %a.real
|
|
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %0, <vscale x 2 x double> %1)
|
|
ret <vscale x 4 x double> %interleaved.vec
|
|
}
|
|
|
|
; Expected to transform
|
|
define <vscale x 8 x double> @complex_add_v8f64(<vscale x 8 x double> %a, <vscale x 8 x double> %b) {
|
|
; CHECK-LABEL: complex_add_v8f64:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fcadd z4.d, p0/m, z4.d, z0.d, #90
|
|
; CHECK-NEXT: fcadd z5.d, p0/m, z5.d, z1.d, #90
|
|
; CHECK-NEXT: fcadd z6.d, p0/m, z6.d, z2.d, #90
|
|
; CHECK-NEXT: fcadd z7.d, p0/m, z7.d, z3.d, #90
|
|
; CHECK-NEXT: mov z0.d, z4.d
|
|
; CHECK-NEXT: mov z1.d, z5.d
|
|
; CHECK-NEXT: mov z2.d, z6.d
|
|
; CHECK-NEXT: mov z3.d, z7.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%a.deinterleaved = tail call { <vscale x 4 x double>, <vscale x 4 x double> } @llvm.vector.deinterleave2.nxv8f64(<vscale x 8 x double> %a)
|
|
%a.real = extractvalue { <vscale x 4 x double>, <vscale x 4 x double> } %a.deinterleaved, 0
|
|
%a.imag = extractvalue { <vscale x 4 x double>, <vscale x 4 x double> } %a.deinterleaved, 1
|
|
%b.deinterleaved = tail call { <vscale x 4 x double>, <vscale x 4 x double> } @llvm.vector.deinterleave2.nxv8f64(<vscale x 8 x double> %b)
|
|
%b.real = extractvalue { <vscale x 4 x double>, <vscale x 4 x double> } %b.deinterleaved, 0
|
|
%b.imag = extractvalue { <vscale x 4 x double>, <vscale x 4 x double> } %b.deinterleaved, 1
|
|
%0 = fsub fast <vscale x 4 x double> %b.real, %a.imag
|
|
%1 = fadd fast <vscale x 4 x double> %b.imag, %a.real
|
|
%interleaved.vec = tail call <vscale x 8 x double> @llvm.vector.interleave2.nxv8f64(<vscale x 4 x double> %0, <vscale x 4 x double> %1)
|
|
ret <vscale x 8 x double> %interleaved.vec
|
|
}
|
|
|
|
declare { <vscale x 1 x double>, <vscale x 1 x double> } @llvm.vector.deinterleave2.nxv2f64(<vscale x 2 x double>)
|
|
declare <vscale x 2 x double> @llvm.vector.interleave2.nxv2f64(<vscale x 1 x double>, <vscale x 1 x double>)
|
|
|
|
declare { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double>)
|
|
declare <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double>, <vscale x 2 x double>)
|
|
|
|
declare { <vscale x 4 x double>, <vscale x 4 x double> } @llvm.vector.deinterleave2.nxv8f64(<vscale x 8 x double>)
|
|
declare <vscale x 8 x double> @llvm.vector.interleave2.nxv8f64(<vscale x 4 x double>, <vscale x 4 x double>)
|