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
187 lines
9.5 KiB
LLVM
187 lines
9.5 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 <vscale x 2 x i64> @masked_gather_nxv2i8(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1b { z0.d }, p0/z, [z0.d, #1]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i8, <vscale x 2 x ptr> %bases, i32 1
|
|
%vals = call <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x ptr> %ptrs, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> poison)
|
|
%vals.zext = zext <vscale x 2 x i8> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.zext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @masked_gather_nxv2i16(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1h { z0.d }, p0/z, [z0.d, #2]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i16, <vscale x 2 x ptr> %bases, i32 1
|
|
%vals = call <vscale x 2 x i16> @llvm.masked.gather.nxv2i16(<vscale x 2 x ptr> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> poison)
|
|
%vals.zext = zext <vscale x 2 x i16> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.zext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @masked_gather_nxv2i32(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1w { z0.d }, p0/z, [z0.d, #4]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i32, <vscale x 2 x ptr> %bases, i32 1
|
|
%vals = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x ptr> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> poison)
|
|
%vals.zext = zext <vscale x 2 x i32> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.zext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @masked_gather_nxv2i64(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2i64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1d { z0.d }, p0/z, [z0.d, #8]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i64, <vscale x 2 x ptr> %bases, i32 1
|
|
%vals.zext = call <vscale x 2 x i64> @llvm.masked.gather.nxv2i64(<vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask, <vscale x 2 x i64> poison)
|
|
ret <vscale x 2 x i64> %vals.zext
|
|
}
|
|
|
|
define <vscale x 2 x half> @masked_gather_nxv2f16(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1h { z0.d }, p0/z, [z0.d, #4]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr half, <vscale x 2 x ptr> %bases, i32 2
|
|
%vals = call <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x ptr> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x half> poison)
|
|
ret <vscale x 2 x half> %vals
|
|
}
|
|
|
|
define <vscale x 2 x bfloat> @masked_gather_nxv2bf16(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) #0 {
|
|
; CHECK-LABEL: masked_gather_nxv2bf16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1h { z0.d }, p0/z, [z0.d, #4]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr bfloat, <vscale x 2 x ptr> %bases, i32 2
|
|
%vals = call <vscale x 2 x bfloat> @llvm.masked.gather.nxv2bf16(<vscale x 2 x ptr> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x bfloat> poison)
|
|
ret <vscale x 2 x bfloat> %vals
|
|
}
|
|
|
|
define <vscale x 2 x float> @masked_gather_nxv2f32(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1w { z0.d }, p0/z, [z0.d, #12]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr float, <vscale x 2 x ptr> %bases, i32 3
|
|
%vals = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32(<vscale x 2 x ptr> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x float> poison)
|
|
ret <vscale x 2 x float> %vals
|
|
}
|
|
|
|
define <vscale x 2 x double> @masked_gather_nxv2f64(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1d { z0.d }, p0/z, [z0.d, #32]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr double, <vscale x 2 x ptr> %bases, i32 4
|
|
%vals = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask, <vscale x 2 x double> poison)
|
|
ret <vscale x 2 x double> %vals
|
|
}
|
|
|
|
define <vscale x 2 x i64> @masked_sgather_nxv2i8(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_sgather_nxv2i8:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1sb { z0.d }, p0/z, [z0.d, #5]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i8, <vscale x 2 x ptr> %bases, i32 5
|
|
%vals = call <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x ptr> %ptrs, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> poison)
|
|
%vals.sext = sext <vscale x 2 x i8> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.sext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @masked_sgather_nxv2i16(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_sgather_nxv2i16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1sh { z0.d }, p0/z, [z0.d, #12]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i16, <vscale x 2 x ptr> %bases, i32 6
|
|
%vals = call <vscale x 2 x i16> @llvm.masked.gather.nxv2i16(<vscale x 2 x ptr> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x i16> poison)
|
|
%vals.sext = sext <vscale x 2 x i16> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.sext
|
|
}
|
|
|
|
define <vscale x 2 x i64> @masked_sgather_nxv2i32(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_sgather_nxv2i32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: ld1sw { z0.d }, p0/z, [z0.d, #28]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i32, <vscale x 2 x ptr> %bases, i32 7
|
|
%vals = call <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x ptr> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x i32> poison)
|
|
%vals.sext = sext <vscale x 2 x i32> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.sext
|
|
}
|
|
|
|
; Tests where the immediate is out of range
|
|
|
|
define <vscale x 2 x i64> @masked_gather_nxv2i8_range(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2i8_range:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov w8, #32
|
|
; CHECK-NEXT: ld1b { z0.d }, p0/z, [x8, z0.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr i8, <vscale x 2 x ptr> %bases, i32 32
|
|
%vals = call <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x ptr> %ptrs, i32 1, <vscale x 2 x i1> %mask, <vscale x 2 x i8> poison)
|
|
%vals.zext = zext <vscale x 2 x i8> %vals to <vscale x 2 x i64>
|
|
ret <vscale x 2 x i64> %vals.zext
|
|
}
|
|
|
|
define <vscale x 2 x half> @masked_gather_nxv2f16_range(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2f16_range:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov w8, #64
|
|
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x8, z0.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr half, <vscale x 2 x ptr> %bases, i32 32
|
|
%vals = call <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x ptr> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x half> poison)
|
|
ret <vscale x 2 x half> %vals
|
|
}
|
|
|
|
define <vscale x 2 x bfloat> @masked_gather_nxv2bf16_range(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) #0 {
|
|
; CHECK-LABEL: masked_gather_nxv2bf16_range:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov w8, #64
|
|
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x8, z0.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr bfloat, <vscale x 2 x ptr> %bases, i32 32
|
|
%vals = call <vscale x 2 x bfloat> @llvm.masked.gather.nxv2bf16(<vscale x 2 x ptr> %ptrs, i32 2, <vscale x 2 x i1> %mask, <vscale x 2 x bfloat> poison)
|
|
ret <vscale x 2 x bfloat> %vals
|
|
}
|
|
|
|
define <vscale x 2 x float> @masked_gather_nxv2f32_range(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2f32_range:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov w8, #128
|
|
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x8, z0.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr float, <vscale x 2 x ptr> %bases, i32 32
|
|
%vals = call <vscale x 2 x float> @llvm.masked.gather.nxv2f32(<vscale x 2 x ptr> %ptrs, i32 4, <vscale x 2 x i1> %mask, <vscale x 2 x float> poison)
|
|
ret <vscale x 2 x float> %vals
|
|
}
|
|
|
|
define <vscale x 2 x double> @masked_gather_nxv2f64_range(<vscale x 2 x ptr> %bases, <vscale x 2 x i1> %mask) {
|
|
; CHECK-LABEL: masked_gather_nxv2f64_range:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: mov w8, #256
|
|
; CHECK-NEXT: ld1d { z0.d }, p0/z, [x8, z0.d]
|
|
; CHECK-NEXT: ret
|
|
%ptrs = getelementptr double, <vscale x 2 x ptr> %bases, i32 32
|
|
%vals = call <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x ptr> %ptrs, i32 8, <vscale x 2 x i1> %mask, <vscale x 2 x double> poison)
|
|
ret <vscale x 2 x double> %vals
|
|
}
|
|
|
|
declare <vscale x 2 x i8> @llvm.masked.gather.nxv2i8(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x i8>)
|
|
declare <vscale x 2 x i16> @llvm.masked.gather.nxv2i16(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x i16>)
|
|
declare <vscale x 2 x i32> @llvm.masked.gather.nxv2i32(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x i32>)
|
|
declare <vscale x 2 x i64> @llvm.masked.gather.nxv2i64(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x i64>)
|
|
declare <vscale x 2 x half> @llvm.masked.gather.nxv2f16(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x half>)
|
|
declare <vscale x 2 x bfloat> @llvm.masked.gather.nxv2bf16(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x bfloat>)
|
|
declare <vscale x 2 x float> @llvm.masked.gather.nxv2f32(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x float>)
|
|
declare <vscale x 2 x double> @llvm.masked.gather.nxv2f64(<vscale x 2 x ptr>, i32, <vscale x 2 x i1>, <vscale x 2 x double>)
|
|
attributes #0 = { "target-features"="+sve,+bf16" }
|