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
66 lines
3.3 KiB
LLVM
66 lines
3.3 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=+sme2 -force-streaming < %s | FileCheck %s
|
|
|
|
; lookup table expand one register
|
|
|
|
define {<vscale x 16 x i8>, <vscale x 16 x i8>} @luti2_i8(<vscale x 16 x i8> %x) {
|
|
; CHECK-LABEL: luti2_i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: luti2 { z0.b, z1.b }, zt0, z0[7]
|
|
; CHECK-NEXT: ret
|
|
%res = call {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv16i8(i32 0, <vscale x 16 x i8> %x, i32 7)
|
|
ret {<vscale x 16 x i8>, <vscale x 16 x i8>} %res
|
|
}
|
|
|
|
define {<vscale x 8 x i16>, <vscale x 8 x i16>} @luti2_i16(<vscale x 16 x i8> %x) {
|
|
; CHECK-LABEL: luti2_i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: luti2 { z0.h, z1.h }, zt0, z0[7]
|
|
; CHECK-NEXT: ret
|
|
%res = call {<vscale x 8 x i16>, <vscale x 8 x i16>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv8i16(i32 0, <vscale x 16 x i8> %x, i32 7)
|
|
ret {<vscale x 8 x i16>, <vscale x 8 x i16>} %res
|
|
}
|
|
|
|
define {<vscale x 4 x i32>, <vscale x 4 x i32>} @luti2_i32(<vscale x 16 x i8> %x) {
|
|
; CHECK-LABEL: luti2_i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: luti2 { z0.s, z1.s }, zt0, z0[7]
|
|
; CHECK-NEXT: ret
|
|
%res = call {<vscale x 4 x i32>, <vscale x 4 x i32>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv4i32(i32 0, <vscale x 16 x i8> %x, i32 7)
|
|
ret {<vscale x 4 x i32>, <vscale x 4 x i32>} %res
|
|
}
|
|
|
|
define {<vscale x 8 x half>, <vscale x 8 x half>} @luti2_f16(<vscale x 16 x i8> %x) {
|
|
; CHECK-LABEL: luti2_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: luti2 { z0.h, z1.h }, zt0, z0[7]
|
|
; CHECK-NEXT: ret
|
|
%res = call {<vscale x 8 x half>, <vscale x 8 x half>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv8f16(i32 0, <vscale x 16 x i8> %x, i32 7)
|
|
ret {<vscale x 8 x half>, <vscale x 8 x half>} %res
|
|
}
|
|
|
|
define {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} @luti2_bf16(<vscale x 16 x i8> %x) {
|
|
; CHECK-LABEL: luti2_bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: luti2 { z0.h, z1.h }, zt0, z0[7]
|
|
; CHECK-NEXT: ret
|
|
%res = call {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv8bf16(i32 0, <vscale x 16 x i8> %x, i32 7)
|
|
ret {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} %res
|
|
}
|
|
|
|
define {<vscale x 4 x float>, <vscale x 4 x float>} @luti2_f32(<vscale x 16 x i8> %x) {
|
|
; CHECK-LABEL: luti2_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: luti2 { z0.s, z1.s }, zt0, z0[7]
|
|
; CHECK-NEXT: ret
|
|
%res = call {<vscale x 4 x float>, <vscale x 4 x float>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv4f32(i32 0, <vscale x 16 x i8> %x, i32 7)
|
|
ret {<vscale x 4 x float>, <vscale x 4 x float>} %res
|
|
}
|
|
|
|
declare {<vscale x 16 x i8>, <vscale x 16 x i8>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv16i8(i32, <vscale x 16 x i8>, i32)
|
|
declare {<vscale x 8 x i16>, <vscale x 8 x i16>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv8i16(i32, <vscale x 16 x i8>, i32)
|
|
declare {<vscale x 4 x i32>, <vscale x 4 x i32>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv4i32(i32, <vscale x 16 x i8>, i32)
|
|
declare {<vscale x 8 x half>, <vscale x 8 x half>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv8f16(i32, <vscale x 16 x i8>, i32)
|
|
declare {<vscale x 8 x bfloat>, <vscale x 8 x bfloat>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv8bf16(i32, <vscale x 16 x i8>, i32)
|
|
declare {<vscale x 4 x float>, <vscale x 4 x float>} @llvm.aarch64.sme.luti2.lane.zt.x2.nxv4f32(i32, <vscale x 16 x i8>, i32)
|