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
537 lines
18 KiB
LLVM
537 lines
18 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve.fp -o - %s | FileCheck %s
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vaddq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vaddq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vadd.f16 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vadd.v8f16(<8 x half> %a, <8 x half> %b)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vaddq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vaddq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vadd.f32 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vadd.v4f32(<4 x float> %a, <4 x float> %b)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vsubq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vsubq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vsub.f16 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vsub.v8f16(<8 x half> %a, <8 x half> %b)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vsubq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vsubq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vsub.f32 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vsub.v4f32(<4 x float> %a, <4 x float> %b)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vmulq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vmulq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmul.f16 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vmul.v8f16(<8 x half> %a, <8 x half> %b)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vmulq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vmulq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmul.f32 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vmul.v4f32(<4 x float> %a, <4 x float> %b)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
|
|
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vaddq_f16_splat(<8 x half> %a, half %b) #0 {
|
|
; CHECK-LABEL: test_vaddq_f16_splat:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov.f16 r0, s4
|
|
; CHECK-NEXT: vadd.f16 q0, q0, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <8 x half> poison, half %b, i32 0
|
|
%s = shufflevector <8 x half> %i, <8 x half> poison, <8 x i32> zeroinitializer
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vadd.v8f16(<8 x half> %a, <8 x half> %s)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vaddq_f32_splat(<4 x float> %a, float %b) #0 {
|
|
; CHECK-LABEL: test_vaddq_f32_splat:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vadd.f32 q0, q0, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <4 x float> poison, float %b, i32 0
|
|
%s = shufflevector <4 x float> %i, <4 x float> poison, <4 x i32> zeroinitializer
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vadd.v4f32(<4 x float> %a, <4 x float> %s)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vsubq_f16_splat(<8 x half> %a, half %b) #0 {
|
|
; CHECK-LABEL: test_vsubq_f16_splat:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov.f16 r0, s4
|
|
; CHECK-NEXT: vsub.f16 q0, q0, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <8 x half> poison, half %b, i32 0
|
|
%s = shufflevector <8 x half> %i, <8 x half> poison, <8 x i32> zeroinitializer
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vsub.v8f16(<8 x half> %a, <8 x half> %s)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vsubq_f32_splat(<4 x float> %a, float %b) #0 {
|
|
; CHECK-LABEL: test_vsubq_f32_splat:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vsub.f32 q0, q0, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <4 x float> poison, float %b, i32 0
|
|
%s = shufflevector <4 x float> %i, <4 x float> poison, <4 x i32> zeroinitializer
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vsub.v4f32(<4 x float> %a, <4 x float> %s)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vmulq_f16_splat(<8 x half> %a, half %b) #0 {
|
|
; CHECK-LABEL: test_vmulq_f16_splat:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov.f16 r0, s4
|
|
; CHECK-NEXT: vmul.f16 q0, q0, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <8 x half> poison, half %b, i32 0
|
|
%s = shufflevector <8 x half> %i, <8 x half> poison, <8 x i32> zeroinitializer
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vmul.v8f16(<8 x half> %a, <8 x half> %s)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vmulq_f32_splat(<4 x float> %a, float %b) #0 {
|
|
; CHECK-LABEL: test_vmulq_f32_splat:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov r0, s4
|
|
; CHECK-NEXT: vmul.f32 q0, q0, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <4 x float> poison, float %b, i32 0
|
|
%s = shufflevector <4 x float> %i, <4 x float> poison, <4 x i32> zeroinitializer
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vmul.v4f32(<4 x float> %a, <4 x float> %s)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @fma_v4f32(<4 x float> %dst, <4 x float> %s1, <4 x float> %s2) #0 {
|
|
; CHECK-LABEL: fma_v4f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vfma.f32 q0, q1, q2
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.fma.v4f32(<4 x float> %s1, <4 x float> %s2, <4 x float> %dst)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @fma_v8f16(<8 x half> %dst, <8 x half> %s1, <8 x half> %s2) #0 {
|
|
; CHECK-LABEL: fma_v8f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vfma.f16 q0, q1, q2
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.fma.v8f16(<8 x half> %s1, <8 x half> %s2, <8 x half> %dst)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @fma_n_v8f16(<4 x float> %s1, <4 x float> %s2, float %s3) #0 {
|
|
; CHECK-LABEL: fma_n_v8f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov r0, s8
|
|
; CHECK-NEXT: vfma.f32 q0, q1, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <4 x float> poison, float %s3, i32 0
|
|
%sp = shufflevector <4 x float> %i, <4 x float> poison, <4 x i32> zeroinitializer
|
|
%0 = tail call <4 x float> @llvm.arm.mve.fma.v4f32(<4 x float> %s2, <4 x float> %sp, <4 x float> %s1)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @fma_n_v4f32(<8 x half> %s1, <8 x half> %s2, half %s3) #0 {
|
|
; CHECK-LABEL: fma_n_v4f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov.f16 r0, s8
|
|
; CHECK-NEXT: vfma.f16 q0, q1, r0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%i = insertelement <8 x half> poison, half %s3, i32 0
|
|
%sp = shufflevector <8 x half> %i, <8 x half> poison, <8 x i32> zeroinitializer
|
|
%0 = tail call <8 x half> @llvm.arm.mve.fma.v8f16(<8 x half> %s2, <8 x half> %sp, <8 x half> %s1)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @fms_v4f32(<4 x float> %dst, <4 x float> %s1, <4 x float> %s2) #0 {
|
|
; CHECK-LABEL: fms_v4f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vfms.f32 q0, q1, q2
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%c = fneg <4 x float> %s1
|
|
%0 = tail call <4 x float> @llvm.arm.mve.fma.v4f32(<4 x float> %c, <4 x float> %s2, <4 x float> %dst)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @fms_v8f16(<8 x half> %dst, <8 x half> %s1, <8 x half> %s2) #0 {
|
|
; CHECK-LABEL: fms_v8f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vfms.f16 q0, q1, q2
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%c = fneg <8 x half> %s1
|
|
%0 = tail call <8 x half> @llvm.arm.mve.fma.v8f16(<8 x half> %c, <8 x half> %s2, <8 x half> %dst)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @fms_n_v8f16(<4 x float> %s1, <4 x float> %s2, float %s3) #0 {
|
|
; CHECK-LABEL: fms_n_v8f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov r0, s8
|
|
; CHECK-NEXT: vdup.32 q2, r0
|
|
; CHECK-NEXT: vfms.f32 q0, q1, q2
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%c = fneg <4 x float> %s2
|
|
%i = insertelement <4 x float> poison, float %s3, i32 0
|
|
%sp = shufflevector <4 x float> %i, <4 x float> poison, <4 x i32> zeroinitializer
|
|
%0 = tail call <4 x float> @llvm.arm.mve.fma.v4f32(<4 x float> %c, <4 x float> %sp, <4 x float> %s1)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @fms_n_v4f32(<8 x half> %s1, <8 x half> %s2, half %s3) #0 {
|
|
; CHECK-LABEL: fms_n_v4f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmov.f16 r0, s8
|
|
; CHECK-NEXT: vdup.16 q2, r0
|
|
; CHECK-NEXT: vfms.f16 q0, q1, q2
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%c = fneg <8 x half> %s2
|
|
%i = insertelement <8 x half> poison, half %s3, i32 0
|
|
%sp = shufflevector <8 x half> %i, <8 x half> poison, <8 x i32> zeroinitializer
|
|
%0 = tail call <8 x half> @llvm.arm.mve.fma.v8f16(<8 x half> %c, <8 x half> %sp, <8 x half> %s1)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vminnmq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vminnmq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnm.f16 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%2 = tail call <8 x half> @llvm.arm.mve.vmaxnm.v8f16(<8 x half> %a, <8 x half> %b)
|
|
ret <8 x half> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vminnmq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vminnmq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnm.f32 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%2 = tail call <4 x float> @llvm.arm.mve.vmaxnm.v4f32(<4 x float> %a, <4 x float> %b)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vmaxnmq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vmaxnmq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnm.f16 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%2 = tail call <8 x half> @llvm.arm.mve.vmaxnm.v8f16(<8 x half> %a, <8 x half> %b)
|
|
ret <8 x half> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vmaxnmq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vmaxnmq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnm.f32 q0, q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%2 = tail call <4 x float> @llvm.arm.mve.vmaxnm.v4f32(<4 x float> %a, <4 x float> %b)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vminnmaq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vminnmaq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnma.f16 q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%1 = tail call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%2 = tail call <8 x half> @llvm.arm.mve.vmaxnm.v8f16(<8 x half> %0, <8 x half> %1)
|
|
ret <8 x half> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vminnmaq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vminnmaq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnma.f32 q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%1 = tail call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%2 = tail call <4 x float> @llvm.arm.mve.vmaxnm.v4f32(<4 x float> %0, <4 x float> %1)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vmaxnmaq_f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_vmaxnmaq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnma.f16 q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%1 = tail call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%2 = tail call <8 x half> @llvm.arm.mve.vmaxnm.v8f16(<8 x half> %0, <8 x half> %1)
|
|
ret <8 x half> %2
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vmaxnmaq_f32(<4 x float> %a, <4 x float> %b) #0 {
|
|
; CHECK-LABEL: test_vmaxnmaq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vmaxnma.f32 q0, q1
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%1 = tail call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%2 = tail call <4 x float> @llvm.arm.mve.vmaxnm.v4f32(<4 x float> %0, <4 x float> %1)
|
|
ret <4 x float> %2
|
|
}
|
|
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vrndnq_f16(<8 x half> %a) #0 {
|
|
; CHECK-LABEL: test_vrndnq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintn.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vrintn.v8f16(<8 x half> %a)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vrndnq_f32(<4 x float> %a) #0 {
|
|
; CHECK-LABEL: test_vrndnq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintn.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vrintn.v4f32(<4 x float> %a)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vrndxq_f16(<8 x half> %a) #0 {
|
|
; CHECK-LABEL: test_vrndxq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintx.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vrintx.v8f16(<8 x half> %a)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vrndxq_f32(<4 x float> %a) #0 {
|
|
; CHECK-LABEL: test_vrndxq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintx.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vrintx.v4f32(<4 x float> %a)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vrndaq_f16(<8 x half> %a) #0 {
|
|
; CHECK-LABEL: test_vrndaq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrinta.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vrinta.v8f16(<8 x half> %a)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vrndaq_f32(<4 x float> %a) #0 {
|
|
; CHECK-LABEL: test_vrndaq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrinta.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vrinta.v4f32(<4 x float> %a)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vrndzq_f16(<8 x half> %a) #0 {
|
|
; CHECK-LABEL: test_vrndzq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintz.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vrintz.v8f16(<8 x half> %a)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vrndzq_f32(<4 x float> %a) #0 {
|
|
; CHECK-LABEL: test_vrndzq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintz.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vrintz.v4f32(<4 x float> %a)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vrndmq_f16(<8 x half> %a) #0 {
|
|
; CHECK-LABEL: test_vrndmq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintm.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vrintm.v8f16(<8 x half> %a)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vrndmq_f32(<4 x float> %a) #0 {
|
|
; CHECK-LABEL: test_vrndmq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintm.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vrintm.v4f32(<4 x float> %a)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vrndpq_f16(<8 x half> %a) #0 {
|
|
; CHECK-LABEL: test_vrndpq_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintp.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vrintp.v8f16(<8 x half> %a)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vrndpq_f32(<4 x float> %a) #0 {
|
|
; CHECK-LABEL: test_vrndpq_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vrintp.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vrintp.v4f32(<4 x float> %a)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
|
|
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vcvtq_f16_s16(<8 x i16> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_f16_s16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.f16.s16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vcvt.fp.int.v8f16.v8i16(<8 x i16> %a, i32 0)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x half> @test_vcvtq_f16_u16(<8 x i16> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_f16_u16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.f16.u16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x half> @llvm.arm.mve.vcvt.fp.int.v8f16.v8i16(<8 x i16> %a, i32 1)
|
|
ret <8 x half> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vcvtq_f32_s32(<4 x i32> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_f32_s32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.f32.s32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vcvt.fp.int.v4f32.v4i32(<4 x i32> %a, i32 0)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x float> @test_vcvtq_f32_u32(<4 x i32> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_f32_u32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.f32.u32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x float> @llvm.arm.mve.vcvt.fp.int.v4f32.v4i32(<4 x i32> %a, i32 1)
|
|
ret <4 x float> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x i16> @test_vcvtq_s16_f16(<8 x half> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_s16_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.s16.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.arm.mve.vcvt.int.fp.v8i16.v8f16(<8 x half> %a, i32 0)
|
|
ret <8 x i16> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x i32> @test_vcvtq_s32_f32(<4 x float> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_s32_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.s32.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x i32> @llvm.arm.mve.vcvt.int.fp.v4i32.v4f32(<4 x float> %a, i32 0)
|
|
ret <4 x i32> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <8 x i16> @test_vcvtq_u16_f16(<8 x half> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_u16_f16:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.u16.f16 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <8 x i16> @llvm.arm.mve.vcvt.int.fp.v8i16.v8f16(<8 x half> %a, i32 1)
|
|
ret <8 x i16> %0
|
|
}
|
|
|
|
define arm_aapcs_vfpcc <4 x i32> @test_vcvtq_u32_f32(<4 x float> noundef %a) #0 {
|
|
; CHECK-LABEL: test_vcvtq_u32_f32:
|
|
; CHECK: @ %bb.0: @ %entry
|
|
; CHECK-NEXT: vcvt.u32.f32 q0, q0
|
|
; CHECK-NEXT: bx lr
|
|
entry:
|
|
%0 = tail call <4 x i32> @llvm.arm.mve.vcvt.int.fp.v4i32.v4f32(<4 x float> %a, i32 1)
|
|
ret <4 x i32> %0
|
|
}
|
|
|
|
attributes #0 = { strictfp }
|