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
111 lines
8.8 KiB
LLVM
111 lines
8.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 6
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme2p2 -force-streaming -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
define { <vscale x 8 x half>, <vscale x 8 x half> } @multi_vec_mul_single_x2_f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zm) {
|
|
; CHECK-LABEL: multi_vec_mul_single_x2_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.h, z1.h }, { z0.h, z1.h }, z2.h
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.fmul.single.x2.nxv8f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zm)
|
|
ret { <vscale x 8 x half>, <vscale x 8 x half> } %res
|
|
}
|
|
|
|
define { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @multi_vec_mul_single_x4_f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zdn3, <vscale x 8 x half> %zdn4, <vscale x 8 x half> %zm) {
|
|
; CHECK-LABEL: multi_vec_mul_single_x4_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.h - z3.h }, { z0.h - z3.h }, z4.h
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.fmul.single.x4.nxv8f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zdn3, <vscale x 8 x half> %zdn4, <vscale x 8 x half> %zm)
|
|
ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } %res
|
|
}
|
|
|
|
define { <vscale x 8 x half>, <vscale x 8 x half> } @multi_vec_mul_x2_f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zm1, <vscale x 8 x half> %zm2) {
|
|
; CHECK-LABEL: multi_vec_mul_x2_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.h, z1.h }, { z0.h, z1.h }, { z2.h, z3.h }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.fmul.x2.nxv8f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zm1, <vscale x 8 x half> %zm2)
|
|
ret { <vscale x 8 x half>, <vscale x 8 x half> } %res
|
|
}
|
|
|
|
define { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @multi_vec_mul_x4_f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zdn3, <vscale x 8 x half> %zdn4, <vscale x 8 x half> %zm1, <vscale x 8 x half> %zm2, <vscale x 8 x half> %zm3, <vscale x 8 x half> %zm4) {
|
|
; CHECK-LABEL: multi_vec_mul_x4_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.h - z3.h }, { z0.h - z3.h }, { z4.h - z7.h }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } @llvm.aarch64.sve.fmul.x4.nxv8f16(<vscale x 8 x half> %zdn1, <vscale x 8 x half> %zdn2, <vscale x 8 x half> %zdn3, <vscale x 8 x half> %zdn4, <vscale x 8 x half> %zm1, <vscale x 8 x half> %zm2, <vscale x 8 x half> %zm3, <vscale x 8 x half> %zm4)
|
|
ret { <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half>, <vscale x 8 x half> } %res
|
|
}
|
|
|
|
define { <vscale x 4 x float>, <vscale x 4 x float> } @multi_vec_mul_single_x2_f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zm) {
|
|
; CHECK-LABEL: multi_vec_mul_single_x2_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.s, z1.s }, { z0.s, z1.s }, z2.s
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.fmul.single.x2.nxv4f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zm)
|
|
ret { <vscale x 4 x float>, <vscale x 4 x float> } %res
|
|
}
|
|
|
|
define { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @multi_vec_mul_single_x4_f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zdn3, <vscale x 4 x float> %zdn4, <vscale x 4 x float> %zm) {
|
|
; CHECK-LABEL: multi_vec_mul_single_x4_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.s - z3.s }, { z0.s - z3.s }, z4.s
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.fmul.single.x4.nxv4f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zdn3, <vscale x 4 x float> %zdn4, <vscale x 4 x float> %zm)
|
|
ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } %res
|
|
}
|
|
|
|
define { <vscale x 4 x float>, <vscale x 4 x float> } @multi_vec_mul_x2_f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zm1, <vscale x 4 x float> %zm2) {
|
|
; CHECK-LABEL: multi_vec_mul_x2_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.s, z1.s }, { z0.s, z1.s }, { z2.s, z3.s }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.fmul.x2.nxv4f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zm1, <vscale x 4 x float> %zm2)
|
|
ret { <vscale x 4 x float>, <vscale x 4 x float> } %res
|
|
}
|
|
|
|
define { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @multi_vec_mul_x4_f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zdn3, <vscale x 4 x float> %zdn4, <vscale x 4 x float> %zm1, <vscale x 4 x float> %zm2, <vscale x 4 x float> %zm3, <vscale x 4 x float> %zm4) {
|
|
; CHECK-LABEL: multi_vec_mul_x4_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.s - z3.s }, { z0.s - z3.s }, { z4.s - z7.s }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } @llvm.aarch64.sve.fmul.x4.nxv4f32(<vscale x 4 x float> %zdn1, <vscale x 4 x float> %zdn2, <vscale x 4 x float> %zdn3, <vscale x 4 x float> %zdn4, <vscale x 4 x float> %zm1, <vscale x 4 x float> %zm2, <vscale x 4 x float> %zm3, <vscale x 4 x float> %zm4)
|
|
ret { <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float>, <vscale x 4 x float> } %res
|
|
}
|
|
|
|
define { <vscale x 2 x double>, <vscale x 2 x double> } @multi_vec_mul_single_x2_f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zm) {
|
|
; CHECK-LABEL: multi_vec_mul_single_x2_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.d, z1.d }, { z0.d, z1.d }, z2.d
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.fmul.single.x2.nxv2f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zm)
|
|
ret { <vscale x 2 x double>, <vscale x 2 x double> } %res
|
|
}
|
|
|
|
define { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @multi_vec_mul_single_x4_f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zdn3, <vscale x 2 x double> %zdn4, <vscale x 2 x double> %zm) {
|
|
; CHECK-LABEL: multi_vec_mul_single_x4_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.d - z3.d }, { z0.d - z3.d }, z4.d
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.fmul.single.x4.nxv2f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zdn3, <vscale x 2 x double> %zdn4, <vscale x 2 x double> %zm)
|
|
ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %res
|
|
}
|
|
|
|
define { <vscale x 2 x double>, <vscale x 2 x double> } @multi_vec_mul_x2_f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zm1, <vscale x 2 x double> %zm2) {
|
|
; CHECK-LABEL: multi_vec_mul_x2_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.d, z1.d }, { z0.d, z1.d }, { z2.d, z3.d }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.fmul.x2.nxv2f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zm1, <vscale x 2 x double> %zm2)
|
|
ret { <vscale x 2 x double>, <vscale x 2 x double> } %res
|
|
}
|
|
|
|
define { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @multi_vec_mul_x4_f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zdn3, <vscale x 2 x double> %zdn4, <vscale x 2 x double> %zm1, <vscale x 2 x double> %zm2, <vscale x 2 x double> %zm3, <vscale x 2 x double> %zm4) {
|
|
; CHECK-LABEL: multi_vec_mul_x4_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmul { z0.d - z3.d }, { z0.d - z3.d }, { z4.d - z7.d }
|
|
; CHECK-NEXT: ret
|
|
%res = call { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } @llvm.aarch64.sve.fmul.x4.nxv2f64(<vscale x 2 x double> %zdn1, <vscale x 2 x double> %zdn2, <vscale x 2 x double> %zdn3, <vscale x 2 x double> %zdn4, <vscale x 2 x double> %zm1, <vscale x 2 x double> %zm2, <vscale x 2 x double> %zm3, <vscale x 2 x double> %zm4)
|
|
ret { <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double>, <vscale x 2 x double> } %res
|
|
}
|