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
106 lines
6.8 KiB
LLVM
106 lines
6.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s --mattr=+complxnum,+sve,+fullfp16 -o - | FileCheck %s
|
|
|
|
target triple = "aarch64"
|
|
|
|
define <vscale x 4 x double> @simple_symmetric_muladd2(<vscale x 4 x double> %a, <vscale x 4 x double> %b) {
|
|
; CHECK-LABEL: simple_symmetric_muladd2:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: adrp x8, .LCPI0_0
|
|
; CHECK-NEXT: add x8, x8, :lo12:.LCPI0_0
|
|
; CHECK-NEXT: ld1rd { z4.d }, p0/z, [x8]
|
|
; CHECK-NEXT: fmad z0.d, p0/m, z4.d, z2.d
|
|
; CHECK-NEXT: fmad z1.d, p0/m, z4.d, z3.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
|
|
%ext00 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
|
|
%ext01 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
|
|
%fmul0 = fmul fast <vscale x 2 x double> %ext00, splat (double 3.200000e+00)
|
|
%strided.vec44 = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %b)
|
|
%ext10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec44, 0
|
|
%ext11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec44, 1
|
|
%fadd0 = fadd fast <vscale x 2 x double> %ext10, %fmul0
|
|
%fmul1 = fmul fast <vscale x 2 x double> %ext01, splat (double 3.200000e+00)
|
|
%fadd1 = fadd fast <vscale x 2 x double> %ext11, %fmul1
|
|
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %fadd0, <vscale x 2 x double> %fadd1)
|
|
ret <vscale x 4 x double> %interleaved.vec
|
|
}
|
|
|
|
define <vscale x 4 x double> @simple_symmetric_unary2(<vscale x 4 x double> %a) {
|
|
; CHECK-LABEL: simple_symmetric_unary2:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fneg z0.d, p0/m, z0.d
|
|
; CHECK-NEXT: fneg z1.d, p0/m, z1.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave2.nxv4f64(<vscale x 4 x double> %a)
|
|
%ext00 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
|
|
%ext01 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
|
|
%fneg0 = fneg fast <vscale x 2 x double> %ext00
|
|
%fneg1 = fneg fast <vscale x 2 x double> %ext01
|
|
%interleaved.vec = tail call <vscale x 4 x double> @llvm.vector.interleave2.nxv4f64(<vscale x 2 x double> %fneg0, <vscale x 2 x double> %fneg1)
|
|
ret <vscale x 4 x double> %interleaved.vec
|
|
}
|
|
|
|
define <vscale x 8 x double> @simple_symmetric_muladd4(<vscale x 8 x double> %a, <vscale x 8 x double> %b) {
|
|
; CHECK-LABEL: simple_symmetric_muladd4:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: adrp x8, .LCPI2_0
|
|
; CHECK-NEXT: add x8, x8, :lo12:.LCPI2_0
|
|
; CHECK-NEXT: ld1rd { z24.d }, p0/z, [x8]
|
|
; CHECK-NEXT: fmad z0.d, p0/m, z24.d, z4.d
|
|
; CHECK-NEXT: fmad z1.d, p0/m, z24.d, z5.d
|
|
; CHECK-NEXT: fmad z2.d, p0/m, z24.d, z6.d
|
|
; CHECK-NEXT: fmad z3.d, p0/m, z24.d, z7.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave4.nxv8f64(<vscale x 8 x double> %a)
|
|
%ext00 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
|
|
%ext01 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
|
|
%ext02 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 2
|
|
%ext03 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 3
|
|
%fmul0 = fmul fast <vscale x 2 x double> %ext00, splat (double 3.200000e+00)
|
|
%strided.vec44 = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave4.nxv8f64(<vscale x 8 x double> %b)
|
|
%ext10 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec44, 0
|
|
%ext11 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec44, 1
|
|
%ext12 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec44, 2
|
|
%ext13 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec44, 3
|
|
%fadd0 = fadd fast <vscale x 2 x double> %ext10, %fmul0
|
|
%fmul1 = fmul fast <vscale x 2 x double> %ext01, splat (double 3.200000e+00)
|
|
%fadd1 = fadd fast <vscale x 2 x double> %ext11, %fmul1
|
|
%fmul2 = fmul fast <vscale x 2 x double> %ext02, splat (double 3.200000e+00)
|
|
%fadd2 = fadd fast <vscale x 2 x double> %ext12, %fmul2
|
|
%fmul3 = fmul fast <vscale x 2 x double> %ext03, splat (double 3.200000e+00)
|
|
%fadd3 = fadd fast <vscale x 2 x double> %ext13, %fmul3
|
|
%interleaved.vec = tail call <vscale x 8 x double> @llvm.vector.interleave4.nxv8f64(<vscale x 2 x double> %fadd0, <vscale x 2 x double> %fadd1, <vscale x 2 x double> %fadd2, <vscale x 2 x double> %fadd3)
|
|
ret <vscale x 8 x double> %interleaved.vec
|
|
}
|
|
|
|
|
|
define <vscale x 8 x double> @simple_symmetric_unary4(<vscale x 8 x double> %a) {
|
|
; CHECK-LABEL: simple_symmetric_unary4:
|
|
; CHECK: // %bb.0: // %entry
|
|
; CHECK-NEXT: ptrue p0.d
|
|
; CHECK-NEXT: fneg z0.d, p0/m, z0.d
|
|
; CHECK-NEXT: fneg z1.d, p0/m, z1.d
|
|
; CHECK-NEXT: fneg z2.d, p0/m, z2.d
|
|
; CHECK-NEXT: fneg z3.d, p0/m, z3.d
|
|
; CHECK-NEXT: ret
|
|
entry:
|
|
%strided.vec = tail call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.vector.deinterleave4.nxv8f64(<vscale x 8 x double> %a)
|
|
%ext00 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 0
|
|
%ext01 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 1
|
|
%ext02 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 2
|
|
%ext03 = extractvalue { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %strided.vec, 3
|
|
%fneg0 = fneg fast <vscale x 2 x double> %ext00
|
|
%fneg1 = fneg fast <vscale x 2 x double> %ext01
|
|
%fneg2 = fneg fast <vscale x 2 x double> %ext02
|
|
%fneg3 = fneg fast <vscale x 2 x double> %ext03
|
|
%interleaved.vec = tail call <vscale x 8 x double> @llvm.vector.interleave4.nxv8f64(<vscale x 2 x double> %fneg0, <vscale x 2 x double> %fneg1, <vscale x 2 x double> %fneg2, <vscale x 2 x double> %fneg3)
|
|
ret <vscale x 8 x double> %interleaved.vec
|
|
}
|