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
87 lines
4.2 KiB
LLVM
87 lines
4.2 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve2p1 < %s | FileCheck %s
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve,+sme2p1 < %s | FileCheck %s
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sme2p1 -force-streaming < %s | FileCheck %s
|
|
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sme,+sve2p1 -force-streaming < %s | FileCheck %s
|
|
|
|
define <vscale x 16 x i8> @test_extq_i8 (<vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm) {
|
|
; CHECK-LABEL: test_extq_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #15
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 16 x i8> @llvm.aarch64.sve.extq.nxv16i8(<vscale x 16 x i8> %zn, <vscale x 16 x i8> %zm, i32 15)
|
|
ret <vscale x 16 x i8> %res
|
|
}
|
|
|
|
define <vscale x 8 x i16> @test_extq_i16 (<vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm) {
|
|
; CHECK-LABEL: test_extq_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #2
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 8 x i16> @llvm.aarch64.sve.extq.nxv8i16(<vscale x 8 x i16> %zn, <vscale x 8 x i16> %zm, i32 1)
|
|
ret <vscale x 8 x i16> %res
|
|
}
|
|
|
|
define <vscale x 4 x i32> @test_extq_i32 (<vscale x 4 x i32> %zn, <vscale x 4 x i32> %zm) {
|
|
; CHECK-LABEL: test_extq_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #8
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 4 x i32> @llvm.aarch64.sve.extq.nxv4i32(<vscale x 4 x i32> %zn, <vscale x 4 x i32> %zm, i32 2)
|
|
ret <vscale x 4 x i32> %res
|
|
}
|
|
|
|
define <vscale x 2 x i64> @test_extq_i64 (<vscale x 2 x i64> %zn, <vscale x 2 x i64> %zm) {
|
|
; CHECK-LABEL: test_extq_i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #8
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 2 x i64> @llvm.aarch64.sve.extq.nxv2i64(<vscale x 2 x i64> %zn, <vscale x 2 x i64> %zm, i32 1)
|
|
ret <vscale x 2 x i64> %res
|
|
}
|
|
|
|
define <vscale x 8 x half> @test_extq_f16(<vscale x 8 x half> %zn, <vscale x 8 x half> %zm) {
|
|
; CHECK-LABEL: test_extq_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #14
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 8 x half> @llvm.aarch64.sve.extq.nxv8f16(<vscale x 8 x half> %zn, <vscale x 8 x half> %zm, i32 7)
|
|
ret <vscale x 8 x half> %res
|
|
}
|
|
|
|
define <vscale x 4 x float> @test_extq_f32(<vscale x 4 x float> %zn, <vscale x 4 x float> %zm) {
|
|
; CHECK-LABEL: test_extq_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #4
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 4 x float> @llvm.aarch64.sve.extq.nxv4f32(<vscale x 4 x float> %zn, <vscale x 4 x float> %zm, i32 1)
|
|
ret <vscale x 4 x float> %res
|
|
}
|
|
|
|
define <vscale x 2 x double> @test_extq_f64(<vscale x 2 x double> %zn, <vscale x 2 x double> %zm) {
|
|
; CHECK-LABEL: test_extq_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #8
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 2 x double> @llvm.aarch64.sve.extq.nxv2f64(<vscale x 2 x double> %zn, <vscale x 2 x double> %zm, i32 1)
|
|
ret <vscale x 2 x double> %res
|
|
}
|
|
|
|
define <vscale x 8 x bfloat> @test_extq_bf16(<vscale x 8 x bfloat> %zn, <vscale x 8 x bfloat> %zm) {
|
|
; CHECK-LABEL: test_extq_bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: extq z0.b, z0.b, z1.b, #6
|
|
; CHECK-NEXT: ret
|
|
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.extq.nxv8bf16(<vscale x 8 x bfloat> %zn, <vscale x 8 x bfloat> %zm, i32 3)
|
|
ret <vscale x 8 x bfloat> %res
|
|
}
|
|
|
|
declare <vscale x 16 x i8> @llvm.aarch64.sve.extq.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>, i32)
|
|
declare <vscale x 8 x i16> @llvm.aarch64.sve.extq.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>, i32)
|
|
declare <vscale x 4 x i32> @llvm.aarch64.sve.extq.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>, i32)
|
|
declare <vscale x 2 x i64> @llvm.aarch64.sve.extq.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>, i32)
|
|
declare <vscale x 8 x half> @llvm.aarch64.sve.extq.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>, i32)
|
|
declare <vscale x 4 x float> @llvm.aarch64.sve.extq.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>, i32)
|
|
declare <vscale x 2 x double> @llvm.aarch64.sve.extq.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>, i32)
|
|
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.extq.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>, i32)
|