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
653 lines
49 KiB
LLVM
653 lines
49 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=aarch64 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-NOF16
|
|
; RUN: opt -passes="print<cost-model>" 2>&1 -disable-output -cost-kind=all -mtriple=aarch64 -mattr=+fullfp16 < %s | FileCheck %s --check-prefixes=CHECK,CHECK-F16
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
define void @umin() {
|
|
; CHECK-LABEL: 'umin'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.umin.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.umin.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4i64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%i8 = call i8 @llvm.umin.i8(i8 undef, i8 undef)
|
|
%i16 = call i16 @llvm.umin.i16(i16 undef, i16 undef)
|
|
%i32 = call i32 @llvm.umin.i32(i32 undef, i32 undef)
|
|
%i64 = call i64 @llvm.umin.i64(i64 undef, i64 undef)
|
|
%V1i8 = call <1 x i8> @llvm.umin.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
%V3i8 = call <3 x i8> @llvm.umin.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
%V4i8 = call <4 x i8> @llvm.umin.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
%V8i8 = call <8 x i8> @llvm.umin.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
%V16i8 = call <16 x i8> @llvm.umin.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
%V32i8 = call <32 x i8> @llvm.umin.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
%V64i8 = call <64 x i8> @llvm.umin.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
%V2i16 = call <2 x i16> @llvm.umin.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
%V4i16 = call <4 x i16> @llvm.umin.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
%V8i16 = call <8 x i16> @llvm.umin.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
%V16i16 = call <16 x i16> @llvm.umin.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
%V2i32 = call <2 x i32> @llvm.umin.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
%V4i32 = call <4 x i32> @llvm.umin.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
%V8i32 = call <8 x i32> @llvm.umin.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
%V2i64 = call <2 x i64> @llvm.umin.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
%V4i64 = call <4 x i64> @llvm.umin.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @umax() {
|
|
; CHECK-LABEL: 'umax'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.umax.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.umax.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4i64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%i8 = call i8 @llvm.umax.i8(i8 undef, i8 undef)
|
|
%i16 = call i16 @llvm.umax.i16(i16 undef, i16 undef)
|
|
%i32 = call i32 @llvm.umax.i32(i32 undef, i32 undef)
|
|
%i64 = call i64 @llvm.umax.i64(i64 undef, i64 undef)
|
|
%V1i8 = call <1 x i8> @llvm.umax.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
%V3i8 = call <3 x i8> @llvm.umax.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
%V4i8 = call <4 x i8> @llvm.umax.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
%V8i8 = call <8 x i8> @llvm.umax.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
%V16i8 = call <16 x i8> @llvm.umax.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
%V32i8 = call <32 x i8> @llvm.umax.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
%V64i8 = call <64 x i8> @llvm.umax.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
%V2i16 = call <2 x i16> @llvm.umax.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
%V4i16 = call <4 x i16> @llvm.umax.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
%V8i16 = call <8 x i16> @llvm.umax.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
%V16i16 = call <16 x i16> @llvm.umax.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
%V2i32 = call <2 x i32> @llvm.umax.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
%V4i32 = call <4 x i32> @llvm.umax.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
%V8i32 = call <8 x i32> @llvm.umax.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
%V2i64 = call <2 x i64> @llvm.umax.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
%V4i64 = call <4 x i64> @llvm.umax.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @smin() {
|
|
; CHECK-LABEL: 'smin'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.smin.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.smin.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4i64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%i8 = call i8 @llvm.smin.i8(i8 undef, i8 undef)
|
|
%i16 = call i16 @llvm.smin.i16(i16 undef, i16 undef)
|
|
%i32 = call i32 @llvm.smin.i32(i32 undef, i32 undef)
|
|
%i64 = call i64 @llvm.smin.i64(i64 undef, i64 undef)
|
|
%V1i8 = call <1 x i8> @llvm.smin.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
%V3i8 = call <3 x i8> @llvm.smin.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
%V4i8 = call <4 x i8> @llvm.smin.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
%V8i8 = call <8 x i8> @llvm.smin.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
%V16i8 = call <16 x i8> @llvm.smin.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
%V32i8 = call <32 x i8> @llvm.smin.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
%V64i8 = call <64 x i8> @llvm.smin.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
%V2i16 = call <2 x i16> @llvm.smin.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
%V4i16 = call <4 x i16> @llvm.smin.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
%V8i16 = call <8 x i16> @llvm.smin.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
%V16i16 = call <16 x i16> @llvm.smin.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
%V2i32 = call <2 x i32> @llvm.smin.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
%V4i32 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
%V8i32 = call <8 x i32> @llvm.smin.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
%V2i64 = call <2 x i64> @llvm.smin.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
%V4i64 = call <4 x i64> @llvm.smin.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @smax() {
|
|
; CHECK-LABEL: 'smax'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %i64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V1i8 = call <1 x i8> @llvm.smax.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V3i8 = call <3 x i8> @llvm.smax.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4i64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%i8 = call i8 @llvm.smax.i8(i8 undef, i8 undef)
|
|
%i16 = call i16 @llvm.smax.i16(i16 undef, i16 undef)
|
|
%i32 = call i32 @llvm.smax.i32(i32 undef, i32 undef)
|
|
%i64 = call i64 @llvm.smax.i64(i64 undef, i64 undef)
|
|
%V1i8 = call <1 x i8> @llvm.smax.v1i8(<1 x i8> undef, <1 x i8> undef)
|
|
%V3i8 = call <3 x i8> @llvm.smax.v3i8(<3 x i8> undef, <3 x i8> undef)
|
|
%V4i8 = call <4 x i8> @llvm.smax.v4i8(<4 x i8> undef, <4 x i8> undef)
|
|
%V8i8 = call <8 x i8> @llvm.smax.v8i8(<8 x i8> undef, <8 x i8> undef)
|
|
%V16i8 = call <16 x i8> @llvm.smax.v16i8(<16 x i8> undef, <16 x i8> undef)
|
|
%V32i8 = call <32 x i8> @llvm.smax.v32i8(<32 x i8> undef, <32 x i8> undef)
|
|
%V64i8 = call <64 x i8> @llvm.smax.v64i8(<64 x i8> undef, <64 x i8> undef)
|
|
%V2i16 = call <2 x i16> @llvm.smax.v2i16(<2 x i16> undef, <2 x i16> undef)
|
|
%V4i16 = call <4 x i16> @llvm.smax.v4i16(<4 x i16> undef, <4 x i16> undef)
|
|
%V8i16 = call <8 x i16> @llvm.smax.v8i16(<8 x i16> undef, <8 x i16> undef)
|
|
%V16i16 = call <16 x i16> @llvm.smax.v16i16(<16 x i16> undef, <16 x i16> undef)
|
|
%V2i32 = call <2 x i32> @llvm.smax.v2i32(<2 x i32> undef, <2 x i32> undef)
|
|
%V4i32 = call <4 x i32> @llvm.smax.v4i32(<4 x i32> undef, <4 x i32> undef)
|
|
%V8i32 = call <8 x i32> @llvm.smax.v8i32(<8 x i32> undef, <8 x i32> undef)
|
|
%V2i64 = call <2 x i64> @llvm.smax.v2i64(<2 x i64> undef, <2 x i64> undef)
|
|
%V4i64 = call <4 x i64> @llvm.smax.v4i64(<4 x i64> undef, <4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minnum16() {
|
|
; CHECK-NOF16-LABEL: 'minnum16'
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.minnum.f16(half undef, half undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %V2f16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %V4f16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %V8f16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %V16f16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-F16-LABEL: 'minnum16'
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.minnum.f16(half undef, half undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 4 for: %V16f16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f16 = call half @llvm.minnum.f16(half undef, half undef)
|
|
%V2f16 = call <2 x half> @llvm.minnum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
%V4f16 = call <4 x half> @llvm.minnum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
%V8f16 = call <8 x half> @llvm.minnum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
%V16f16 = call <16 x half> @llvm.minnum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @maxnum16() {
|
|
; CHECK-NOF16-LABEL: 'maxnum16'
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.maxnum.f16(half undef, half undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %V2f16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %V4f16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %V8f16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %V16f16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-F16-LABEL: 'maxnum16'
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.maxnum.f16(half undef, half undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 4 for: %V16f16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f16 = call half @llvm.maxnum.f16(half undef, half undef)
|
|
%V2f16 = call <2 x half> @llvm.maxnum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
%V4f16 = call <4 x half> @llvm.maxnum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
%V8f16 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
%V16f16 = call <16 x half> @llvm.maxnum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minnum() {
|
|
; CHECK-LABEL: 'minnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f32 = call float @llvm.minnum.f32(float undef, float undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f64 = call double @llvm.minnum.f64(double undef, double undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8f32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4f64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f32 = call float @llvm.minnum.f32(float undef, float undef)
|
|
%f64 = call double @llvm.minnum.f64(double undef, double undef)
|
|
%V2f32 = call <2 x float> @llvm.minnum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
%V4f32 = call <4 x float> @llvm.minnum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
%V8f32 = call <8 x float> @llvm.minnum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
%V2f64 = call <2 x double> @llvm.minnum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
%V4f64 = call <4 x double> @llvm.minnum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @maxnum() {
|
|
; CHECK-LABEL: 'maxnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f32 = call float @llvm.maxnum.f32(float undef, float undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f64 = call double @llvm.maxnum.f64(double undef, double undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8f32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4f64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f32 = call float @llvm.maxnum.f32(float undef, float undef)
|
|
%f64 = call double @llvm.maxnum.f64(double undef, double undef)
|
|
%V2f32 = call <2 x float> @llvm.maxnum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
%V4f32 = call <4 x float> @llvm.maxnum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
%V8f32 = call <8 x float> @llvm.maxnum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
%V2f64 = call <2 x double> @llvm.maxnum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
%V4f64 = call <4 x double> @llvm.maxnum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
ret void
|
|
}
|
|
|
|
|
|
define void @minimum16() {
|
|
; CHECK-NOF16-LABEL: 'minimum16'
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.minimum.f16(half undef, half undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %V2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %V4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %V8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %V16f16 = call <16 x half> @llvm.minimum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-F16-LABEL: 'minimum16'
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.minimum.f16(half undef, half undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 4 for: %V16f16 = call <16 x half> @llvm.minimum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f16 = call half @llvm.minimum.f16(half undef, half undef)
|
|
%V2f16 = call <2 x half> @llvm.minimum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
%V4f16 = call <4 x half> @llvm.minimum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
%V8f16 = call <8 x half> @llvm.minimum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
%V16f16 = call <16 x half> @llvm.minimum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @maximum16() {
|
|
; CHECK-NOF16-LABEL: 'maximum16'
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.maximum.f16(half undef, half undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %V2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %V4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %V8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %V16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-F16-LABEL: 'maximum16'
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %f16 = call half @llvm.maximum.f16(half undef, half undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 4 for: %V16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f16 = call half @llvm.maximum.f16(half undef, half undef)
|
|
%V2f16 = call <2 x half> @llvm.maximum.v2f16(<2 x half> undef, <2 x half> undef)
|
|
%V4f16 = call <4 x half> @llvm.maximum.v4f16(<4 x half> undef, <4 x half> undef)
|
|
%V8f16 = call <8 x half> @llvm.maximum.v8f16(<8 x half> undef, <8 x half> undef)
|
|
%V16f16 = call <16 x half> @llvm.maximum.v16f16(<16 x half> undef, <16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minimum() {
|
|
; CHECK-LABEL: 'minimum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f32 = call float @llvm.minimum.f32(float undef, float undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f64 = call double @llvm.minimum.f64(double undef, double undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8f32 = call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4f64 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f32 = call float @llvm.minimum.f32(float undef, float undef)
|
|
%f64 = call double @llvm.minimum.f64(double undef, double undef)
|
|
%V2f32 = call <2 x float> @llvm.minimum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
%V4f32 = call <4 x float> @llvm.minimum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
%V8f32 = call <8 x float> @llvm.minimum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
%V2f64 = call <2 x double> @llvm.minimum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
%V4f64 = call <4 x double> @llvm.minimum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @maximum() {
|
|
; CHECK-LABEL: 'maximum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f32 = call float @llvm.maximum.f32(float undef, float undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %f64 = call double @llvm.maximum.f64(double undef, double undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%f32 = call float @llvm.maximum.f32(float undef, float undef)
|
|
%f64 = call double @llvm.maximum.f64(double undef, double undef)
|
|
%V2f32 = call <2 x float> @llvm.maximum.v2f32(<2 x float> undef, <2 x float> undef)
|
|
%V4f32 = call <4 x float> @llvm.maximum.v4f32(<4 x float> undef, <4 x float> undef)
|
|
%V8f32 = call <8 x float> @llvm.maximum.v8f32(<8 x float> undef, <8 x float> undef)
|
|
%V2f64 = call <2 x double> @llvm.maximum.v2f64(<2 x double> undef, <2 x double> undef)
|
|
%V4f64 = call <4 x double> @llvm.maximum.v4f64(<4 x double> undef, <4 x double> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minimumnum() {
|
|
; CHECK-LABEL: 'minimumnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %1 = call float @llvm.minimumnum.f32(float poison, float poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %2 = call double @llvm.minimumnum.f64(double poison, double poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %3 = call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %4 = call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 10 for: %5 = call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 20 for: %6 = call <16 x float> @llvm.minimumnum.v16f32(<16 x float> poison, <16 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %7 = call <2 x double> @llvm.minimumnum.v2f64(<2 x double> poison, <2 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 10 for: %8 = call <4 x double> @llvm.minimumnum.v4f64(<4 x double> poison, <4 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 20 for: %9 = call <8 x double> @llvm.minimumnum.v8f64(<8 x double> poison, <8 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 40 for: %10 = call <16 x double> @llvm.minimumnum.v16f64(<16 x double> poison, <16 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call float @llvm.minimumnum.f32(float poison, float poison)
|
|
call double @llvm.minimumnum.f64(double poison, double poison)
|
|
call <2 x float> @llvm.minimumnum.v2f32(<2 x float> poison, <2 x float> poison)
|
|
call <4 x float> @llvm.minimumnum.v4f32(<4 x float> poison, <4 x float> poison)
|
|
call <8 x float> @llvm.minimumnum.v8f32(<8 x float> poison, <8 x float> poison)
|
|
call <16 x float> @llvm.minimumnum.v16f32(<16 x float> poison, <16 x float> poison)
|
|
call <2 x double> @llvm.minimumnum.v2f64(<2 x double> poison, <2 x double> poison)
|
|
call <4 x double> @llvm.minimumnum.v4f64(<4 x double> poison, <4 x double> poison)
|
|
call <8 x double> @llvm.minimumnum.v8f64(<8 x double> poison, <8 x double> poison)
|
|
call <16 x double> @llvm.minimumnum.v16f64(<16 x double> poison, <16 x double> poison)
|
|
ret void
|
|
}
|
|
|
|
define void @minimumnum_fp16() {
|
|
; CHECK-NOF16-LABEL: 'minimumnum_fp16'
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of 1 for: %1 = call half @llvm.minimumnum.f16(half poison, half poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %2 = call <2 x half> @llvm.minimumnum.v2f16(<2 x half> poison, <2 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %3 = call <4 x half> @llvm.minimumnum.v4f16(<4 x half> poison, <4 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %4 = call <8 x half> @llvm.minimumnum.v8f16(<8 x half> poison, <8 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %5 = call <16 x half> @llvm.minimumnum.v16f16(<16 x half> poison, <16 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-F16-LABEL: 'minimumnum_fp16'
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %1 = call half @llvm.minimumnum.f16(half poison, half poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %2 = call <2 x half> @llvm.minimumnum.v2f16(<2 x half> poison, <2 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %3 = call <4 x half> @llvm.minimumnum.v4f16(<4 x half> poison, <4 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %4 = call <8 x half> @llvm.minimumnum.v8f16(<8 x half> poison, <8 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 10 for: %5 = call <16 x half> @llvm.minimumnum.v16f16(<16 x half> poison, <16 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call half @llvm.minimumnum.f32(half poison, half poison)
|
|
call <2 x half> @llvm.minimumnum.v2f16(<2 x half> poison, <2 x half> poison)
|
|
call <4 x half> @llvm.minimumnum.v4f16(<4 x half> poison, <4 x half> poison)
|
|
call <8 x half> @llvm.minimumnum.v8f16(<8 x half> poison, <8 x half> poison)
|
|
call <16 x half> @llvm.minimumnum.v16f16(<16 x half> poison, <16 x half> poison)
|
|
ret void
|
|
}
|
|
|
|
define void @minimumnum_bf16() {
|
|
; CHECK-LABEL: 'minimumnum_bf16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %1 = call bfloat @llvm.minimumnum.bf16(bfloat poison, bfloat poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %2 = call <2 x bfloat> @llvm.minimumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %3 = call <4 x bfloat> @llvm.minimumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %4 = call <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %5 = call <16 x bfloat> @llvm.minimumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call bfloat @llvm.minimumnum.f32(bfloat poison, bfloat poison)
|
|
call <2 x bfloat> @llvm.minimumnum.v2fb16(<2 x bfloat> poison, <2 x bfloat> poison)
|
|
call <4 x bfloat> @llvm.minimumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
|
|
call <8 x bfloat> @llvm.minimumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
|
|
call <16 x bfloat> @llvm.minimumnum.v6bf16(<16 x bfloat> poison, <16 x bfloat> poison)
|
|
ret void
|
|
}
|
|
|
|
define void @maximumnum() {
|
|
; CHECK-LABEL: 'maximumnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %1 = call float @llvm.maximumnum.f32(float poison, float poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %2 = call double @llvm.maximumnum.f64(double poison, double poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %3 = call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %4 = call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 10 for: %5 = call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 20 for: %6 = call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %7 = call <2 x double> @llvm.maximumnum.v2f64(<2 x double> poison, <2 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 10 for: %8 = call <4 x double> @llvm.maximumnum.v4f64(<4 x double> poison, <4 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 20 for: %9 = call <8 x double> @llvm.maximumnum.v8f64(<8 x double> poison, <8 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of 40 for: %10 = call <16 x double> @llvm.maximumnum.v16f64(<16 x double> poison, <16 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call float @llvm.maximumnum.f32(float poison, float poison)
|
|
call double @llvm.maximumnum.f64(double poison, double poison)
|
|
call <2 x float> @llvm.maximumnum.v2f32(<2 x float> poison, <2 x float> poison)
|
|
call <4 x float> @llvm.maximumnum.v4f32(<4 x float> poison, <4 x float> poison)
|
|
call <8 x float> @llvm.maximumnum.v8f32(<8 x float> poison, <8 x float> poison)
|
|
call <16 x float> @llvm.maximumnum.v16f32(<16 x float> poison, <16 x float> poison)
|
|
call <2 x double> @llvm.maximumnum.v2f64(<2 x double> poison, <2 x double> poison)
|
|
call <4 x double> @llvm.maximumnum.v4f64(<4 x double> poison, <4 x double> poison)
|
|
call <8 x double> @llvm.maximumnum.v8f64(<8 x double> poison, <8 x double> poison)
|
|
call <16 x double> @llvm.maximumnum.v16f64(<16 x double> poison, <16 x double> poison)
|
|
ret void
|
|
}
|
|
|
|
define void @maximumnum_fp16() {
|
|
; CHECK-NOF16-LABEL: 'maximumnum_fp16'
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of 1 for: %1 = call half @llvm.maximumnum.f16(half poison, half poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %2 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %3 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %4 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %5 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
|
|
; CHECK-NOF16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
; CHECK-F16-LABEL: 'maximumnum_fp16'
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %1 = call half @llvm.maximumnum.f16(half poison, half poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %2 = call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %3 = call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 3 for: %4 = call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of 10 for: %5 = call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
|
|
; CHECK-F16-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call half @llvm.maximumnum.f32(half poison, half poison)
|
|
call <2 x half> @llvm.maximumnum.v2f16(<2 x half> poison, <2 x half> poison)
|
|
call <4 x half> @llvm.maximumnum.v4f16(<4 x half> poison, <4 x half> poison)
|
|
call <8 x half> @llvm.maximumnum.v8f16(<8 x half> poison, <8 x half> poison)
|
|
call <16 x half> @llvm.maximumnum.v16f16(<16 x half> poison, <16 x half> poison)
|
|
ret void
|
|
}
|
|
|
|
define void @maximumnum_bf16() {
|
|
; CHECK-LABEL: 'maximumnum_bf16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %1 = call bfloat @llvm.maximumnum.bf16(bfloat poison, bfloat poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:4 CodeSize:3 Lat:4 SizeLat:4 for: %2 = call <2 x bfloat> @llvm.maximumnum.v2bf16(<2 x bfloat> poison, <2 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:10 CodeSize:7 Lat:10 SizeLat:10 for: %3 = call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:22 CodeSize:15 Lat:22 SizeLat:22 for: %4 = call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:44 CodeSize:30 Lat:44 SizeLat:44 for: %5 = call <16 x bfloat> @llvm.maximumnum.v16bf16(<16 x bfloat> poison, <16 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call bfloat @llvm.maximumnum.f32(bfloat poison, bfloat poison)
|
|
call <2 x bfloat> @llvm.maximumnum.v2fb16(<2 x bfloat> poison, <2 x bfloat> poison)
|
|
call <4 x bfloat> @llvm.maximumnum.v4bf16(<4 x bfloat> poison, <4 x bfloat> poison)
|
|
call <8 x bfloat> @llvm.maximumnum.v8bf16(<8 x bfloat> poison, <8 x bfloat> poison)
|
|
call <16 x bfloat> @llvm.maximumnum.v6bf16(<16 x bfloat> poison, <16 x bfloat> poison)
|
|
ret void
|
|
}
|
|
|
|
declare i8 @llvm.umin.i8(i8, i8)
|
|
declare i16 @llvm.umin.i16(i16, i16)
|
|
declare i32 @llvm.umin.i32(i32, i32)
|
|
declare i64 @llvm.umin.i64(i64, i64)
|
|
declare <1 x i8> @llvm.umin.v1i8(<1 x i8>, <1 x i8>)
|
|
declare <3 x i8> @llvm.umin.v3i8(<3 x i8>, <3 x i8>)
|
|
declare <4 x i8> @llvm.umin.v4i8(<4 x i8>, <4 x i8>)
|
|
declare <8 x i8> @llvm.umin.v8i8(<8 x i8>, <8 x i8>)
|
|
declare <16 x i8> @llvm.umin.v16i8(<16 x i8>, <16 x i8>)
|
|
declare <32 x i8> @llvm.umin.v32i8(<32 x i8>, <32 x i8>)
|
|
declare <64 x i8> @llvm.umin.v64i8(<64 x i8>, <64 x i8>)
|
|
declare <2 x i16> @llvm.umin.v2i16(<2 x i16>, <2 x i16>)
|
|
declare <4 x i16> @llvm.umin.v4i16(<4 x i16>, <4 x i16>)
|
|
declare <8 x i16> @llvm.umin.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <16 x i16> @llvm.umin.v16i16(<16 x i16>, <16 x i16>)
|
|
declare <2 x i32> @llvm.umin.v2i32(<2 x i32>, <2 x i32>)
|
|
declare <4 x i32> @llvm.umin.v4i32(<4 x i32>, <4 x i32>)
|
|
declare <8 x i32> @llvm.umin.v8i32(<8 x i32>, <8 x i32>)
|
|
declare <2 x i64> @llvm.umin.v2i64(<2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.umin.v4i64(<4 x i64>, <4 x i64>)
|
|
|
|
declare i8 @llvm.umax.i8(i8, i8)
|
|
declare i16 @llvm.umax.i16(i16, i16)
|
|
declare i32 @llvm.umax.i32(i32, i32)
|
|
declare i64 @llvm.umax.i64(i64, i64)
|
|
declare <1 x i8> @llvm.umax.v1i8(<1 x i8>, <1 x i8>)
|
|
declare <3 x i8> @llvm.umax.v3i8(<3 x i8>, <3 x i8>)
|
|
declare <4 x i8> @llvm.umax.v4i8(<4 x i8>, <4 x i8>)
|
|
declare <8 x i8> @llvm.umax.v8i8(<8 x i8>, <8 x i8>)
|
|
declare <16 x i8> @llvm.umax.v16i8(<16 x i8>, <16 x i8>)
|
|
declare <32 x i8> @llvm.umax.v32i8(<32 x i8>, <32 x i8>)
|
|
declare <64 x i8> @llvm.umax.v64i8(<64 x i8>, <64 x i8>)
|
|
declare <2 x i16> @llvm.umax.v2i16(<2 x i16>, <2 x i16>)
|
|
declare <4 x i16> @llvm.umax.v4i16(<4 x i16>, <4 x i16>)
|
|
declare <8 x i16> @llvm.umax.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <16 x i16> @llvm.umax.v16i16(<16 x i16>, <16 x i16>)
|
|
declare <2 x i32> @llvm.umax.v2i32(<2 x i32>, <2 x i32>)
|
|
declare <4 x i32> @llvm.umax.v4i32(<4 x i32>, <4 x i32>)
|
|
declare <8 x i32> @llvm.umax.v8i32(<8 x i32>, <8 x i32>)
|
|
declare <2 x i64> @llvm.umax.v2i64(<2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.umax.v4i64(<4 x i64>, <4 x i64>)
|
|
|
|
declare i8 @llvm.smin.i8(i8, i8)
|
|
declare i16 @llvm.smin.i16(i16, i16)
|
|
declare i32 @llvm.smin.i32(i32, i32)
|
|
declare i64 @llvm.smin.i64(i64, i64)
|
|
declare <1 x i8> @llvm.smin.v1i8(<1 x i8>, <1 x i8>)
|
|
declare <3 x i8> @llvm.smin.v3i8(<3 x i8>, <3 x i8>)
|
|
declare <4 x i8> @llvm.smin.v4i8(<4 x i8>, <4 x i8>)
|
|
declare <8 x i8> @llvm.smin.v8i8(<8 x i8>, <8 x i8>)
|
|
declare <16 x i8> @llvm.smin.v16i8(<16 x i8>, <16 x i8>)
|
|
declare <32 x i8> @llvm.smin.v32i8(<32 x i8>, <32 x i8>)
|
|
declare <64 x i8> @llvm.smin.v64i8(<64 x i8>, <64 x i8>)
|
|
declare <2 x i16> @llvm.smin.v2i16(<2 x i16>, <2 x i16>)
|
|
declare <4 x i16> @llvm.smin.v4i16(<4 x i16>, <4 x i16>)
|
|
declare <8 x i16> @llvm.smin.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <16 x i16> @llvm.smin.v16i16(<16 x i16>, <16 x i16>)
|
|
declare <2 x i32> @llvm.smin.v2i32(<2 x i32>, <2 x i32>)
|
|
declare <4 x i32> @llvm.smin.v4i32(<4 x i32>, <4 x i32>)
|
|
declare <8 x i32> @llvm.smin.v8i32(<8 x i32>, <8 x i32>)
|
|
declare <2 x i64> @llvm.smin.v2i64(<2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.smin.v4i64(<4 x i64>, <4 x i64>)
|
|
|
|
declare i8 @llvm.smax.i8(i8, i8)
|
|
declare i16 @llvm.smax.i16(i16, i16)
|
|
declare i32 @llvm.smax.i32(i32, i32)
|
|
declare i64 @llvm.smax.i64(i64, i64)
|
|
declare <1 x i8> @llvm.smax.v1i8(<1 x i8>, <1 x i8>)
|
|
declare <3 x i8> @llvm.smax.v3i8(<3 x i8>, <3 x i8>)
|
|
declare <4 x i8> @llvm.smax.v4i8(<4 x i8>, <4 x i8>)
|
|
declare <8 x i8> @llvm.smax.v8i8(<8 x i8>, <8 x i8>)
|
|
declare <16 x i8> @llvm.smax.v16i8(<16 x i8>, <16 x i8>)
|
|
declare <32 x i8> @llvm.smax.v32i8(<32 x i8>, <32 x i8>)
|
|
declare <64 x i8> @llvm.smax.v64i8(<64 x i8>, <64 x i8>)
|
|
declare <2 x i16> @llvm.smax.v2i16(<2 x i16>, <2 x i16>)
|
|
declare <4 x i16> @llvm.smax.v4i16(<4 x i16>, <4 x i16>)
|
|
declare <8 x i16> @llvm.smax.v8i16(<8 x i16>, <8 x i16>)
|
|
declare <16 x i16> @llvm.smax.v16i16(<16 x i16>, <16 x i16>)
|
|
declare <2 x i32> @llvm.smax.v2i32(<2 x i32>, <2 x i32>)
|
|
declare <4 x i32> @llvm.smax.v4i32(<4 x i32>, <4 x i32>)
|
|
declare <8 x i32> @llvm.smax.v8i32(<8 x i32>, <8 x i32>)
|
|
declare <2 x i64> @llvm.smax.v2i64(<2 x i64>, <2 x i64>)
|
|
declare <4 x i64> @llvm.smax.v4i64(<4 x i64>, <4 x i64>)
|
|
|
|
declare half @llvm.minnum.f16(half, half)
|
|
declare float @llvm.minnum.f32(float, float)
|
|
declare double @llvm.minnum.f64(double, double)
|
|
declare <2 x half> @llvm.minnum.v2f16(<2 x half>, <2 x half>)
|
|
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 <16 x half> @llvm.minnum.v16f16(<16 x half>, <16 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 <8 x float> @llvm.minnum.v8f32(<8 x float>, <8 x float>)
|
|
declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
|
|
declare <4 x double> @llvm.minnum.v4f64(<4 x double>, <4 x double>)
|
|
|
|
declare half @llvm.maxnum.f16(half, half)
|
|
declare float @llvm.maxnum.f32(float, float)
|
|
declare double @llvm.maxnum.f64(double, double)
|
|
declare <2 x half> @llvm.maxnum.v2f16(<2 x half>, <2 x half>)
|
|
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 <16 x half> @llvm.maxnum.v16f16(<16 x half>, <16 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 <8 x float> @llvm.maxnum.v8f32(<8 x float>, <8 x float>)
|
|
declare <2 x double> @llvm.maxnum.v2f64(<2 x double>, <2 x double>)
|
|
declare <4 x double> @llvm.maxnum.v4f64(<4 x double>, <4 x double>)
|
|
|
|
declare half @llvm.minimum.f16(half, half)
|
|
declare float @llvm.minimum.f32(float, float)
|
|
declare double @llvm.minimum.f64(double, double)
|
|
declare <2 x half> @llvm.minimum.v2f16(<2 x half>, <2 x half>)
|
|
declare <4 x half> @llvm.minimum.v4f16(<4 x half>, <4 x half>)
|
|
declare <8 x half> @llvm.minimum.v8f16(<8 x half>, <8 x half>)
|
|
declare <16 x half> @llvm.minimum.v16f16(<16 x half>, <16 x half>)
|
|
declare <2 x float> @llvm.minimum.v2f32(<2 x float>, <2 x float>)
|
|
declare <4 x float> @llvm.minimum.v4f32(<4 x float>, <4 x float>)
|
|
declare <8 x float> @llvm.minimum.v8f32(<8 x float>, <8 x float>)
|
|
declare <2 x double> @llvm.minimum.v2f64(<2 x double>, <2 x double>)
|
|
declare <4 x double> @llvm.minimum.v4f64(<4 x double>, <4 x double>)
|
|
|
|
declare half @llvm.maximum.f16(half, half)
|
|
declare float @llvm.maximum.f32(float, float)
|
|
declare double @llvm.maximum.f64(double, double)
|
|
declare <2 x half> @llvm.maximum.v2f16(<2 x half>, <2 x half>)
|
|
declare <4 x half> @llvm.maximum.v4f16(<4 x half>, <4 x half>)
|
|
declare <8 x half> @llvm.maximum.v8f16(<8 x half>, <8 x half>)
|
|
declare <16 x half> @llvm.maximum.v16f16(<16 x half>, <16 x half>)
|
|
declare <2 x float> @llvm.maximum.v2f32(<2 x float>, <2 x float>)
|
|
declare <4 x float> @llvm.maximum.v4f32(<4 x float>, <4 x float>)
|
|
declare <8 x float> @llvm.maximum.v8f32(<8 x float>, <8 x float>)
|
|
declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
|
|
declare <4 x double> @llvm.maximum.v4f64(<4 x double>, <4 x double>)
|