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
605 lines
23 KiB
LLVM
605 lines
23 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
|
|
; RUN: llc -mattr=+faminmax -verify-machineinstrs %s -o - | FileCheck %s
|
|
; RUN: llc -verify-machineinstrs %s -o - | FileCheck %s --check-prefix=CHECK-NO-FAMINMAX
|
|
|
|
target triple = "aarch64-unknown-linux-gnu"
|
|
|
|
; Replace min(abs(a), abs(b)) with famin(a, b)
|
|
; Replace max(abs(a), abs(b)) with famax(a, b)
|
|
|
|
; When the fastmath flag 'nnan' (no nan) is enabled, we may also replace:
|
|
; minnm(abs(a), abs(b)) with famin(a, b)
|
|
; maxnm(abs(a), abs(b)) with famax(a, b)
|
|
|
|
define <4 x half> @test_max_v4f16(<4 x half> %a, <4 x half> %b) #0 {
|
|
; CHECK-LABEL: test_max_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_max_v4f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmax v0.4h, v0.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x half> @llvm.fabs.v4f16(<4 x half> %a)
|
|
%ab = call <4 x half> @llvm.fabs.v4f16(<4 x half> %b)
|
|
%r = call <4 x half> @llvm.maximum.v4f16(<4 x half> %aa, <4 x half> %ab)
|
|
ret <4 x half> %r
|
|
}
|
|
|
|
define <4 x half> @test_maxnm_nnan_v4f16(<4 x half> %a, <4 x half> %b) #0 {
|
|
; CHECK-LABEL: test_maxnm_nnan_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_nnan_v4f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.4h, v0.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x half> @llvm.fabs.v4f16(<4 x half> %a)
|
|
%ab = call <4 x half> @llvm.fabs.v4f16(<4 x half> %b)
|
|
%r = call nnan <4 x half> @llvm.maxnum.v4f16(<4 x half> %aa, <4 x half> %ab)
|
|
ret <4 x half> %r
|
|
}
|
|
|
|
define <4 x half> @test_maxnm_noflag_v4f16(<4 x half> %a, <4 x half> %b) #0 {
|
|
; CHECK-LABEL: test_maxnm_noflag_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NEXT: fmaxnm v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_noflag_v4f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.4h, v0.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x half> @llvm.fabs.v4f16(<4 x half> %a)
|
|
%ab = call <4 x half> @llvm.fabs.v4f16(<4 x half> %b)
|
|
%r = call <4 x half> @llvm.maxnum.v4f16(<4 x half> %aa, <4 x half> %ab)
|
|
ret <4 x half> %r
|
|
}
|
|
|
|
define <4 x half> @test_min_v4f16(<4 x half> %a, <4 x half> %b) #0 {
|
|
; CHECK-LABEL: test_min_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_min_v4f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmin v0.4h, v0.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x half> @llvm.fabs.v4f16(<4 x half> %a)
|
|
%ab = call <4 x half> @llvm.fabs.v4f16(<4 x half> %b)
|
|
%r = call <4 x half> @llvm.minimum.v4f16(<4 x half> %aa, <4 x half> %ab)
|
|
ret <4 x half> %r
|
|
}
|
|
|
|
define <4 x half> @test_minnm_nnan_v4f16(<4 x half> %a, <4 x half> %b) #0 {
|
|
; CHECK-LABEL: test_minnm_nnan_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_nnan_v4f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.4h, v0.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x half> @llvm.fabs.v4f16(<4 x half> %a)
|
|
%ab = call <4 x half> @llvm.fabs.v4f16(<4 x half> %b)
|
|
%r = call nnan <4 x half> @llvm.minnum.v4f16(<4 x half> %aa, <4 x half> %ab)
|
|
ret <4 x half> %r
|
|
}
|
|
|
|
define <4 x half> @test_minnm_noflag_v4f16(<4 x half> %a, <4 x half> %b) #0 {
|
|
; CHECK-LABEL: test_minnm_noflag_v4f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NEXT: fminnm v0.4h, v0.4h, v1.4h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_noflag_v4f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4h, v0.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.4h, v0.4h, v1.4h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x half> @llvm.fabs.v4f16(<4 x half> %a)
|
|
%ab = call <4 x half> @llvm.fabs.v4f16(<4 x half> %b)
|
|
%r = call <4 x half> @llvm.minnum.v4f16(<4 x half> %aa, <4 x half> %ab)
|
|
ret <4 x half> %r
|
|
}
|
|
|
|
define <8 x half> @test_max_v8f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_max_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_max_v8f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmax v0.8h, v0.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%ab = call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%r = call <8 x half> @llvm.maximum.v8f16(<8 x half> %aa, <8 x half> %ab)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define <8 x half> @test_maxnm_nnan_v8f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_maxnm_nnan_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_nnan_v8f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.8h, v0.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%ab = call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%r = call nnan <8 x half> @llvm.maxnum.v8f16(<8 x half> %aa, <8 x half> %ab)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define <8 x half> @test_maxnm_noflag_v8f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_maxnm_noflag_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NEXT: fmaxnm v0.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_noflag_v8f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.8h, v0.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%ab = call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%r = call <8 x half> @llvm.maxnum.v8f16(<8 x half> %aa, <8 x half> %ab)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define <8 x half> @test_min_v8f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_min_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_min_v8f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fmin v0.8h, v0.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%ab = call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%r = call <8 x half> @llvm.minimum.v8f16(<8 x half> %aa, <8 x half> %ab)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define <8 x half> @test_minnm_nnan_v8f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_minnm_nnan_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_nnan_v8f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.8h, v0.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%ab = call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%r = call nnan <8 x half> @llvm.minnum.v8f16(<8 x half> %aa, <8 x half> %ab)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define <8 x half> @test_minnm_noflag_v8f16(<8 x half> %a, <8 x half> %b) #0 {
|
|
; CHECK-LABEL: test_minnm_noflag_v8f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NEXT: fminnm v0.8h, v0.8h, v1.8h
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_noflag_v8f16:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.8h, v0.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.8h, v0.8h, v1.8h
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <8 x half> @llvm.fabs.v8f16(<8 x half> %a)
|
|
%ab = call <8 x half> @llvm.fabs.v8f16(<8 x half> %b)
|
|
%r = call <8 x half> @llvm.minnum.v8f16(<8 x half> %aa, <8 x half> %ab)
|
|
ret <8 x half> %r
|
|
}
|
|
|
|
define <2 x float> @test_max_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: test_max_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.2s, v0.2s, v1.2s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_max_v2f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmax v0.2s, v0.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x float> @llvm.fabs.v2f32(<2 x float> %a)
|
|
%ab = call <2 x float> @llvm.fabs.v2f32(<2 x float> %b)
|
|
%r = call <2 x float> @llvm.maximum.v2f32(<2 x float> %aa, <2 x float> %ab)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define <2 x float> @test_maxnm_nnan_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: test_maxnm_nnan_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.2s, v0.2s, v1.2s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_nnan_v2f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.2s, v0.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x float> @llvm.fabs.v2f32(<2 x float> %a)
|
|
%ab = call <2 x float> @llvm.fabs.v2f32(<2 x float> %b)
|
|
%r = call nnan <2 x float> @llvm.maxnum.v2f32(<2 x float> %aa, <2 x float> %ab)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define <2 x float> @test_maxnm_noflag_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: test_maxnm_noflag_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NEXT: fmaxnm v0.2s, v0.2s, v1.2s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_noflag_v2f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.2s, v0.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x float> @llvm.fabs.v2f32(<2 x float> %a)
|
|
%ab = call <2 x float> @llvm.fabs.v2f32(<2 x float> %b)
|
|
%r = call <2 x float> @llvm.maxnum.v2f32(<2 x float> %aa, <2 x float> %ab)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define <2 x float> @test_min_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: test_min_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.2s, v0.2s, v1.2s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_min_v2f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmin v0.2s, v0.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x float> @llvm.fabs.v2f32(<2 x float> %a)
|
|
%ab = call <2 x float> @llvm.fabs.v2f32(<2 x float> %b)
|
|
%r = call <2 x float> @llvm.minimum.v2f32(<2 x float> %aa, <2 x float> %ab)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define <2 x float> @test_minnm_nnan_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: test_minnm_nnan_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.2s, v0.2s, v1.2s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_nnan_v2f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.2s, v0.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x float> @llvm.fabs.v2f32(<2 x float> %a)
|
|
%ab = call <2 x float> @llvm.fabs.v2f32(<2 x float> %b)
|
|
%r = call nnan <2 x float> @llvm.minnum.v2f32(<2 x float> %aa, <2 x float> %ab)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define <2 x float> @test_minnm_noflag_v2f32(<2 x float> %a, <2 x float> %b) {
|
|
; CHECK-LABEL: test_minnm_noflag_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NEXT: fminnm v0.2s, v0.2s, v1.2s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_noflag_v2f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2s, v0.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.2s, v0.2s, v1.2s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x float> @llvm.fabs.v2f32(<2 x float> %a)
|
|
%ab = call <2 x float> @llvm.fabs.v2f32(<2 x float> %b)
|
|
%r = call <2 x float> @llvm.minnum.v2f32(<2 x float> %aa, <2 x float> %ab)
|
|
ret <2 x float> %r
|
|
}
|
|
|
|
define <4 x float> @test_max_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: test_max_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_max_v4f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmax v0.4s, v0.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%ab = call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%r = call <4 x float> @llvm.maximum.v4f32(<4 x float> %aa, <4 x float> %ab)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define <4 x float> @test_maxnm_nnan_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: test_maxnm_nnan_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_nnan_v4f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.4s, v0.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%ab = call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%r = call nnan <4 x float> @llvm.maxnum.v4f32(<4 x float> %aa, <4 x float> %ab)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define <4 x float> @test_maxnm_noflag_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: test_maxnm_noflag_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NEXT: fmaxnm v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_noflag_v4f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.4s, v0.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%ab = call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%r = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %aa, <4 x float> %ab)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define <4 x float> @test_min_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: test_min_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_min_v4f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fmin v0.4s, v0.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%ab = call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%r = call <4 x float> @llvm.minimum.v4f32(<4 x float> %aa, <4 x float> %ab)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define <4 x float> @test_minnm_nnan_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: test_minnm_nnan_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_nnan_v4f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.4s, v0.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%ab = call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%r = call nnan <4 x float> @llvm.minnum.v4f32(<4 x float> %aa, <4 x float> %ab)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define <4 x float> @test_minnm_noflag_v4f32(<4 x float> %a, <4 x float> %b) {
|
|
; CHECK-LABEL: test_minnm_noflag_v4f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NEXT: fminnm v0.4s, v0.4s, v1.4s
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_noflag_v4f32:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.4s, v0.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.4s, v0.4s, v1.4s
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <4 x float> @llvm.fabs.v4f32(<4 x float> %a)
|
|
%ab = call <4 x float> @llvm.fabs.v4f32(<4 x float> %b)
|
|
%r = call <4 x float> @llvm.minnum.v4f32(<4 x float> %aa, <4 x float> %ab)
|
|
ret <4 x float> %r
|
|
}
|
|
|
|
define <2 x double> @test_max_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: test_max_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_max_v2f64:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fmax v0.2d, v0.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x double> @llvm.fabs.v2f64(<2 x double> %a)
|
|
%ab = call <2 x double> @llvm.fabs.v2f64(<2 x double> %b)
|
|
%r = call <2 x double> @llvm.maximum.v2f64(<2 x double> %aa, <2 x double> %ab)
|
|
ret <2 x double> %r
|
|
}
|
|
|
|
define <2 x double> @test_maxnm_nnan_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: test_maxnm_nnan_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famax v0.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_nnan_v2f64:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.2d, v0.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x double> @llvm.fabs.v2f64(<2 x double> %a)
|
|
%ab = call <2 x double> @llvm.fabs.v2f64(<2 x double> %b)
|
|
%r = call nnan <2 x double> @llvm.maxnum.v2f64(<2 x double> %aa, <2 x double> %ab)
|
|
ret <2 x double> %r
|
|
}
|
|
|
|
define <2 x double> @test_maxnm_noflag_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: test_maxnm_noflag_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NEXT: fmaxnm v0.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_maxnm_noflag_v2f64:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fmaxnm v0.2d, v0.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x double> @llvm.fabs.v2f64(<2 x double> %a)
|
|
%ab = call <2 x double> @llvm.fabs.v2f64(<2 x double> %b)
|
|
%r = call <2 x double> @llvm.maxnum.v2f64(<2 x double> %aa, <2 x double> %ab)
|
|
ret <2 x double> %r
|
|
}
|
|
|
|
define <2 x double> @test_min_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: test_min_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_min_v2f64:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fmin v0.2d, v0.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x double> @llvm.fabs.v2f64(<2 x double> %a)
|
|
%ab = call <2 x double> @llvm.fabs.v2f64(<2 x double> %b)
|
|
%r = call <2 x double> @llvm.minimum.v2f64(<2 x double> %aa, <2 x double> %ab)
|
|
ret <2 x double> %r
|
|
}
|
|
|
|
define <2 x double> @test_minnm_nnan_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: test_minnm_nnan_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: famin v0.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_minnm_nnan_v2f64:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.2d, v0.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x double> @llvm.fabs.v2f64(<2 x double> %a)
|
|
%ab = call <2 x double> @llvm.fabs.v2f64(<2 x double> %b)
|
|
%r = call nnan <2 x double> @llvm.minnum.v2f64(<2 x double> %aa, <2 x double> %ab)
|
|
ret <2 x double> %r
|
|
}
|
|
|
|
define <2 x double> @test_min_noflag_v2f64(<2 x double> %a, <2 x double> %b) {
|
|
; CHECK-LABEL: test_min_noflag_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NEXT: fminnm v0.2d, v0.2d, v1.2d
|
|
; CHECK-NEXT: ret
|
|
;
|
|
; CHECK-NO-FAMINMAX-LABEL: test_min_noflag_v2f64:
|
|
; CHECK-NO-FAMINMAX: // %bb.0:
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v0.2d, v0.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fabs v1.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: fminnm v0.2d, v0.2d, v1.2d
|
|
; CHECK-NO-FAMINMAX-NEXT: ret
|
|
%aa = call <2 x double> @llvm.fabs.v2f64(<2 x double> %a)
|
|
%ab = call <2 x double> @llvm.fabs.v2f64(<2 x double> %b)
|
|
%r = call <2 x double> @llvm.minnum.v2f64(<2 x double> %aa, <2 x double> %ab)
|
|
ret <2 x double> %r
|
|
}
|
|
|
|
declare <8 x half> @llvm.fabs.v8f16(<8 x half>)
|
|
declare <4 x half> @llvm.fabs.v4f16(<4 x half>)
|
|
declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
|
|
declare <2 x float> @llvm.fabs.v2f32(<2 x float>)
|
|
declare <2 x double> @llvm.fabs.v2f64(<2 x double>)
|
|
|
|
declare <8 x half> @llvm.minimum.v8f16(<8 x half>, <8 x half>)
|
|
declare <4 x half> @llvm.minimum.v4f16(<4 x half>, <4 x half>)
|
|
declare <4 x float> @llvm.minimum.v4f32(<4 x float>, <4 x float>)
|
|
declare <2 x float> @llvm.minimum.v2f32(<2 x float>, <2 x float>)
|
|
declare <2 x double> @llvm.minimum.v2f64(<2 x double>, <2 x double>)
|
|
|
|
declare <4 x half> @llvm.minnum.v4f16(<4 x half>, <4 x half>)
|
|
declare <8 x half> @llvm.minnum.v8f16(<8 x half>, <8 x half>)
|
|
declare <2 x float> @llvm.minnum.v2f32(<2 x float>, <2 x float>)
|
|
declare <4 x float> @llvm.minnum.v4f32(<4 x float>, <4 x float>)
|
|
declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
|
|
|
|
declare <8 x half> @llvm.maximum.v8f16(<8 x half>, <8 x half>)
|
|
declare <4 x half> @llvm.maximum.v4f16(<4 x half>, <4 x half>)
|
|
declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
|
|
declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>)
|
|
declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
|
|
|
|
declare <4 x half> @llvm.maxnum.v4f16(<4 x half>, <4 x half>)
|
|
declare <8 x half> @llvm.maxnum.v8f16(<8 x half>, <8 x half>)
|
|
declare <2 x float> @llvm.maxnum.v2f32(<2 x float>, <2 x float>)
|
|
declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
|
|
declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>)
|
|
|
|
attributes #0 = { nounwind "target-features"="+fullfp16" }
|