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
140 lines
5.1 KiB
LLVM
140 lines
5.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve,-vfp2 -o - %s | FileCheck %s --check-prefix=CHECK-NOFP
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-eabi -mattr=+mve.fp -o - %s | FileCheck --check-prefix=CHECK-FP %s
|
|
|
|
; This file tests tests that we expand floating point operations correctly,
|
|
; even if we do not have an fpu.
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @vector_add_f16(<8 x half> %lhs, <8 x half> %rhs) {
|
|
; CHECK-NOFP-LABEL: vector_add_f16:
|
|
; CHECK-NOFP: @ %bb.0: @ %entry
|
|
; CHECK-NOFP-NEXT: .save {r4, lr}
|
|
; CHECK-NOFP-NEXT: push {r4, lr}
|
|
; CHECK-NOFP-NEXT: .vsave {d8, d9, d10, d11, d12, d13}
|
|
; CHECK-NOFP-NEXT: vpush {d8, d9, d10, d11, d12, d13}
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q1[0]
|
|
; CHECK-NOFP-NEXT: vmov q5, q1
|
|
; CHECK-NOFP-NEXT: vmov q4, q0
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[0]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[0], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[1]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[1]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[1], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[2]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[2]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[2], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[3]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[3]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[3], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[4]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[4]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[4], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[5]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[5]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[5], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[6]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[6]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[6], r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q5[7]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r4, r0
|
|
; CHECK-NOFP-NEXT: vmov.u16 r0, q4[7]
|
|
; CHECK-NOFP-NEXT: bl __aeabi_h2f
|
|
; CHECK-NOFP-NEXT: mov r1, r4
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: bl __aeabi_f2h
|
|
; CHECK-NOFP-NEXT: vmov.16 q6[7], r0
|
|
; CHECK-NOFP-NEXT: vmov q0, q6
|
|
; CHECK-NOFP-NEXT: vpop {d8, d9, d10, d11, d12, d13}
|
|
; CHECK-NOFP-NEXT: pop {r4, pc}
|
|
;
|
|
; CHECK-FP-LABEL: vector_add_f16:
|
|
; CHECK-FP: @ %bb.0: @ %entry
|
|
; CHECK-FP-NEXT: vadd.f16 q0, q0, q1
|
|
; CHECK-FP-NEXT: bx lr
|
|
entry:
|
|
%sum = fadd <8 x half> %lhs, %rhs
|
|
ret <8 x half> %sum
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @vector_add_f32(<4 x float> %lhs, <4 x float> %rhs) {
|
|
; CHECK-NOFP-LABEL: vector_add_f32:
|
|
; CHECK-NOFP: @ %bb.0: @ %entry
|
|
; CHECK-NOFP-NEXT: .save {r4, r5, r7, lr}
|
|
; CHECK-NOFP-NEXT: push {r4, r5, r7, lr}
|
|
; CHECK-NOFP-NEXT: .vsave {d8, d9, d10, d11}
|
|
; CHECK-NOFP-NEXT: vpush {d8, d9, d10, d11}
|
|
; CHECK-NOFP-NEXT: vmov q4, q1
|
|
; CHECK-NOFP-NEXT: vmov q5, q0
|
|
; CHECK-NOFP-NEXT: vmov r4, r0, d11
|
|
; CHECK-NOFP-NEXT: vmov r5, r1, d9
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: vmov s19, r0
|
|
; CHECK-NOFP-NEXT: mov r0, r4
|
|
; CHECK-NOFP-NEXT: mov r1, r5
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: vmov s18, r0
|
|
; CHECK-NOFP-NEXT: vmov r4, r0, d10
|
|
; CHECK-NOFP-NEXT: vmov r5, r1, d8
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: vmov s17, r0
|
|
; CHECK-NOFP-NEXT: mov r0, r4
|
|
; CHECK-NOFP-NEXT: mov r1, r5
|
|
; CHECK-NOFP-NEXT: bl __aeabi_fadd
|
|
; CHECK-NOFP-NEXT: vmov s16, r0
|
|
; CHECK-NOFP-NEXT: vmov q0, q4
|
|
; CHECK-NOFP-NEXT: vpop {d8, d9, d10, d11}
|
|
; CHECK-NOFP-NEXT: pop {r4, r5, r7, pc}
|
|
;
|
|
; CHECK-FP-LABEL: vector_add_f32:
|
|
; CHECK-FP: @ %bb.0: @ %entry
|
|
; CHECK-FP-NEXT: vadd.f32 q0, q0, q1
|
|
; CHECK-FP-NEXT: bx lr
|
|
entry:
|
|
%sum = fadd <4 x float> %lhs, %rhs
|
|
ret <4 x float> %sum
|
|
}
|
|
|