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
127 lines
6.7 KiB
LLVM
127 lines
6.7 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sme -force-streaming -verify-machineinstrs < %s | FileCheck %s
|
|
|
|
define void @bfmopa(<vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x bfloat> %zn, <vscale x 8 x bfloat> %zm) {
|
|
; CHECK-LABEL: bfmopa:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: bfmopa za3.s, p0/m, p1/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.mopa.wide.nxv8bf16(i32 3, <vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x bfloat> %zn, <vscale x 8 x bfloat> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @fmopa(<vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x half> %zn, <vscale x 8 x half> %zm) {
|
|
; CHECK-LABEL: fmopa:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmopa za3.s, p0/m, p1/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.mopa.wide.nxv8f16(i32 3, <vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x half> %zn, <vscale x 8 x half> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @smopa_s(<vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm) {
|
|
; CHECK-LABEL: smopa_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: smopa za3.s, p0/m, p1/m, z0.b, z1.b
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.smopa.wide.nxv16i8(i32 3, <vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @smopa_d(<vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm) #0 {
|
|
; CHECK-LABEL: smopa_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: smopa za7.d, p0/m, p1/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.smopa.wide.nxv8i16(i32 7, <vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @umopa_s(<vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm) {
|
|
; CHECK-LABEL: umopa_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: umopa za3.s, p0/m, p1/m, z0.b, z1.b
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.umopa.wide.nxv16i8(i32 3, <vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @umopa_d(<vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm) #0 {
|
|
; CHECK-LABEL: umopa_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: umopa za7.d, p0/m, p1/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.umopa.wide.nxv8i16(i32 7, <vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @fmopa_s(<vscale x 4 x i1> %pn, <vscale x 4 x i1> %pm, <vscale x 4 x float> %zn, <vscale x 4 x float> %zm) {
|
|
; CHECK-LABEL: fmopa_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmopa za3.s, p0/m, p1/m, z0.s, z1.s
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.mopa.nxv4f32(i32 3, <vscale x 4 x i1> %pn, <vscale x 4 x i1> %pm, <vscale x 4 x float> %zn, <vscale x 4 x float> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @fmopa_d(<vscale x 2 x i1> %pn, <vscale x 2 x i1> %pm, <vscale x 2 x double> %zn, <vscale x 2 x double> %zm) #1 {
|
|
; CHECK-LABEL: fmopa_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fmopa za7.d, p0/m, p1/m, z0.d, z1.d
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.mopa.nxv2f64(i32 7, <vscale x 2 x i1> %pn, <vscale x 2 x i1> %pm, <vscale x 2 x double> %zn, <vscale x 2 x double> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @sumopa_s(<vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm) {
|
|
; CHECK-LABEL: sumopa_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sumopa za3.s, p0/m, p1/m, z0.b, z1.b
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.sumopa.wide.nxv16i8(i32 3, <vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @sumopa_d(<vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm) #0 {
|
|
; CHECK-LABEL: sumopa_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sumopa za7.d, p0/m, p1/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.sumopa.wide.nxv8i16(i32 7, <vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @usmopa_s(<vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm) {
|
|
; CHECK-LABEL: usmopa_s:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: usmopa za3.s, p0/m, p1/m, z0.b, z1.b
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.usmopa.wide.nxv16i8(i32 3, <vscale x 16 x i1> %pn, <vscale x 16 x i1> %pm, <vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm)
|
|
ret void
|
|
}
|
|
|
|
define void @usmopa_d(<vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm) #0 {
|
|
; CHECK-LABEL: usmopa_d:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: usmopa za7.d, p0/m, p1/m, z0.h, z1.h
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sme.usmopa.wide.nxv8i16(i32 7, <vscale x 8 x i1> %pn, <vscale x 8 x i1> %pm, <vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm)
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { "target-features"="+sme-i16i64" }
|
|
attributes #1 = { "target-features"="+sme-f64f64" }
|
|
|
|
declare void @llvm.aarch64.sme.mopa.wide.nxv8bf16(i32, <vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
|
|
declare void @llvm.aarch64.sme.mopa.wide.nxv8f16(i32, <vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare void @llvm.aarch64.sme.mopa.nxv4f32(i32, <vscale x 4 x i1>, <vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
|
|
declare void @llvm.aarch64.sme.mopa.nxv2f64(i32, <vscale x 2 x i1>, <vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
|
|
declare void @llvm.aarch64.sme.smopa.wide.nxv16i8(i32, <vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare void @llvm.aarch64.sme.smopa.wide.nxv8i16(i32, <vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare void @llvm.aarch64.sme.umopa.wide.nxv16i8(i32, <vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare void @llvm.aarch64.sme.umopa.wide.nxv8i16(i32, <vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare void @llvm.aarch64.sme.sumopa.wide.nxv16i8(i32, <vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare void @llvm.aarch64.sme.sumopa.wide.nxv8i16(i32, <vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare void @llvm.aarch64.sme.usmopa.wide.nxv16i8(i32, <vscale x 16 x i1>, <vscale x 16 x i1>, <vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare void @llvm.aarch64.sme.usmopa.wide.nxv8i16(i32, <vscale x 8 x i1>, <vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
|