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
106 lines
12 KiB
LLVM
106 lines
12 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
|
|
; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=aarch64--linux-gnu | FileCheck %s
|
|
|
|
target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
|
|
|
|
define void @vector_splice(i32 %offset) #0 {
|
|
; CHECK-LABEL: 'vector_splice'
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %1 = call <16 x i8> @llvm.vector.splice.left.v16i8(<16 x i8> zeroinitializer, <16 x i8> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %2 = call <32 x i8> @llvm.vector.splice.left.v32i8(<32 x i8> zeroinitializer, <32 x i8> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %3 = call <2 x i16> @llvm.vector.splice.left.v2i16(<2 x i16> zeroinitializer, <2 x i16> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %4 = call <4 x i16> @llvm.vector.splice.left.v4i16(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %5 = call <8 x i16> @llvm.vector.splice.left.v8i16(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %6 = call <16 x i16> @llvm.vector.splice.left.v16i16(<16 x i16> zeroinitializer, <16 x i16> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %7 = call <4 x i32> @llvm.vector.splice.left.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %8 = call <8 x i32> @llvm.vector.splice.left.v8i32(<8 x i32> zeroinitializer, <8 x i32> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %9 = call <2 x i64> @llvm.vector.splice.left.v2i64(<2 x i64> zeroinitializer, <2 x i64> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %10 = call <4 x i64> @llvm.vector.splice.left.v4i64(<4 x i64> zeroinitializer, <4 x i64> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %11 = call <2 x half> @llvm.vector.splice.left.v2f16(<2 x half> zeroinitializer, <2 x half> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %12 = call <4 x half> @llvm.vector.splice.left.v4f16(<4 x half> zeroinitializer, <4 x half> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %13 = call <8 x half> @llvm.vector.splice.left.v8f16(<8 x half> zeroinitializer, <8 x half> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %14 = call <16 x half> @llvm.vector.splice.left.v16f16(<16 x half> zeroinitializer, <16 x half> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %15 = call <2 x float> @llvm.vector.splice.left.v2f32(<2 x float> zeroinitializer, <2 x float> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %16 = call <4 x float> @llvm.vector.splice.left.v4f32(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %17 = call <8 x float> @llvm.vector.splice.left.v8f32(<8 x float> zeroinitializer, <8 x float> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %18 = call <2 x double> @llvm.vector.splice.left.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %19 = call <4 x double> @llvm.vector.splice.left.v4f64(<4 x double> zeroinitializer, <4 x double> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %20 = call <2 x bfloat> @llvm.vector.splice.left.v2bf16(<2 x bfloat> zeroinitializer, <2 x bfloat> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %21 = call <4 x bfloat> @llvm.vector.splice.left.v4bf16(<4 x bfloat> zeroinitializer, <4 x bfloat> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %22 = call <8 x bfloat> @llvm.vector.splice.left.v8bf16(<8 x bfloat> zeroinitializer, <8 x bfloat> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 2 for instruction: %23 = call <16 x bfloat> @llvm.vector.splice.left.v16bf16(<16 x bfloat> zeroinitializer, <16 x bfloat> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %24 = call <16 x i1> @llvm.vector.splice.left.v16i1(<16 x i1> zeroinitializer, <16 x i1> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %25 = call <8 x i1> @llvm.vector.splice.left.v8i1(<8 x i1> zeroinitializer, <8 x i1> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %26 = call <4 x i1> @llvm.vector.splice.left.v4i1(<4 x i1> zeroinitializer, <4 x i1> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %27 = call <2 x i1> @llvm.vector.splice.left.v2i1(<2 x i1> zeroinitializer, <2 x i1> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: %28 = call <2 x i128> @llvm.vector.splice.left.v2i128(<2 x i128> zeroinitializer, <2 x i128> zeroinitializer, i32 1)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %left.variable = call <4 x i32> @llvm.vector.splice.left.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 %offset)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 12 for instruction: %right.variable = call <4 x i32> @llvm.vector.splice.right.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 %offset)
|
|
; CHECK-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret void
|
|
;
|
|
%splice.v16i8 = call <16 x i8> @llvm.vector.splice.v16i8(<16 x i8> zeroinitializer, <16 x i8> zeroinitializer, i32 1)
|
|
%splice.v32i8 = call <32 x i8> @llvm.vector.splice.v32i8(<32 x i8> zeroinitializer, <32 x i8> zeroinitializer, i32 1)
|
|
%splice.v2i16 = call <2 x i16> @llvm.vector.splice.v2i16(<2 x i16> zeroinitializer, <2 x i16> zeroinitializer, i32 1)
|
|
%splice.v4i16 = call <4 x i16> @llvm.vector.splice.v4i16(<4 x i16> zeroinitializer, <4 x i16> zeroinitializer, i32 1)
|
|
%splice.v8i16 = call <8 x i16> @llvm.vector.splice.v8i16(<8 x i16> zeroinitializer, <8 x i16> zeroinitializer, i32 1)
|
|
%splice.v16i16 = call <16 x i16> @llvm.vector.splice.v16i16(<16 x i16> zeroinitializer, <16 x i16> zeroinitializer, i32 1)
|
|
%splice.v4i32 = call <4 x i32> @llvm.vector.splice.v4i32(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 1)
|
|
%splice.v8i32 = call <8 x i32> @llvm.vector.splice.v8i32(<8 x i32> zeroinitializer, <8 x i32> zeroinitializer, i32 1)
|
|
%splice.v2i64 = call <2 x i64> @llvm.vector.splice.v2i64(<2 x i64> zeroinitializer, <2 x i64> zeroinitializer, i32 1)
|
|
%splice.v4i64 = call <4 x i64> @llvm.vector.splice.v4i64(<4 x i64> zeroinitializer, <4 x i64> zeroinitializer, i32 1)
|
|
%splice.v2f16 = call <2 x half> @llvm.vector.splice.v2f16(<2 x half> zeroinitializer, <2 x half> zeroinitializer, i32 1)
|
|
%splice.v4f16 = call <4 x half> @llvm.vector.splice.v4f16(<4 x half> zeroinitializer, <4 x half> zeroinitializer, i32 1)
|
|
%splice.v8f16 = call <8 x half> @llvm.vector.splice.v8f16(<8 x half> zeroinitializer, <8 x half> zeroinitializer, i32 1)
|
|
%splice.v16f16 = call <16 x half> @llvm.vector.splice.v16f16(<16 x half> zeroinitializer, <16 x half> zeroinitializer, i32 1)
|
|
%splice.v2f32 = call <2 x float> @llvm.vector.splice.v2f32(<2 x float> zeroinitializer, <2 x float> zeroinitializer, i32 1)
|
|
%splice.v4f32 = call <4 x float> @llvm.vector.splice.v4f32(<4 x float> zeroinitializer, <4 x float> zeroinitializer, i32 1)
|
|
%splice.v8f32 = call <8 x float> @llvm.vector.splice.v8f32(<8 x float> zeroinitializer, <8 x float> zeroinitializer, i32 1)
|
|
%splice.v2f64 = call <2 x double> @llvm.vector.splice.v2f64(<2 x double> zeroinitializer, <2 x double> zeroinitializer, i32 1)
|
|
%splice.v4f64 = call <4 x double> @llvm.vector.splice.v4f64(<4 x double> zeroinitializer, <4 x double> zeroinitializer, i32 1)
|
|
%splice.v2bf16 = call <2 x bfloat> @llvm.vector.splice.v2bf16(<2 x bfloat> zeroinitializer, <2 x bfloat> zeroinitializer, i32 1)
|
|
%splice.v4bf16 = call <4 x bfloat> @llvm.vector.splice.v4bf16(<4 x bfloat> zeroinitializer, <4 x bfloat> zeroinitializer, i32 1)
|
|
%splice.v8bf16 = call <8 x bfloat> @llvm.vector.splice.v8bf16(<8 x bfloat> zeroinitializer, <8 x bfloat> zeroinitializer, i32 1)
|
|
%splice.v16bf16 = call <16 x bfloat> @llvm.vector.splice.v16bf16(<16 x bfloat> zeroinitializer, <16 x bfloat> zeroinitializer, i32 1)
|
|
%splice.v16i1 = call <16 x i1> @llvm.vector.splice.v16i1(<16 x i1> zeroinitializer, <16 x i1> zeroinitializer, i32 1)
|
|
%splice.v8i1 = call <8 x i1> @llvm.vector.splice.v8i1(<8 x i1> zeroinitializer, <8 x i1> zeroinitializer, i32 1)
|
|
%splice.v4i1 = call <4 x i1> @llvm.vector.splice.v4i1(<4 x i1> zeroinitializer, <4 x i1> zeroinitializer, i32 1)
|
|
%splice.v2i1 = call <2 x i1> @llvm.vector.splice.v2i1(<2 x i1> zeroinitializer, <2 x i1> zeroinitializer, i32 1)
|
|
%splice.v2i128 = call <2 x i128> @llvm.vector.splice.v2i128(<2 x i128> zeroinitializer, <2 x i128> zeroinitializer, i32 1)
|
|
|
|
%left.variable = call <4 x i32> @llvm.vector.splice.left(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 %offset)
|
|
%right.variable = call <4 x i32> @llvm.vector.splice.right(<4 x i32> zeroinitializer, <4 x i32> zeroinitializer, i32 %offset)
|
|
ret void
|
|
}
|
|
|
|
declare <2 x i1> @llvm.vector.splice.v2i1(<2 x i1>, <2 x i1>, i32)
|
|
declare <4 x i1> @llvm.vector.splice.v4i1(<4 x i1>, <4 x i1>, i32)
|
|
declare <8 x i1> @llvm.vector.splice.v8i1(<8 x i1>, <8 x i1>, i32)
|
|
declare <16 x i1> @llvm.vector.splice.v16i1(<16 x i1>, <16 x i1>, i32)
|
|
declare <2 x i8> @llvm.vector.splice.v2i8(<2 x i8>, <2 x i8>, i32)
|
|
declare <16 x i8> @llvm.vector.splice.v16i8(<16 x i8>, <16 x i8>, i32)
|
|
declare <32 x i8> @llvm.vector.splice.v32i8(<32 x i8>, <32 x i8>, i32)
|
|
declare <2 x i16> @llvm.vector.splice.v2i16(<2 x i16>, <2 x i16>, i32)
|
|
declare <4 x i16> @llvm.vector.splice.v4i16(<4 x i16>, <4 x i16>, i32)
|
|
declare <8 x i16> @llvm.vector.splice.v8i16(<8 x i16>, <8 x i16>, i32)
|
|
declare <16 x i16> @llvm.vector.splice.v16i16(<16 x i16>, <16 x i16>, i32)
|
|
declare <4 x i32> @llvm.vector.splice.v4i32(<4 x i32>, <4 x i32>, i32)
|
|
declare <8 x i32> @llvm.vector.splice.v8i32(<8 x i32>, <8 x i32>, i32)
|
|
declare <2 x i64> @llvm.vector.splice.v2i64(<2 x i64>, <2 x i64>, i32)
|
|
declare <4 x i64> @llvm.vector.splice.v4i64(<4 x i64>, <4 x i64>, i32)
|
|
declare <2 x half> @llvm.vector.splice.v2f16(<2 x half>, <2 x half>, i32)
|
|
declare <4 x half> @llvm.vector.splice.v4f16(<4 x half>, <4 x half>, i32)
|
|
declare <8 x half> @llvm.vector.splice.v8f16(<8 x half>, <8 x half>, i32)
|
|
declare <16 x half> @llvm.vector.splice.v16f16(<16 x half>, <16 x half>, i32)
|
|
declare <2 x bfloat> @llvm.vector.splice.v2bf16(<2 x bfloat>, <2 x bfloat>, i32)
|
|
declare <4 x bfloat> @llvm.vector.splice.v4bf16(<4 x bfloat>, <4 x bfloat>, i32)
|
|
declare <8 x bfloat> @llvm.vector.splice.v8bf16(<8 x bfloat>, <8 x bfloat>, i32)
|
|
declare <16 x bfloat> @llvm.vector.splice.v16bf16(<16 x bfloat>, <16 x bfloat>, i32)
|
|
declare <2 x float> @llvm.vector.splice.v2f32(<2 x float>, <2 x float>, i32)
|
|
declare <4 x float> @llvm.vector.splice.v4f32(<4 x float>, <4 x float>, i32)
|
|
declare <8 x float> @llvm.vector.splice.v8f32(<8 x float>, <8 x float>, i32)
|
|
declare <16 x float> @llvm.vector.splice.v16f32(<16 x float>, <16 x float>, i32)
|
|
declare <2 x double> @llvm.vector.splice.v2f64(<2 x double>, <2 x double>, i32)
|
|
declare <4 x double> @llvm.vector.splice.v4f64(<4 x double>, <4 x double>, i32)
|
|
declare <2 x i128> @llvm.vector.splice.v2i128(<2 x i128>, <2 x i128>, i32)
|
|
|
|
attributes #0 = { "target-features"="+bf16" }
|