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
46 lines
3.4 KiB
LLVM
46 lines
3.4 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
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
define void @reduce() {
|
|
; CHECK-LABEL: 'reduce'
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V1i8 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i8 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V3i8 = call i8 @llvm.vector.reduce.add.v3i8(<3 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i8 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 5 for: %V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 2 for: %V2i64 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of 3 for: %V4i64 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found costs of RThru:0 CodeSize:1 Lat:1 SizeLat:1 for: ret void
|
|
;
|
|
%V1i8 = call i8 @llvm.vector.reduce.add.v1i8(<1 x i8> undef)
|
|
%V2i8 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
|
|
%V3i8 = call i8 @llvm.vector.reduce.add.v3i8(<3 x i8> undef)
|
|
%V4i8 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
|
|
%V8i8 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
|
|
%V16i8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
|
|
%V32i8 = call i8 @llvm.vector.reduce.add.v32i8(<32 x i8> undef)
|
|
%V64i8 = call i8 @llvm.vector.reduce.add.v64i8(<64 x i8> undef)
|
|
%V2i16 = call i16 @llvm.vector.reduce.add.v2i16(<2 x i16> undef)
|
|
%V4i16 = call i16 @llvm.vector.reduce.add.v4i16(<4 x i16> undef)
|
|
%V8i16 = call i16 @llvm.vector.reduce.add.v8i16(<8 x i16> undef)
|
|
%V16i16 = call i16 @llvm.vector.reduce.add.v16i16(<16 x i16> undef)
|
|
%V2i32 = call i32 @llvm.vector.reduce.add.v2i32(<2 x i32> undef)
|
|
%V4i32 = call i32 @llvm.vector.reduce.add.v4i32(<4 x i32> undef)
|
|
%V8i32 = call i32 @llvm.vector.reduce.add.v8i32(<8 x i32> undef)
|
|
%V2i64 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
|
|
%V4i64 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
|
|
ret void
|
|
}
|