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
211 lines
8.1 KiB
LLVM
211 lines
8.1 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -verify-machineinstrs -mtriple=x86_64-unknown-unknown -mattr=+avx512fp16,+avx512vl | FileCheck %s
|
|
|
|
declare half @llvm.minimum.f16(half, half)
|
|
declare half @llvm.maximum.f16(half, half)
|
|
declare <8 x half> @llvm.minimum.v8f16(<8 x half>, <8 x half>)
|
|
declare <8 x half> @llvm.maximum.v8f16(<8 x half>, <8 x half>)
|
|
declare <16 x half> @llvm.minimum.v16f16(<16 x half>, <16 x half>)
|
|
declare <16 x half> @llvm.maximum.v16f16(<16 x half>, <16 x half>)
|
|
declare <32 x half> @llvm.minimum.v32f16(<32 x half>, <32 x half>)
|
|
declare <32 x half> @llvm.maximum.v32f16(<32 x half>, <32 x half>)
|
|
|
|
define half @test_fminimum(half %x, half %y) {
|
|
; CHECK-LABEL: test_fminimum:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vminsh %xmm1, %xmm0, %xmm2
|
|
; CHECK-NEXT: vpbroadcastw {{.*#+}} xmm1 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
|
|
; CHECK-NEXT: vpternlogq {{.*#+}} xmm1 = (xmm1 & xmm0) | xmm2
|
|
; CHECK-NEXT: vcmpunordsh %xmm0, %xmm0, %k1
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%z = call half @llvm.minimum.f16(half %x, half %y)
|
|
ret half %z
|
|
}
|
|
|
|
define <8 x half> @test_fminimum_v8f16(<8 x half> %x, <8 x half> %y) {
|
|
; CHECK-LABEL: test_fminimum_v8f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vminph %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%r = call nnan nsz <8 x half> @llvm.minimum.v8f16(<8 x half> %x, <8 x half> %y)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define half @test_fminimum_nnan(half %x, half %y) {
|
|
; CHECK-LABEL: test_fminimum_nnan:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vfpclasssh $5, %xmm0, %k1 # k1 = isQuietNaN(xmm0) | isNegativeZero(xmm0)
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm2
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovsh %xmm1, %xmm0, %xmm0 {%k1}
|
|
; CHECK-NEXT: vminsh %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call nnan half @llvm.minimum.f16(half %x, half %y)
|
|
ret half %1
|
|
}
|
|
|
|
define half @test_fminimum_zero(half %x, half %y) {
|
|
; CHECK-LABEL: test_fminimum_zero:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vcmpunordsh %xmm1, %xmm1, %k1
|
|
; CHECK-NEXT: vminsh {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm0
|
|
; CHECK-NEXT: vmovsh %xmm1, %xmm0, %xmm0 {%k1}
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call half @llvm.minimum.f16(half -0.0, half %y)
|
|
ret half %1
|
|
}
|
|
|
|
define half @test_fminimum_nsz(half %x, half %y) {
|
|
; CHECK-LABEL: test_fminimum_nsz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vminsh %xmm1, %xmm0, %xmm1
|
|
; CHECK-NEXT: vcmpunordsh %xmm0, %xmm0, %k1
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call nsz half @llvm.minimum.f16(half %x, half %y)
|
|
ret half %1
|
|
}
|
|
|
|
define half @test_fminimum_combine_cmps(half %x, half %y) {
|
|
; CHECK-LABEL: test_fminimum_combine_cmps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vdivsh %xmm0, %xmm1, %xmm1
|
|
; CHECK-NEXT: vfpclasssh $5, %xmm0, %k1 # k1 = isQuietNaN(xmm0) | isNegativeZero(xmm0)
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm2
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovsh %xmm1, %xmm0, %xmm0 {%k1}
|
|
; CHECK-NEXT: vminsh %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = fdiv nnan half %y, %x
|
|
%2 = tail call half @llvm.minimum.f16(half %x, half %1)
|
|
ret half %2
|
|
}
|
|
|
|
define half @test_fmaximum(half %x, half %y) {
|
|
; CHECK-LABEL: test_fmaximum:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmaxsh %xmm1, %xmm0, %xmm2
|
|
; CHECK-NEXT: vpbroadcastw {{.*#+}} xmm1 = [NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN]
|
|
; CHECK-NEXT: vpternlogq {{.*#+}} xmm1 = xmm2 & (xmm1 | xmm0)
|
|
; CHECK-NEXT: vcmpunordsh %xmm0, %xmm0, %k1
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%r = call half @llvm.maximum.f16(half %x, half %y)
|
|
ret half %r
|
|
}
|
|
|
|
define <8 x half> @test_fmaximum_v8f16(<8 x half> %x, <8 x half> %y) {
|
|
; CHECK-LABEL: test_fmaximum_v8f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmaxph %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%r = call nnan nsz <8 x half> @llvm.maximum.v8f16(<8 x half> %x, <8 x half> %y)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define half @test_fmaximum_nnan(half %x, half %y) {
|
|
; CHECK-LABEL: test_fmaximum_nnan:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vaddsh %xmm1, %xmm0, %xmm2
|
|
; CHECK-NEXT: vsubsh %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: vfpclasssh $3, %xmm0, %k1 # k1 = isQuietNaN(xmm0) | isPositiveZero(xmm0)
|
|
; CHECK-NEXT: vmovaps %xmm2, %xmm1
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vmovsh %xmm2, %xmm0, %xmm0 {%k1}
|
|
; CHECK-NEXT: vmaxsh %xmm1, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = fadd nnan half %x, %y
|
|
%2 = fsub nnan half %x, %y
|
|
%3 = tail call half @llvm.maximum.f16(half %1, half %2)
|
|
ret half %3
|
|
}
|
|
|
|
define half @test_fmaximum_zero(half %x, half %y) {
|
|
; CHECK-LABEL: test_fmaximum_zero:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: vmaxsh %xmm0, %xmm1, %xmm0
|
|
; CHECK-NEXT: vcmpunordsh %xmm1, %xmm1, %k1
|
|
; CHECK-NEXT: vmovsh %xmm1, %xmm0, %xmm0 {%k1}
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call half @llvm.maximum.f16(half 0.0, half %y)
|
|
ret half %1
|
|
}
|
|
|
|
define half @test_fmaximum_nsz(half %x, half %y) {
|
|
; CHECK-LABEL: test_fmaximum_nsz:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmaxsh %xmm1, %xmm0, %xmm1
|
|
; CHECK-NEXT: vcmpunordsh %xmm0, %xmm0, %k1
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm1 {%k1}
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = tail call nsz half @llvm.maximum.f16(half %x, half %y)
|
|
ret half %1
|
|
}
|
|
|
|
define half @test_fmaximum_combine_cmps(half %x, half %y) {
|
|
; CHECK-LABEL: test_fmaximum_combine_cmps:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vdivsh %xmm0, %xmm1, %xmm1
|
|
; CHECK-NEXT: vfpclasssh $3, %xmm0, %k1 # k1 = isQuietNaN(xmm0) | isPositiveZero(xmm0)
|
|
; CHECK-NEXT: vmovaps %xmm1, %xmm2
|
|
; CHECK-NEXT: vmovsh %xmm0, %xmm0, %xmm2 {%k1}
|
|
; CHECK-NEXT: vmovsh %xmm1, %xmm0, %xmm0 {%k1}
|
|
; CHECK-NEXT: vmaxsh %xmm2, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%1 = fdiv nnan half %y, %x
|
|
%2 = tail call half @llvm.maximum.f16(half %x, half %1)
|
|
ret half %2
|
|
}
|
|
|
|
define <16 x half> @test_fminimum_v16f16(<16 x half> %x, <16 x half> %y) {
|
|
; CHECK-LABEL: test_fminimum_v16f16:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vminph %ymm1, %ymm0, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%r = call nnan nsz <16 x half> @llvm.minimum.v16f16(<16 x half> %x, <16 x half> %y)
|
|
ret <16 x half> %r
|
|
}
|
|
|
|
define <16 x half> @test_fmaximum_v16f16_nans(<16 x half> %x, <16 x half> %y) {
|
|
; CHECK-LABEL: test_fmaximum_v16f16_nans:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmaxph %ymm1, %ymm0, %ymm1
|
|
; CHECK-NEXT: vcmpunordph %ymm0, %ymm0, %k1
|
|
; CHECK-NEXT: vmovdqu16 %ymm0, %ymm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa %ymm1, %ymm0
|
|
; CHECK-NEXT: retq
|
|
%r = call nsz <16 x half> @llvm.maximum.v16f16(<16 x half> %x, <16 x half> %y)
|
|
ret <16 x half> %r
|
|
}
|
|
|
|
define <32 x half> @test_fminimum_v32f16_szero(<32 x half> %x, <32 x half> %y) {
|
|
; CHECK-LABEL: test_fminimum_v32f16_szero:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vminph %zmm1, %zmm0, %zmm1
|
|
; CHECK-NEXT: vpbroadcastw {{.*#+}} zmm2 = [-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0,-0.0E+0]
|
|
; CHECK-NEXT: vpternlogq {{.*#+}} zmm0 = (zmm0 & zmm2) | zmm1
|
|
; CHECK-NEXT: retq
|
|
%r = call nnan <32 x half> @llvm.minimum.v32f16(<32 x half> %x, <32 x half> %y)
|
|
ret <32 x half> %r
|
|
}
|
|
|
|
define <32 x half> @test_fmaximum_v32f16_nans_szero(<32 x half> %x, <32 x half> %y) {
|
|
; CHECK-LABEL: test_fmaximum_v32f16_nans_szero:
|
|
; CHECK: # %bb.0:
|
|
; CHECK-NEXT: vmaxph %zmm1, %zmm0, %zmm2
|
|
; CHECK-NEXT: vpbroadcastw {{.*#+}} zmm1 = [NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN,NaN]
|
|
; CHECK-NEXT: vpternlogq {{.*#+}} zmm1 = zmm2 & (zmm1 | zmm0)
|
|
; CHECK-NEXT: vcmpunordph %zmm0, %zmm0, %k1
|
|
; CHECK-NEXT: vmovdqu16 %zmm0, %zmm1 {%k1}
|
|
; CHECK-NEXT: vmovdqa64 %zmm1, %zmm0
|
|
; CHECK-NEXT: retq
|
|
%r = call <32 x half> @llvm.maximum.v32f16(<32 x half> %x, <32 x half> %y)
|
|
ret <32 x half> %r
|
|
}
|