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
98 lines
3.9 KiB
LLVM
98 lines
3.9 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp,+fp64 -verify-machineinstrs -o - %s | FileCheck %s
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp,+fp64 -verify-machineinstrs -early-live-intervals -o - %s | FileCheck %s
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @foo_v4i16(ptr nocapture readonly %pSrc, i32 %blockSize, <4 x i16> %a) {
|
|
; CHECK-LABEL: foo_v4i16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmovlb.s16 q0, q0
|
|
; CHECK-NEXT: vpt.s32 lt, q0, zr
|
|
; CHECK-NEXT: vldrht.s32 q0, [r0]
|
|
; CHECK-NEXT: vcvt.f32.s32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%active.lane.mask = icmp slt <4 x i16> %a, zeroinitializer
|
|
%wide.masked.load = call <4 x i16> @llvm.masked.load.v4i16.p0(ptr %pSrc, i32 2, <4 x i1> %active.lane.mask, <4 x i16> undef)
|
|
%0 = sitofp <4 x i16> %wide.masked.load to <4 x float>
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @foo_v8i8(ptr nocapture readonly %pSrc, i32 %blockSize, <8 x i8> %a) {
|
|
; CHECK-LABEL: foo_v8i8:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmovlb.s8 q0, q0
|
|
; CHECK-NEXT: vpt.s16 lt, q0, zr
|
|
; CHECK-NEXT: vldrbt.s16 q0, [r0]
|
|
; CHECK-NEXT: vcvt.f16.s16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%active.lane.mask = icmp slt <8 x i8> %a, zeroinitializer
|
|
%wide.masked.load = call <8 x i8> @llvm.masked.load.v8i8.p0(ptr %pSrc, i32 1, <8 x i1> %active.lane.mask, <8 x i8> undef)
|
|
%0 = sitofp <8 x i8> %wide.masked.load to <8 x half>
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @foo_v4i8(ptr nocapture readonly %pSrc, i32 %blockSize, <4 x i8> %a) {
|
|
; CHECK-LABEL: foo_v4i8:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmovlb.s8 q0, q0
|
|
; CHECK-NEXT: vmovlb.s16 q0, q0
|
|
; CHECK-NEXT: vpt.s32 lt, q0, zr
|
|
; CHECK-NEXT: vldrbt.s32 q0, [r0]
|
|
; CHECK-NEXT: vcvt.f32.s32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%active.lane.mask = icmp slt <4 x i8> %a, zeroinitializer
|
|
%wide.masked.load = call <4 x i8> @llvm.masked.load.v4i8.p0(ptr %pSrc, i32 1, <4 x i1> %active.lane.mask, <4 x i8> undef)
|
|
%0 = sitofp <4 x i8> %wide.masked.load to <4 x float>
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x double> @foo_v4i32(ptr nocapture readonly %pSrc, i32 %blockSize, <4 x i32> %a) {
|
|
; CHECK-LABEL: foo_v4i32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: .save {r4, r5, r7, lr}
|
|
; CHECK-NEXT: push {r4, r5, r7, lr}
|
|
; CHECK-NEXT: .vsave {d8, d9, d10, d11}
|
|
; CHECK-NEXT: vpush {d8, d9, d10, d11}
|
|
; CHECK-NEXT: vpt.s32 lt, q0, zr
|
|
; CHECK-NEXT: vldrwt.u32 q4, [r0]
|
|
; CHECK-NEXT: vmov r0, s19
|
|
; CHECK-NEXT: asrs r1, r0, #31
|
|
; CHECK-NEXT: bl __aeabi_l2d
|
|
; CHECK-NEXT: vmov r2, s18
|
|
; CHECK-NEXT: vmov d9, r0, r1
|
|
; CHECK-NEXT: vmov r4, r5, d8
|
|
; CHECK-NEXT: asrs r3, r2, #31
|
|
; CHECK-NEXT: mov r0, r2
|
|
; CHECK-NEXT: mov r1, r3
|
|
; CHECK-NEXT: bl __aeabi_l2d
|
|
; CHECK-NEXT: vmov d8, r0, r1
|
|
; CHECK-NEXT: asrs r1, r5, #31
|
|
; CHECK-NEXT: mov r0, r5
|
|
; CHECK-NEXT: bl __aeabi_l2d
|
|
; CHECK-NEXT: asrs r2, r4, #31
|
|
; CHECK-NEXT: vmov d11, r0, r1
|
|
; CHECK-NEXT: mov r0, r4
|
|
; CHECK-NEXT: mov r1, r2
|
|
; CHECK-NEXT: bl __aeabi_l2d
|
|
; CHECK-NEXT: vmov d10, r0, r1
|
|
; CHECK-NEXT: vmov q1, q4
|
|
; CHECK-NEXT: vmov q0, q5
|
|
; CHECK-NEXT: vpop {d8, d9, d10, d11}
|
|
; CHECK-NEXT: pop {r4, r5, r7, pc}
|
|
entry:
|
|
%active.lane.mask = icmp slt <4 x i32> %a, zeroinitializer
|
|
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %pSrc, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
|
|
%0 = sitofp <4 x i32> %wide.masked.load to <4 x double>
|
|
ret <4 x double> %0
|
|
}
|
|
|
|
declare <4 x i16> @llvm.masked.load.v4i16.p0(ptr, i32 immarg, <4 x i1>, <4 x i16>)
|
|
|
|
declare <8 x i8> @llvm.masked.load.v8i8.p0(ptr, i32 immarg, <8 x i1>, <8 x i8>)
|
|
|
|
declare <4 x i8> @llvm.masked.load.v4i8.p0(ptr, i32 immarg, <4 x i1>, <4 x i8>)
|
|
|
|
declare <4 x i32> @llvm.masked.load.v4i32.p0(ptr, i32 immarg, <4 x i1>, <4 x i32>)
|