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
209 lines
11 KiB
LLVM
209 lines
11 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
|
|
|
|
;
|
|
; ST1H, ST1W, ST1D: base + 32-bit scaled offset, sign (sxtw) or zero
|
|
; (uxtw) extended to 64 bits.
|
|
; e.g. st1h { z0.d }, p0, [x0, z1.d, uxtw #1]
|
|
;
|
|
|
|
; ST1H
|
|
define void @sst1h_s_uxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %indices) {
|
|
; CHECK-LABEL: sst1h_s_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.s }, p0, [x0, z1.s, uxtw #1]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 4 x i32> %data to <vscale x 4 x i16>
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv4i16(<vscale x 4 x i16> %data_trunc,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1h_s_sxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %indices) {
|
|
; CHECK-LABEL: sst1h_s_sxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.s }, p0, [x0, z1.s, sxtw #1]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 4 x i32> %data to <vscale x 4 x i16>
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv4i16(<vscale x 4 x i16> %data_trunc,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1h_d_uxtw(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1h_d_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [x0, z1.d, uxtw #1]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i16>
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2i16(<vscale x 2 x i16> %data_trunc,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1h_d_sxtw(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1h_d_sxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [x0, z1.d, sxtw #1]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i16>
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2i16(<vscale x 2 x i16> %data_trunc,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
; ST1W
|
|
define void @sst1w_s_uxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %indices) {
|
|
; CHECK-LABEL: sst1w_s_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.s }, p0, [x0, z1.s, uxtw #2]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv4i32(<vscale x 4 x i32> %data,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1w_s_sxtw(<vscale x 4 x i32> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %indices) {
|
|
; CHECK-LABEL: sst1w_s_sxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.s }, p0, [x0, z1.s, sxtw #2]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv4i32(<vscale x 4 x i32> %data,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1w_d_uxtw(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1w_d_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [x0, z1.d, uxtw #2]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i32>
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2i32(<vscale x 2 x i32> %data_trunc,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1w_d_sxtw(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1w_d_sxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [x0, z1.d, sxtw #2]
|
|
; CHECK-NEXT: ret
|
|
%data_trunc = trunc <vscale x 2 x i64> %data to <vscale x 2 x i32>
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2i32(<vscale x 2 x i32> %data_trunc,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1w_s_uxtw_float(<vscale x 4 x float> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %indices) {
|
|
; CHECK-LABEL: sst1w_s_uxtw_float:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.s }, p0, [x0, z1.s, uxtw #2]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv4f32(<vscale x 4 x float> %data,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1w_s_sxtw_float(<vscale x 4 x float> %data, <vscale x 4 x i1> %pg, ptr %base, <vscale x 4 x i32> %indices) {
|
|
; CHECK-LABEL: sst1w_s_sxtw_float:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.s }, p0, [x0, z1.s, sxtw #2]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv4f32(<vscale x 4 x float> %data,
|
|
<vscale x 4 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 4 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
; ST1D
|
|
define void @sst1d_d_uxtw(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1d_d_uxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d, uxtw #3]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2i64(<vscale x 2 x i64> %data,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1d_d_sxtw(<vscale x 2 x i64> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1d_d_sxtw:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d, sxtw #3]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2i64(<vscale x 2 x i64> %data,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1d_d_uxtw_double(<vscale x 2 x double> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1d_d_uxtw_double:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d, uxtw #3]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2f64(<vscale x 2 x double> %data,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
define void @sst1d_d_sxtw_double(<vscale x 2 x double> %data, <vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i32> %indices) {
|
|
; CHECK-LABEL: sst1d_d_sxtw_double:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d, sxtw #3]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2f64(<vscale x 2 x double> %data,
|
|
<vscale x 2 x i1> %pg,
|
|
ptr %base,
|
|
<vscale x 2 x i32> %indices)
|
|
ret void
|
|
}
|
|
|
|
|
|
; ST1H
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
|
|
; ST1W
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv4f32(<vscale x 4 x float>, <vscale x 4 x i1>, ptr, <vscale x 4 x i32>)
|
|
|
|
; ST1D
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
|
|
declare void @llvm.aarch64.sve.st1.scatter.sxtw.index.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|
|
declare void @llvm.aarch64.sve.st1.scatter.uxtw.index.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, ptr, <vscale x 2 x i32>)
|