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
83 lines
4.4 KiB
LLVM
83 lines
4.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
|
|
|
|
;
|
|
; STNT1B, STNT1W, STNT1H, STNT1D: base + 32-bit unscaled offset, zero (uxtw)
|
|
; extended to 64 bits.
|
|
; e.g. stnt1h { z0.d }, p0, [z1.d, x0]
|
|
;
|
|
|
|
; STNT1B
|
|
define void @sstnt1b_s_uxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %offsets) {
|
|
; CHECK-LABEL: sstnt1b_s_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stnt1b { z0.s }, p0, [z1.s, x0]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 4 x i32> %data to <vscale x 4 x i8>
|
|
call void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4i8(<vscale x 4 x i8> %data_trunc,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %offsets)
|
|
ret void
|
|
}
|
|
|
|
; STNT1H
|
|
define void @sstnt1h_s_uxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %offsets) {
|
|
; CHECK-LABEL: sstnt1h_s_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stnt1h { z0.s }, p0, [z1.s, x0]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 4 x i32> %data to <vscale x 4 x i16>
|
|
call void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4i16(<vscale x 4 x i16> %data_trunc,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %offsets)
|
|
ret void
|
|
}
|
|
|
|
; STNT1W
|
|
define void @sstnt1w_s_uxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %offsets) {
|
|
; CHECK-LABEL: sstnt1w_s_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stnt1w { z0.s }, p0, [z1.s, x0]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4i32(<vscale x 4 x i32> %data,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %offsets)
|
|
ret void
|
|
}
|
|
|
|
define void @sstnt1w_s_uxtw_float(<vscale x 4 x float> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %offsets) {
|
|
; CHECK-LABEL: sstnt1w_s_uxtw_float:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: stnt1w { z0.s }, p0, [z1.s, x0]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4f32(<vscale x 4 x float> %data,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %offsets)
|
|
ret void
|
|
}
|
|
|
|
; STNT1B
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
|
|
; STNT1H
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
|
|
; STNT1W
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.sxtw.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.stnt1.scatter.uxtw.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|