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
346 lines
30 KiB
LLVM
346 lines
30 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
|
|
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -passes="print<cost-model>" -cost-kind=throughput 2>&1 -disable-output | FileCheck %s
|
|
; RUN: opt < %s -mtriple=riscv32 -mattr=+v -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck %s --check-prefix=SIZE
|
|
; RUN: opt < %s -mtriple=riscv64 -mattr=+v -passes="print<cost-model>" -cost-kind=code-size 2>&1 -disable-output | FileCheck %s --check-prefix=SIZE
|
|
|
|
define i32 @reduce_umin_i1(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_umin_i1'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.umax.v1i1(<1 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.umax.v2i1(<2 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.umax.v4i1(<4 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.umax.v8i1(<8 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.umax.v16i1(<16 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i1 @llvm.vector.reduce.umax.v32i1(<32 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call i1 @llvm.vector.reduce.umax.v64i1(<64 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = call i1 @llvm.vector.reduce.umax.v128i1(<128 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_umin_i1'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.umax.v1i1(<1 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i1 @llvm.vector.reduce.umax.v2i1(<2 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i1 @llvm.vector.reduce.umax.v4i1(<4 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i1 @llvm.vector.reduce.umax.v8i1(<8 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i1 @llvm.vector.reduce.umax.v16i1(<16 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i1 @llvm.vector.reduce.umax.v32i1(<32 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call i1 @llvm.vector.reduce.umax.v64i1(<64 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = call i1 @llvm.vector.reduce.umax.v128i1(<128 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i1 @llvm.vector.reduce.umax.v1i1(<1 x i1> undef)
|
|
%V2 = call i1 @llvm.vector.reduce.umax.v2i1(<2 x i1> undef)
|
|
%V4 = call i1 @llvm.vector.reduce.umax.v4i1(<4 x i1> undef)
|
|
%V8 = call i1 @llvm.vector.reduce.umax.v8i1(<8 x i1> undef)
|
|
%V16 = call i1 @llvm.vector.reduce.umax.v16i1(<16 x i1> undef)
|
|
%V32 = call i1 @llvm.vector.reduce.umax.v32i1(<32 x i1> undef)
|
|
%V64 = call i1 @llvm.vector.reduce.umax.v64i1(<64 x i1> undef)
|
|
%V128 = call i1 @llvm.vector.reduce.umax.v128i1(<128 x i1> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_umax_i8(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_umax_i8'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.vector.reduce.umax.v4i8(<4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_umax_i8'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.vector.reduce.umax.v4i8(<4 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i8 @llvm.vector.reduce.umax.v1i8(<1 x i8> undef)
|
|
%V2 = call i8 @llvm.vector.reduce.umax.v2i8(<2 x i8> undef)
|
|
%V4 = call i8 @llvm.vector.reduce.umax.v4i8(<4 x i8> undef)
|
|
%V8 = call i8 @llvm.vector.reduce.umax.v8i8(<8 x i8> undef)
|
|
%V16 = call i8 @llvm.vector.reduce.umax.v16i8(<16 x i8> undef)
|
|
%V32 = call i8 @llvm.vector.reduce.umax.v32i8(<32 x i8> undef)
|
|
%V64 = call i8 @llvm.vector.reduce.umax.v64i8(<64 x i8> undef)
|
|
%V128 = call i8 @llvm.vector.reduce.umax.v128i8(<128 x i8> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_umax_i16(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_umax_i16'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i16 @llvm.vector.reduce.umax.v1i16(<1 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V128 = call i16 @llvm.vector.reduce.umax.v128i16(<128 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_umax_i16'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i16 @llvm.vector.reduce.umax.v1i16(<1 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i16 @llvm.vector.reduce.umax.v128i16(<128 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i16 @llvm.vector.reduce.umax.v1i16(<1 x i16> undef)
|
|
%V2 = call i16 @llvm.vector.reduce.umax.v2i16(<2 x i16> undef)
|
|
%V4 = call i16 @llvm.vector.reduce.umax.v4i16(<4 x i16> undef)
|
|
%V8 = call i16 @llvm.vector.reduce.umax.v8i16(<8 x i16> undef)
|
|
%V16 = call i16 @llvm.vector.reduce.umax.v16i16(<16 x i16> undef)
|
|
%V32 = call i16 @llvm.vector.reduce.umax.v32i16(<32 x i16> undef)
|
|
%V64 = call i16 @llvm.vector.reduce.umax.v64i16(<64 x i16> undef)
|
|
%V128 = call i16 @llvm.vector.reduce.umax.v128i16(<128 x i16> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_umax_i32(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_umax_i32'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i32 @llvm.vector.reduce.umax.v1i32(<1 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i32 @llvm.vector.reduce.umax.v32i32(<32 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i32 @llvm.vector.reduce.umax.v64i32(<64 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i32 @llvm.vector.reduce.umax.v128i32(<128 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_umax_i32'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i32 @llvm.vector.reduce.umax.v1i32(<1 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i32 @llvm.vector.reduce.umax.v32i32(<32 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i32 @llvm.vector.reduce.umax.v64i32(<64 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V128 = call i32 @llvm.vector.reduce.umax.v128i32(<128 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i32 @llvm.vector.reduce.umax.v1i32(<1 x i32> undef)
|
|
%V2 = call i32 @llvm.vector.reduce.umax.v2i32(<2 x i32> undef)
|
|
%V4 = call i32 @llvm.vector.reduce.umax.v4i32(<4 x i32> undef)
|
|
%V8 = call i32 @llvm.vector.reduce.umax.v8i32(<8 x i32> undef)
|
|
%V16 = call i32 @llvm.vector.reduce.umax.v16i32(<16 x i32> undef)
|
|
%V32 = call i32 @llvm.vector.reduce.umax.v32i32(<32 x i32> undef)
|
|
%V64 = call i32 @llvm.vector.reduce.umax.v64i32(<64 x i32> undef)
|
|
%V128 = call i32 @llvm.vector.reduce.umax.v128i32(<128 x i32> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_umax_i64(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_umax_i64'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i64 @llvm.vector.reduce.umax.v16i64(<16 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i64 @llvm.vector.reduce.umax.v32i64(<32 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V64 = call i64 @llvm.vector.reduce.umax.v64i64(<64 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V128 = call i64 @llvm.vector.reduce.umax.v128i64(<128 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_umax_i64'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i64 @llvm.vector.reduce.umax.v16i64(<16 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i64 @llvm.vector.reduce.umax.v32i64(<32 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64 = call i64 @llvm.vector.reduce.umax.v64i64(<64 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i64 @llvm.vector.reduce.umax.v128i64(<128 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i64 @llvm.vector.reduce.umax.v1i64(<1 x i64> undef)
|
|
%V2 = call i64 @llvm.vector.reduce.umax.v2i64(<2 x i64> undef)
|
|
%V4 = call i64 @llvm.vector.reduce.umax.v4i64(<4 x i64> undef)
|
|
%V8 = call i64 @llvm.vector.reduce.umax.v8i64(<8 x i64> undef)
|
|
%V16 = call i64 @llvm.vector.reduce.umax.v16i64(<16 x i64> undef)
|
|
%V32 = call i64 @llvm.vector.reduce.umax.v32i64(<32 x i64> undef)
|
|
%V64 = call i64 @llvm.vector.reduce.umax.v64i64(<64 x i64> undef)
|
|
%V128 = call i64 @llvm.vector.reduce.umax.v128i64(<128 x i64> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_smin_i1(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_smin_i1'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.smax.v2i1(<2 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.smax.v4i1(<4 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.smax.v8i1(<8 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i1 @llvm.vector.reduce.smax.v16i1(<16 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.smax.v32i1(<32 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i1 @llvm.vector.reduce.smax.v64i1(<64 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i1 @llvm.vector.reduce.smax.v128i1(<128 x i1> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_smin_i1'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V2 = call i1 @llvm.vector.reduce.smax.v2i1(<2 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i1 @llvm.vector.reduce.smax.v4i1(<4 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V8 = call i1 @llvm.vector.reduce.smax.v8i1(<8 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V16 = call i1 @llvm.vector.reduce.smax.v16i1(<16 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i1 @llvm.vector.reduce.smax.v32i1(<32 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i1 @llvm.vector.reduce.smax.v64i1(<64 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i1 @llvm.vector.reduce.smax.v128i1(<128 x i1> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i1 @llvm.vector.reduce.smax.v1i1(<1 x i1> undef)
|
|
%V2 = call i1 @llvm.vector.reduce.smax.v2i1(<2 x i1> undef)
|
|
%V4 = call i1 @llvm.vector.reduce.smax.v4i1(<4 x i1> undef)
|
|
%V8 = call i1 @llvm.vector.reduce.smax.v8i1(<8 x i1> undef)
|
|
%V16 = call i1 @llvm.vector.reduce.smax.v16i1(<16 x i1> undef)
|
|
%V32 = call i1 @llvm.vector.reduce.smax.v32i1(<32 x i1> undef)
|
|
%V64 = call i1 @llvm.vector.reduce.smax.v64i1(<64 x i1> undef)
|
|
%V128 = call i1 @llvm.vector.reduce.smax.v128i1(<128 x i1> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_smax_i8(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_smax_i8'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i8 @llvm.vector.reduce.smax.v1i8(<1 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_smax_i8'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i8 @llvm.vector.reduce.smax.v1i8(<1 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i8 @llvm.vector.reduce.smax.v1i8(<1 x i8> undef)
|
|
%V2 = call i8 @llvm.vector.reduce.smax.v2i8(<2 x i8> undef)
|
|
%V4 = call i8 @llvm.vector.reduce.smax.v4i8(<4 x i8> undef)
|
|
%V8 = call i8 @llvm.vector.reduce.smax.v8i8(<8 x i8> undef)
|
|
%V16 = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> undef)
|
|
%V32 = call i8 @llvm.vector.reduce.smax.v32i8(<32 x i8> undef)
|
|
%V64 = call i8 @llvm.vector.reduce.smax.v64i8(<64 x i8> undef)
|
|
%V128 = call i8 @llvm.vector.reduce.smax.v128i8(<128 x i8> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_smax_i16(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_smax_i16'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i16 @llvm.vector.reduce.smax.v1i16(<1 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 7 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 15 for instruction: %V128 = call i16 @llvm.vector.reduce.smax.v128i16(<128 x i16> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_smax_i16'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i16 @llvm.vector.reduce.smax.v1i16(<1 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V128 = call i16 @llvm.vector.reduce.smax.v128i16(<128 x i16> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i16 @llvm.vector.reduce.smax.v1i16(<1 x i16> undef)
|
|
%V2 = call i16 @llvm.vector.reduce.smax.v2i16(<2 x i16> undef)
|
|
%V4 = call i16 @llvm.vector.reduce.smax.v4i16(<4 x i16> undef)
|
|
%V8 = call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> undef)
|
|
%V16 = call i16 @llvm.vector.reduce.smax.v16i16(<16 x i16> undef)
|
|
%V32 = call i16 @llvm.vector.reduce.smax.v32i16(<32 x i16> undef)
|
|
%V64 = call i16 @llvm.vector.reduce.smax.v64i16(<64 x i16> undef)
|
|
%V128 = call i16 @llvm.vector.reduce.smax.v128i16(<128 x i16> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_smax_i32(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_smax_i32'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i32 @llvm.vector.reduce.smax.v1i32(<1 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 6 for instruction: %V32 = call i32 @llvm.vector.reduce.smax.v32i32(<32 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 14 for instruction: %V64 = call i32 @llvm.vector.reduce.smax.v64i32(<64 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 30 for instruction: %V128 = call i32 @llvm.vector.reduce.smax.v128i32(<128 x i32> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_smax_i32'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i32 @llvm.vector.reduce.smax.v1i32(<1 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V32 = call i32 @llvm.vector.reduce.smax.v32i32(<32 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V64 = call i32 @llvm.vector.reduce.smax.v64i32(<64 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V128 = call i32 @llvm.vector.reduce.smax.v128i32(<128 x i32> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i32 @llvm.vector.reduce.smax.v1i32(<1 x i32> undef)
|
|
%V2 = call i32 @llvm.vector.reduce.smax.v2i32(<2 x i32> undef)
|
|
%V4 = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> undef)
|
|
%V8 = call i32 @llvm.vector.reduce.smax.v8i32(<8 x i32> undef)
|
|
%V16 = call i32 @llvm.vector.reduce.smax.v16i32(<16 x i32> undef)
|
|
%V32 = call i32 @llvm.vector.reduce.smax.v32i32(<32 x i32> undef)
|
|
%V64 = call i32 @llvm.vector.reduce.smax.v64i32(<64 x i32> undef)
|
|
%V128 = call i32 @llvm.vector.reduce.smax.v128i32(<128 x i32> undef)
|
|
ret i32 undef
|
|
}
|
|
|
|
define i32 @reduce_smax_i64(i32 %arg) {
|
|
; CHECK-LABEL: 'reduce_smax_i64'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %V1 = call i64 @llvm.vector.reduce.smax.v1i64(<1 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V4 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 4 for instruction: %V8 = call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V16 = call i64 @llvm.vector.reduce.smax.v16i64(<16 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %V32 = call i64 @llvm.vector.reduce.smax.v32i64(<32 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 29 for instruction: %V64 = call i64 @llvm.vector.reduce.smax.v64i64(<64 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 61 for instruction: %V128 = call i64 @llvm.vector.reduce.smax.v128i64(<128 x i64> undef)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
|
|
;
|
|
; SIZE-LABEL: 'reduce_smax_i64'
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V1 = call i64 @llvm.vector.reduce.smax.v1i64(<1 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V2 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V4 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V8 = call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %V16 = call i64 @llvm.vector.reduce.smax.v16i64(<16 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 3 for instruction: %V32 = call i64 @llvm.vector.reduce.smax.v32i64(<32 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 5 for instruction: %V64 = call i64 @llvm.vector.reduce.smax.v64i64(<64 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 9 for instruction: %V128 = call i64 @llvm.vector.reduce.smax.v128i64(<128 x i64> undef)
|
|
; SIZE-NEXT: Cost Model: Found an estimated cost of 1 for instruction: ret i32 undef
|
|
;
|
|
%V1 = call i64 @llvm.vector.reduce.smax.v1i64(<1 x i64> undef)
|
|
%V2 = call i64 @llvm.vector.reduce.smax.v2i64(<2 x i64> undef)
|
|
%V4 = call i64 @llvm.vector.reduce.smax.v4i64(<4 x i64> undef)
|
|
%V8 = call i64 @llvm.vector.reduce.smax.v8i64(<8 x i64> undef)
|
|
%V16 = call i64 @llvm.vector.reduce.smax.v16i64(<16 x i64> undef)
|
|
%V32 = call i64 @llvm.vector.reduce.smax.v32i64(<32 x i64> undef)
|
|
%V64 = call i64 @llvm.vector.reduce.smax.v64i64(<64 x i64> undef)
|
|
%V128 = call i64 @llvm.vector.reduce.smax.v128i64(<128 x i64> undef)
|
|
ret i32 undef
|
|
}
|