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
282 lines
11 KiB
LLVM
282 lines
11 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -mtriple=aarch64--linux-gnu -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 i8 @add.i8.v8i8(<8 x i8> %v) {
|
|
; CHECK-LABEL: 'add.i8.v8i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i8 @add.i8.v16i8(<16 x i8> %v) {
|
|
; CHECK-LABEL: 'add.i8.v16i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i16 @add.i16.v4i16(<4 x i16> %v) {
|
|
; CHECK-LABEL: 'add.i16.v4i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i16 @add.i16.v8i16(<8 x i16> %v) {
|
|
; CHECK-LABEL: 'add.i16.v8i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i32 @add.i32.v4i32(<4 x i32> %v) {
|
|
; CHECK-LABEL: 'add.i32.v4i32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 %r
|
|
;
|
|
%r = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> %v)
|
|
ret i32 %r
|
|
}
|
|
|
|
define i8 @umin.i8.v8i8(<8 x i8> %v) {
|
|
; CHECK-LABEL: 'umin.i8.v8i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.umin.v8i8(<8 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i8 @umin.i8.v16i8(<16 x i8> %v) {
|
|
; CHECK-LABEL: 'umin.i8.v16i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.umin.v16i8(<16 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i16 @umin.i16.v4i16(<4 x i16> %v) {
|
|
; CHECK-LABEL: 'umin.i16.v4i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.umin.v4i16(<4 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i16 @umin.i16.v8i16(<8 x i16> %v) {
|
|
; CHECK-LABEL: 'umin.i16.v8i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.umin.v8i16(<8 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i32 @umin.i32.v4i32(<4 x i32> %v) {
|
|
; CHECK-LABEL: 'umin.i32.v4i32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 %r
|
|
;
|
|
%r = call i32 @llvm.vector.reduce.umin.v4i32(<4 x i32> %v)
|
|
ret i32 %r
|
|
}
|
|
|
|
define i8 @umax.i8.v8i8(<8 x i8> %v) {
|
|
; CHECK-LABEL: 'umax.i8.v8i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i8 @umax.i8.v16i8(<16 x i8> %v) {
|
|
; CHECK-LABEL: 'umax.i8.v16i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i16 @umax.i16.v4i16(<4 x i16> %v) {
|
|
; CHECK-LABEL: 'umax.i16.v4i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i16 @umax.i16.v8i16(<8 x i16> %v) {
|
|
; CHECK-LABEL: 'umax.i16.v8i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i32 @umax.i32.v4i32(<4 x i32> %v) {
|
|
; CHECK-LABEL: 'umax.i32.v4i32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 %r
|
|
;
|
|
%r = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> %v)
|
|
ret i32 %r
|
|
}
|
|
|
|
define i8 @smin.i8.v8i8(<8 x i8> %v) {
|
|
; CHECK-LABEL: 'smin.i8.v8i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.smin.v8i8(<8 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i8 @smin.i8.v16i8(<16 x i8> %v) {
|
|
; CHECK-LABEL: 'smin.i8.v16i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.smin.v16i8(<16 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i16 @smin.i16.v4i16(<4 x i16> %v) {
|
|
; CHECK-LABEL: 'smin.i16.v4i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.smin.v4i16(<4 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i16 @smin.i16.v8i16(<8 x i16> %v) {
|
|
; CHECK-LABEL: 'smin.i16.v8i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.smin.v8i16(<8 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i32 @smin.i32.v4i32(<4 x i32> %v) {
|
|
; CHECK-LABEL: 'smin.i32.v4i32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 %r
|
|
;
|
|
%r = call i32 @llvm.vector.reduce.smin.v4i32(<4 x i32> %v)
|
|
ret i32 %r
|
|
}
|
|
|
|
define i8 @smax.i8.v8i8(<8 x i8> %v) {
|
|
; CHECK-LABEL: 'smax.i8.v8i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i8 @smax.i8.v16i8(<16 x i8> %v) {
|
|
; CHECK-LABEL: 'smax.i8.v16i8'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i8 %r
|
|
;
|
|
%r = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> %v)
|
|
ret i8 %r
|
|
}
|
|
|
|
define i16 @smax.i16.v4i16(<4 x i16> %v) {
|
|
; CHECK-LABEL: 'smax.i16.v4i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i16 @smax.i16.v8i16(<8 x i16> %v) {
|
|
; CHECK-LABEL: 'smax.i16.v8i16'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i16 %r
|
|
;
|
|
%r = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> %v)
|
|
ret i16 %r
|
|
}
|
|
|
|
define i32 @smax.i32.v4i32(<4 x i32> %v) {
|
|
; CHECK-LABEL: 'smax.i32.v4i32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret i32 %r
|
|
;
|
|
%r = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> %v)
|
|
ret i32 %r
|
|
}
|
|
|
|
define float @fmin.f32.v4f32(<4 x float> %v) {
|
|
; CHECK-LABEL: 'fmin.f32.v4f32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call nnan float @llvm.vector.reduce.fmin.v4f32(<4 x float> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret float %r
|
|
;
|
|
%r = call nnan float @llvm.vector.reduce.fmin.v4f32(<4 x float> %v)
|
|
ret float %r
|
|
}
|
|
|
|
define float @fmax.f32.v4f32(<4 x float> %v) {
|
|
; CHECK-LABEL: 'fmax.f32.v4f32'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %r = call nnan float @llvm.vector.reduce.fmax.v4f32(<4 x float> %v)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret float %r
|
|
;
|
|
%r = call nnan float @llvm.vector.reduce.fmax.v4f32(<4 x float> %v)
|
|
ret float %r
|
|
}
|
|
|
|
declare i8 @llvm.vector.reduce.add.v8i8(<8 x i8>)
|
|
declare i8 @llvm.vector.reduce.add.v16i8(<16 x i8>)
|
|
declare i16 @llvm.vector.reduce.add.v4i16(<4 x i16>)
|
|
declare i16 @llvm.vector.reduce.add.v8i16(<8 x i16>)
|
|
declare i32 @llvm.vector.reduce.add.v4i32(<4 x i32>)
|
|
|
|
declare i8 @llvm.vector.reduce.umin.v8i8(<8 x i8>)
|
|
declare i8 @llvm.vector.reduce.umin.v16i8(<16 x i8>)
|
|
declare i16 @llvm.vector.reduce.umin.v4i16(<4 x i16>)
|
|
declare i16 @llvm.vector.reduce.umin.v8i16(<8 x i16>)
|
|
declare i32 @llvm.vector.reduce.umin.v4i32(<4 x i32>)
|
|
|
|
declare i8 @llvm.vector.reduce.umax.v8i8(<8 x i8>)
|
|
declare i8 @llvm.vector.reduce.umax.v16i8(<16 x i8>)
|
|
declare i16 @llvm.vector.reduce.umax.v4i16(<4 x i16>)
|
|
declare i16 @llvm.vector.reduce.umax.v8i16(<8 x i16>)
|
|
declare i32 @llvm.vector.reduce.umax.v4i32(<4 x i32>)
|
|
|
|
declare i8 @llvm.vector.reduce.smin.v8i8(<8 x i8>)
|
|
declare i8 @llvm.vector.reduce.smin.v16i8(<16 x i8>)
|
|
declare i16 @llvm.vector.reduce.smin.v4i16(<4 x i16>)
|
|
declare i16 @llvm.vector.reduce.smin.v8i16(<8 x i16>)
|
|
declare i32 @llvm.vector.reduce.smin.v4i32(<4 x i32>)
|
|
|
|
declare i8 @llvm.vector.reduce.smax.v8i8(<8 x i8>)
|
|
declare i8 @llvm.vector.reduce.smax.v16i8(<16 x i8>)
|
|
declare i16 @llvm.vector.reduce.smax.v4i16(<4 x i16>)
|
|
declare i16 @llvm.vector.reduce.smax.v8i16(<8 x i16>)
|
|
declare i32 @llvm.vector.reduce.smax.v4i32(<4 x i32>)
|
|
|
|
declare float @llvm.vector.reduce.fmin.v4f32(<4 x float>)
|
|
|
|
declare float @llvm.vector.reduce.fmax.v4f32(<4 x float>)
|