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
440 lines
44 KiB
LLVM
440 lines
44 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -mtriple=aarch64-unknown-linux-gnu -mattr=+sve -passes="print<cost-model>" -cost-kind=all 2>&1 -disable-output | FileCheck %s
|
|
|
|
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 1 for: %V4i8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <vscale x 32 x i8> @llvm.umin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <vscale x 64 x i8> @llvm.umin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %V1i32 = call <vscale x 1 x i32> @llvm.umin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i64 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i64 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V4i8 = call <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
%V8i8 = call <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
%V16i8 = call <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
%V32i8 = call <vscale x 32 x i8> @llvm.umin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
%V64i8 = call <vscale x 64 x i8> @llvm.umin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
%V2i16 = call <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
%V4i16 = call <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
%V8i16 = call <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
%V16i16 = call <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
%V1i32 = call <vscale x 1 x i32> @llvm.umin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
%V2i32 = call <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
%V4i32 = call <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
%V8i32 = call <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
%V2i64 = call <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
%V4i64 = call <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @umax() {
|
|
; CHECK-LABEL: 'umax'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <vscale x 32 x i8> @llvm.umax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <vscale x 64 x i8> @llvm.umax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %V1i32 = call <vscale x 1 x i32> @llvm.umax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i64 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i64 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V4i8 = call <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
%V8i8 = call <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
%V16i8 = call <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
%V32i8 = call <vscale x 32 x i8> @llvm.umax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
%V64i8 = call <vscale x 64 x i8> @llvm.umax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
%V2i16 = call <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
%V4i16 = call <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
%V8i16 = call <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
%V16i16 = call <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
%V1i32 = call <vscale x 1 x i32> @llvm.umax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
%V2i32 = call <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
%V4i32 = call <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
%V8i32 = call <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
%V2i64 = call <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
%V4i64 = call <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @smin() {
|
|
; CHECK-LABEL: 'smin'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <vscale x 32 x i8> @llvm.smin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <vscale x 64 x i8> @llvm.smin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %V1i32 = call <vscale x 1 x i32> @llvm.smin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i64 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i64 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V4i8 = call <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
%V8i8 = call <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
%V16i8 = call <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
%V32i8 = call <vscale x 32 x i8> @llvm.smin.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
%V64i8 = call <vscale x 64 x i8> @llvm.smin.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
%V2i16 = call <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
%V4i16 = call <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
%V8i16 = call <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
%V16i16 = call <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
%V1i32 = call <vscale x 1 x i32> @llvm.smin.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
%V2i32 = call <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
%V4i32 = call <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
%V8i32 = call <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
%V2i64 = call <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
%V4i64 = call <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @smax() {
|
|
; CHECK-LABEL: 'smax'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i8 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V16i8 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V32i8 = call <vscale x 32 x i8> @llvm.smax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 4 for: %V64i8 = call <vscale x 64 x i8> @llvm.smax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i16 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8i16 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i16 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %V1i32 = call <vscale x 1 x i32> @llvm.smax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i32 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4i32 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i32 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2i64 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i64 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V4i8 = call <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef)
|
|
%V8i8 = call <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef)
|
|
%V16i8 = call <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef)
|
|
%V32i8 = call <vscale x 32 x i8> @llvm.smax.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef)
|
|
%V64i8 = call <vscale x 64 x i8> @llvm.smax.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef)
|
|
%V2i16 = call <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef)
|
|
%V4i16 = call <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef)
|
|
%V8i16 = call <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef)
|
|
%V16i16 = call <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef)
|
|
%V1i32 = call <vscale x 1 x i32> @llvm.smax.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef)
|
|
%V2i32 = call <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef)
|
|
%V4i32 = call <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef)
|
|
%V8i32 = call <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef)
|
|
%V2i64 = call <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef)
|
|
%V4i64 = call <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minnum() {
|
|
; CHECK-LABEL: 'minnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %V1f32 = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8f32 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4f64 = call <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <vscale x 2 x half> @llvm.minnum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <vscale x 4 x half> @llvm.minnum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <vscale x 8 x half> @llvm.minnum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16f16 = call <vscale x 16 x half> @llvm.minnum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V1f32 = call <vscale x 1 x float> @llvm.minnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
|
|
%V2f32 = call <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
%V4f32 = call <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
%V8f32 = call <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
%V2f64 = call <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
%V4f64 = call <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
%V2f16 = call <vscale x 2 x half> @llvm.minnum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
%V4f16 = call <vscale x 4 x half> @llvm.minnum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
%V8f16 = call <vscale x 8 x half> @llvm.minnum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
%V16f16 = call <vscale x 16 x half> @llvm.minnum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @maxnum() {
|
|
; CHECK-LABEL: 'maxnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %V1f32 = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8f32 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4f64 = call <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <vscale x 2 x half> @llvm.maxnum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <vscale x 4 x half> @llvm.maxnum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <vscale x 8 x half> @llvm.maxnum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16f16 = call <vscale x 16 x half> @llvm.maxnum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V1f32 = call <vscale x 1 x float> @llvm.maxnum.nxv1f32(<vscale x 1 x float> undef, <vscale x 1 x float> undef)
|
|
%V2f32 = call <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
%V4f32 = call <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
%V8f32 = call <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
%V2f64 = call <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
%V4f64 = call <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
%V2f16 = call <vscale x 2 x half> @llvm.maxnum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
%V4f16 = call <vscale x 4 x half> @llvm.maxnum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
%V8f16 = call <vscale x 8 x half> @llvm.maxnum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
%V16f16 = call <vscale x 16 x half> @llvm.maxnum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minimum() {
|
|
; CHECK-LABEL: 'minimum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8f32 = call <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4f64 = call <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <vscale x 2 x half> @llvm.minimum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <vscale x 4 x half> @llvm.minimum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <vscale x 8 x half> @llvm.minimum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16f16 = call <vscale x 16 x half> @llvm.minimum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V2f32 = call <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
%V4f32 = call <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
%V8f32 = call <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
%V2f64 = call <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
%V4f64 = call <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
%V2f16 = call <vscale x 2 x half> @llvm.minimum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
%V4f16 = call <vscale x 4 x half> @llvm.minimum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
%V8f16 = call <vscale x 8 x half> @llvm.minimum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
%V16f16 = call <vscale x 16 x half> @llvm.minimum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @maximum() {
|
|
; CHECK-LABEL: 'maximum'
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f32 = call <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f32 = call <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8f32 = call <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f64 = call <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4f64 = call <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V2f16 = call <vscale x 2 x half> @llvm.maximum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V4f16 = call <vscale x 4 x half> @llvm.maximum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 1 for: %V8f16 = call <vscale x 8 x half> @llvm.maximum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16f16 = call <vscale x 16 x half> @llvm.maximum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V2f32 = call <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef)
|
|
%V4f32 = call <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef)
|
|
%V8f32 = call <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef)
|
|
%V2f64 = call <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef)
|
|
%V4f64 = call <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef)
|
|
%V2f16 = call <vscale x 2 x half> @llvm.maximum.nxv2f16(<vscale x 2 x half> undef, <vscale x 2 x half> undef)
|
|
%V4f16 = call <vscale x 4 x half> @llvm.maximum.nxv4f16(<vscale x 4 x half> undef, <vscale x 4 x half> undef)
|
|
%V8f16 = call <vscale x 8 x half> @llvm.maximum.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x half> undef)
|
|
%V16f16 = call <vscale x 16 x half> @llvm.maximum.nxv16f16(<vscale x 16 x half> undef, <vscale x 16 x half> undef)
|
|
ret void
|
|
}
|
|
|
|
define void @minimumnum() {
|
|
; CHECK-LABEL: 'minimumnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x float> @llvm.minimumnum.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x float> @llvm.minimumnum.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x float> @llvm.minimumnum.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x float> @llvm.minimumnum.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %5 = call <vscale x 2 x double> @llvm.minimumnum.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %6 = call <vscale x 4 x double> @llvm.minimumnum.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %7 = call <vscale x 8 x double> @llvm.minimumnum.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %8 = call <vscale x 16 x double> @llvm.minimumnum.nxv16f64(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %10 = call <vscale x 2 x half> @llvm.minimumnum.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %11 = call <vscale x 4 x half> @llvm.minimumnum.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %12 = call <vscale x 8 x half> @llvm.minimumnum.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %13 = call <vscale x 16 x half> @llvm.minimumnum.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %14 = call <vscale x 2 x bfloat> @llvm.minimumnum.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %15 = call <vscale x 4 x bfloat> @llvm.minimumnum.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %16 = call <vscale x 8 x bfloat> @llvm.minimumnum.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %17 = call <vscale x 16 x bfloat> @llvm.minimumnum.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call <vscale x 2 x float> @llvm.minimumnum(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
|
|
call <vscale x 4 x float> @llvm.minimumnum(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
|
|
call <vscale x 8 x float> @llvm.minimumnum(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
|
|
call <vscale x 16 x float> @llvm.minimumnum(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
|
|
call <vscale x 2 x double> @llvm.minimumnum(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
|
|
call <vscale x 4 x double> @llvm.minimumnum(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
|
|
call <vscale x 8 x double> @llvm.minimumnum(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
|
|
call <vscale x 16 x double> @llvm.minimumnum(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
|
|
ret void
|
|
call <vscale x 2 x half> @llvm.minimumnum(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
|
|
call <vscale x 4 x half> @llvm.minimumnum(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
|
|
call <vscale x 8 x half> @llvm.minimumnum(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
|
|
call <vscale x 16 x half> @llvm.minimumnum(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
|
|
call <vscale x 2 x bfloat> @llvm.minimumnum(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
|
|
call <vscale x 4 x bfloat> @llvm.minimumnum(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
|
|
call <vscale x 8 x bfloat> @llvm.minimumnum(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
|
|
call <vscale x 16 x bfloat> @llvm.minimumnum(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
|
|
ret void
|
|
}
|
|
|
|
define void @maximumnum() {
|
|
; CHECK-LABEL: 'maximumnum'
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %1 = call <vscale x 2 x float> @llvm.maximumnum.nxv2f32(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %2 = call <vscale x 4 x float> @llvm.maximumnum.nxv4f32(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %3 = call <vscale x 8 x float> @llvm.maximumnum.nxv8f32(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %4 = call <vscale x 16 x float> @llvm.maximumnum.nxv16f32(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %5 = call <vscale x 2 x double> @llvm.maximumnum.nxv2f64(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %6 = call <vscale x 4 x double> @llvm.maximumnum.nxv4f64(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %7 = call <vscale x 8 x double> @llvm.maximumnum.nxv8f64(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %8 = call <vscale x 16 x double> @llvm.maximumnum.nxv16f64(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %10 = call <vscale x 2 x half> @llvm.maximumnum.nxv2f16(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %11 = call <vscale x 4 x half> @llvm.maximumnum.nxv4f16(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %12 = call <vscale x 8 x half> @llvm.maximumnum.nxv8f16(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %13 = call <vscale x 16 x half> @llvm.maximumnum.nxv16f16(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %14 = call <vscale x 2 x bfloat> @llvm.maximumnum.nxv2bf16(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %15 = call <vscale x 4 x bfloat> @llvm.maximumnum.nxv4bf16(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %16 = call <vscale x 8 x bfloat> @llvm.maximumnum.nxv8bf16(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of Invalid for: %17 = call <vscale x 16 x bfloat> @llvm.maximumnum.nxv16bf16(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
call <vscale x 2 x float> @llvm.maximumnum(<vscale x 2 x float> poison, <vscale x 2 x float> poison)
|
|
call <vscale x 4 x float> @llvm.maximumnum(<vscale x 4 x float> poison, <vscale x 4 x float> poison)
|
|
call <vscale x 8 x float> @llvm.maximumnum(<vscale x 8 x float> poison, <vscale x 8 x float> poison)
|
|
call <vscale x 16 x float> @llvm.maximumnum(<vscale x 16 x float> poison, <vscale x 16 x float> poison)
|
|
call <vscale x 2 x double> @llvm.maximumnum(<vscale x 2 x double> poison, <vscale x 2 x double> poison)
|
|
call <vscale x 4 x double> @llvm.maximumnum(<vscale x 4 x double> poison, <vscale x 4 x double> poison)
|
|
call <vscale x 8 x double> @llvm.maximumnum(<vscale x 8 x double> poison, <vscale x 8 x double> poison)
|
|
call <vscale x 16 x double> @llvm.maximumnum(<vscale x 16 x double> poison, <vscale x 16 x double> poison)
|
|
ret void
|
|
call <vscale x 2 x half> @llvm.maximumnum(<vscale x 2 x half> poison, <vscale x 2 x half> poison)
|
|
call <vscale x 4 x half> @llvm.maximumnum(<vscale x 4 x half> poison, <vscale x 4 x half> poison)
|
|
call <vscale x 8 x half> @llvm.maximumnum(<vscale x 8 x half> poison, <vscale x 8 x half> poison)
|
|
call <vscale x 16 x half> @llvm.maximumnum(<vscale x 16 x half> poison, <vscale x 16 x half> poison)
|
|
call <vscale x 2 x bfloat> @llvm.maximumnum(<vscale x 2 x bfloat> poison, <vscale x 2 x bfloat> poison)
|
|
call <vscale x 4 x bfloat> @llvm.maximumnum(<vscale x 4 x bfloat> poison, <vscale x 4 x bfloat> poison)
|
|
call <vscale x 8 x bfloat> @llvm.maximumnum(<vscale x 8 x bfloat> poison, <vscale x 8 x bfloat> poison)
|
|
call <vscale x 16 x bfloat> @llvm.maximumnum(<vscale x 16 x bfloat> poison, <vscale x 16 x bfloat> poison)
|
|
ret void
|
|
}
|
|
|
|
|
|
declare <vscale x 4 x i8> @llvm.umin.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
|
|
declare <vscale x 8 x i8> @llvm.umin.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
|
|
declare <vscale x 16 x i8> @llvm.umin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare <vscale x 32 x i8> @llvm.umin.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>)
|
|
declare <vscale x 64 x i8> @llvm.umin.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i8>)
|
|
declare <vscale x 2 x i16> @llvm.umin.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
|
|
declare <vscale x 4 x i16> @llvm.umin.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
|
|
declare <vscale x 8 x i16> @llvm.umin.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare <vscale x 16 x i16> @llvm.umin.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>)
|
|
declare <vscale x 2 x i32> @llvm.umin.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
|
|
declare <vscale x 4 x i32> @llvm.umin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
|
|
declare <vscale x 8 x i32> @llvm.umin.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
|
|
declare <vscale x 2 x i64> @llvm.umin.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
|
|
declare <vscale x 4 x i64> @llvm.umin.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
|
|
|
|
declare <vscale x 4 x i8> @llvm.umax.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
|
|
declare <vscale x 8 x i8> @llvm.umax.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
|
|
declare <vscale x 16 x i8> @llvm.umax.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare <vscale x 32 x i8> @llvm.umax.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>)
|
|
declare <vscale x 64 x i8> @llvm.umax.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i8>)
|
|
declare <vscale x 2 x i16> @llvm.umax.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
|
|
declare <vscale x 4 x i16> @llvm.umax.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
|
|
declare <vscale x 8 x i16> @llvm.umax.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare <vscale x 16 x i16> @llvm.umax.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>)
|
|
declare <vscale x 2 x i32> @llvm.umax.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
|
|
declare <vscale x 4 x i32> @llvm.umax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
|
|
declare <vscale x 8 x i32> @llvm.umax.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
|
|
declare <vscale x 2 x i64> @llvm.umax.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
|
|
declare <vscale x 4 x i64> @llvm.umax.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
|
|
|
|
declare <vscale x 4 x i8> @llvm.smin.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
|
|
declare <vscale x 8 x i8> @llvm.smin.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
|
|
declare <vscale x 16 x i8> @llvm.smin.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare <vscale x 32 x i8> @llvm.smin.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>)
|
|
declare <vscale x 64 x i8> @llvm.smin.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i8>)
|
|
declare <vscale x 2 x i16> @llvm.smin.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
|
|
declare <vscale x 4 x i16> @llvm.smin.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
|
|
declare <vscale x 8 x i16> @llvm.smin.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare <vscale x 16 x i16> @llvm.smin.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>)
|
|
declare <vscale x 2 x i32> @llvm.smin.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
|
|
declare <vscale x 4 x i32> @llvm.smin.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
|
|
declare <vscale x 8 x i32> @llvm.smin.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
|
|
declare <vscale x 2 x i64> @llvm.smin.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
|
|
declare <vscale x 4 x i64> @llvm.smin.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
|
|
|
|
declare <vscale x 4 x i8> @llvm.smax.nxv4i8(<vscale x 4 x i8>, <vscale x 4 x i8>)
|
|
declare <vscale x 8 x i8> @llvm.smax.nxv8i8(<vscale x 8 x i8>, <vscale x 8 x i8>)
|
|
declare <vscale x 16 x i8> @llvm.smax.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)
|
|
declare <vscale x 32 x i8> @llvm.smax.nxv32i8(<vscale x 32 x i8>, <vscale x 32 x i8>)
|
|
declare <vscale x 64 x i8> @llvm.smax.nxv64i8(<vscale x 64 x i8>, <vscale x 64 x i8>)
|
|
declare <vscale x 2 x i16> @llvm.smax.nxv2i16(<vscale x 2 x i16>, <vscale x 2 x i16>)
|
|
declare <vscale x 4 x i16> @llvm.smax.nxv4i16(<vscale x 4 x i16>, <vscale x 4 x i16>)
|
|
declare <vscale x 8 x i16> @llvm.smax.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
|
|
declare <vscale x 16 x i16> @llvm.smax.nxv16i16(<vscale x 16 x i16>, <vscale x 16 x i16>)
|
|
declare <vscale x 2 x i32> @llvm.smax.nxv2i32(<vscale x 2 x i32>, <vscale x 2 x i32>)
|
|
declare <vscale x 4 x i32> @llvm.smax.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
|
|
declare <vscale x 8 x i32> @llvm.smax.nxv8i32(<vscale x 8 x i32>, <vscale x 8 x i32>)
|
|
declare <vscale x 2 x i64> @llvm.smax.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
|
|
declare <vscale x 4 x i64> @llvm.smax.nxv4i64(<vscale x 4 x i64>, <vscale x 4 x i64>)
|
|
|
|
declare <vscale x 2 x half> @llvm.minnum.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>)
|
|
declare <vscale x 4 x half> @llvm.minnum.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
|
|
declare <vscale x 8 x half> @llvm.minnum.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 16 x half> @llvm.minnum.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>)
|
|
declare <vscale x 2 x float> @llvm.minnum.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>)
|
|
declare <vscale x 4 x float> @llvm.minnum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
|
|
declare <vscale x 8 x float> @llvm.minnum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
|
|
declare <vscale x 2 x double> @llvm.minnum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
|
|
declare <vscale x 4 x double> @llvm.minnum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
|
|
|
|
declare <vscale x 2 x half> @llvm.maxnum.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>)
|
|
declare <vscale x 4 x half> @llvm.maxnum.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
|
|
declare <vscale x 8 x half> @llvm.maxnum.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 16 x half> @llvm.maxnum.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>)
|
|
declare <vscale x 2 x float> @llvm.maxnum.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>)
|
|
declare <vscale x 4 x float> @llvm.maxnum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
|
|
declare <vscale x 8 x float> @llvm.maxnum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
|
|
declare <vscale x 2 x double> @llvm.maxnum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
|
|
declare <vscale x 4 x double> @llvm.maxnum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
|
|
|
|
declare <vscale x 2 x half> @llvm.minimum.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>)
|
|
declare <vscale x 4 x half> @llvm.minimum.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
|
|
declare <vscale x 8 x half> @llvm.minimum.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 16 x half> @llvm.minimum.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>)
|
|
declare <vscale x 2 x float> @llvm.minimum.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>)
|
|
declare <vscale x 4 x float> @llvm.minimum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
|
|
declare <vscale x 8 x float> @llvm.minimum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
|
|
declare <vscale x 2 x double> @llvm.minimum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
|
|
declare <vscale x 4 x double> @llvm.minimum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
|
|
|
|
declare <vscale x 2 x half> @llvm.maximum.nxv2f16(<vscale x 2 x half>, <vscale x 2 x half>)
|
|
declare <vscale x 4 x half> @llvm.maximum.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
|
|
declare <vscale x 8 x half> @llvm.maximum.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
|
|
declare <vscale x 16 x half> @llvm.maximum.nxv16f16(<vscale x 16 x half>, <vscale x 16 x half>)
|
|
declare <vscale x 2 x float> @llvm.maximum.nxv2f32(<vscale x 2 x float>, <vscale x 2 x float>)
|
|
declare <vscale x 4 x float> @llvm.maximum.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
|
|
declare <vscale x 8 x float> @llvm.maximum.nxv8f32(<vscale x 8 x float>, <vscale x 8 x float>)
|
|
declare <vscale x 2 x double> @llvm.maximum.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
|
|
declare <vscale x 4 x double> @llvm.maximum.nxv4f64(<vscale x 4 x double>, <vscale x 4 x double>)
|