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
124 lines
6.0 KiB
LLVM
124 lines
6.0 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
|
|
|
|
define void @masked_scatter_nxv2i8(<vscale x 2 x i8> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1b { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2i8(<vscale x 2 x i8> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2i16(<vscale x 2 x i16> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2i16(<vscale x 2 x i16> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2i32(<vscale x 2 x i32> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2i32(<vscale x 2 x i32> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2i64(<vscale x 2 x i64> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2bf16(<vscale x 2 x bfloat> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind #0 {
|
|
; CHECK-LABEL: masked_scatter_nxv2bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1h { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2bf16(<vscale x 2 x bfloat> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2f32(<vscale x 2 x float> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x ptr> %ptrs, <vscale x 2 x i1> %masks) nounwind {
|
|
; CHECK-LABEL: masked_scatter_nxv2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [z1.d]
|
|
; CHECK-NEXT: ret
|
|
call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x ptr> %ptrs, i32 0, <vscale x 2 x i1> %masks)
|
|
ret void
|
|
}
|
|
|
|
define void @masked_scatter_splat_constant_pointer (<vscale x 4 x i1> %pg) {
|
|
; CHECK-LABEL: masked_scatter_splat_constant_pointer:
|
|
; CHECK: // %bb.0: // %vector.body
|
|
; CHECK-NEXT: movi v0.2d, #0000000000000000
|
|
; CHECK-NEXT: punpklo p1.h, p0.b
|
|
; CHECK-NEXT: punpkhi p0.h, p0.b
|
|
; CHECK-NEXT: st1w { z0.d }, p1, [z0.d]
|
|
; CHECK-NEXT: st1w { z0.d }, p0, [z0.d]
|
|
; CHECK-NEXT: ret
|
|
vector.body:
|
|
call void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32> undef, <vscale x 4 x ptr> zeroinitializer, i32 4, <vscale x 4 x i1> %pg)
|
|
ret void
|
|
}
|
|
|
|
%i64_x3 = type { i64, i64, i64 }
|
|
define void @masked_scatter_non_power_of_two_based_scaling(<vscale x 2 x double> %data, ptr %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_non_power_of_two_based_scaling:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mul z1.d, z1.d, #24
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr inbounds %i64_x3, ptr %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
%i64_x4 = type { i64, i64, i64, i64}
|
|
define void @masked_scatter_non_element_type_based_scaling(<vscale x 2 x double> %data, ptr %base, <vscale x 2 x i64> %offsets, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_scatter_non_element_type_based_scaling:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: lsl z1.d, z1.d, #5
|
|
; CHECK-NEXT: st1d { z0.d }, p0, [x0, z1.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr inbounds %i64_x4, ptr %base, <vscale x 2 x i64> %offsets
|
|
call void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double> %data, <vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask)
|
|
ret void
|
|
}
|
|
|
|
declare void @llvm.masked.scatter.nxv2f16(<vscale x 2 x half>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2bf16(<vscale x 2 x bfloat>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2f32(<vscale x 2 x float>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2f64(<vscale x 2 x double>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv2i8(<vscale x 2 x i8>, <vscale x 2 x ptr>, i32, <vscale x 2 x i1>)
|
|
declare void @llvm.masked.scatter.nxv4i32.nxv4p0(<vscale x 4 x i32>, <vscale x 4 x ptr>, i32, <vscale x 4 x i1>)
|
|
attributes #0 = { "target-features"="+sve,+bf16" }
|