derek/TheRock
1
0 Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
7502bf64a4a4f3bf0074ac1068e837355abcfcde
TheRock/compiler/amd-llvm/clang/test/CodeGenHLSL/BasicFeatures/MatrixSplat.hlsl
T
derek.holloway 7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
Details
CodeQL / Analyze (python) (push) Canceled after 0s
Details
pre-commit / pre-commit (push) Canceled after 0s
Details
Multi-Arch CI / setup (push) Canceled after 0s
Details
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Details
Setup (Multi-Arch) / setup (push) Canceled after 0s
Details
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Details
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
Details
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Details
Multi-Arch CI / CI Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Details
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Details
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Details
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Details
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
Details
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

205 lines
10 KiB
HLSL
Raw Blame History

// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6
// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.7-library -disable-llvm-passes -emit-llvm -finclude-default-header -o - %s | FileCheck %s
// CHECK-LABEL: define hidden void @_Z13ConstantSplatv(
// CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[M:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT: store <16 x i32> splat (i32 1), ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ConstantSplat() {
int4x4 M = 1;
}
// CHECK-LABEL: define hidden void @_Z18ConstantFloatSplatv(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[M:%.*]] = alloca [2 x <2 x float>], align 4
// CHECK-NEXT: store <4 x float> splat (float 3.250000e+00), ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ConstantFloatSplat() {
float2x2 M = 3.25;
}
// CHECK-LABEL: define hidden void @_Z21ConstantTrueBoolSplatv(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[M:%.*]] = alloca [3 x <3 x i32>], align 4
// CHECK-NEXT: store <9 x i32> splat (i32 1), ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ConstantTrueBoolSplat() {
bool3x3 M = true;
}
// CHECK-LABEL: define hidden void @_Z22ConstantFalseBoolSplatv(
// CHECK-SAME: ) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[M:%.*]] = alloca [3 x <3 x i32>], align 4
// CHECK-NEXT: store <9 x i32> zeroinitializer, ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ConstantFalseBoolSplat() {
bool3x3 M = false;
}
// CHECK-LABEL: define hidden void @_Z12DynamicSplatf(
// CHECK-SAME: float noundef nofpclass(nan inf) [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [3 x <3 x float>], align 4
// CHECK-NEXT: store float [[VALUE]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <9 x float> poison, float [[TMP0]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <9 x float> [[SPLAT_SPLATINSERT]], <9 x float> poison, <9 x i32> zeroinitializer
// CHECK-NEXT: store <9 x float> [[SPLAT_SPLAT]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void DynamicSplat(float Value) {
float3x3 M = Value;
}
// CHECK-LABEL: define hidden void @_Z16DynamicBoolSplatb(
// CHECK-SAME: i1 noundef [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [4 x <4 x i32>], align 4
// CHECK-NEXT: [[STOREDV:%.*]] = zext i1 [[VALUE]] to i32
// CHECK-NEXT: store i32 [[STOREDV]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[LOADEDV:%.*]] = icmp ne i32 [[TMP0]], 0
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <16 x i1> poison, i1 [[LOADEDV]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <16 x i1> [[SPLAT_SPLATINSERT]], <16 x i1> poison, <16 x i32> zeroinitializer
// CHECK-NEXT: [[TMP1:%.*]] = zext <16 x i1> [[SPLAT_SPLAT]] to <16 x i32>
// CHECK-NEXT: store <16 x i32> [[TMP1]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void DynamicBoolSplat(bool Value) {
bool4x4 M = Value;
}
// CHECK-LABEL: define hidden void @_Z13CastThenSplatDv4_f(
// CHECK-SAME: <4 x float> noundef nofpclass(nan inf) [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca <4 x float>, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [3 x <3 x float>], align 4
// CHECK-NEXT: store <4 x float> [[VALUE]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load <4 x float>, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[CAST_VTRUNC:%.*]] = extractelement <4 x float> [[TMP0]], i32 0
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <9 x float> poison, float [[CAST_VTRUNC]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <9 x float> [[SPLAT_SPLATINSERT]], <9 x float> poison, <9 x i32> zeroinitializer
// CHECK-NEXT: store <9 x float> [[SPLAT_SPLAT]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void CastThenSplat(float4 Value) {
float3x3 M = (float) Value;
}
// CHECK-LABEL: define hidden void @_Z30ExplicitIntToBoolCastThenSplatDv3_i(
// CHECK-SAME: <3 x i32> noundef [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca <3 x i32>, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [2 x <2 x i32>], align 4
// CHECK-NEXT: store <3 x i32> [[VALUE]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load <3 x i32>, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TOBOOL:%.*]] = icmp ne <3 x i32> [[TMP0]], zeroinitializer
// CHECK-NEXT: [[CAST_VTRUNC:%.*]] = extractelement <3 x i1> [[TOBOOL]], i32 0
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <4 x i1> poison, i1 [[CAST_VTRUNC]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <4 x i1> [[SPLAT_SPLATINSERT]], <4 x i1> poison, <4 x i32> zeroinitializer
// CHECK-NEXT: [[TMP1:%.*]] = zext <4 x i1> [[SPLAT_SPLAT]] to <4 x i32>
// CHECK-NEXT: store <4 x i32> [[TMP1]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ExplicitIntToBoolCastThenSplat(int3 Value) {
bool2x2 M = (bool) Value;
}
// CHECK-LABEL: define hidden void @_Z32ExplicitFloatToBoolCastThenSplatDv2_f(
// CHECK-SAME: <2 x float> noundef nofpclass(nan inf) [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca <2 x float>, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [3 x <2 x i32>], align 4
// CHECK-NEXT: store <2 x float> [[VALUE]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load <2 x float>, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TOBOOL:%.*]] = fcmp reassoc nnan ninf nsz arcp afn une <2 x float> [[TMP0]], zeroinitializer
// CHECK-NEXT: [[CAST_VTRUNC:%.*]] = extractelement <2 x i1> [[TOBOOL]], i32 0
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <6 x i1> poison, i1 [[CAST_VTRUNC]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <6 x i1> [[SPLAT_SPLATINSERT]], <6 x i1> poison, <6 x i32> zeroinitializer
// CHECK-NEXT: [[TMP1:%.*]] = zext <6 x i1> [[SPLAT_SPLAT]] to <6 x i32>
// CHECK-NEXT: store <6 x i32> [[TMP1]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ExplicitFloatToBoolCastThenSplat(float2 Value) {
bool2x3 M = (bool) Value;
}
// CHECK-LABEL: define hidden void @_Z32ExplicitBoolToFloatCastThenSplatb(
// CHECK-SAME: i1 noundef [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [2 x <3 x float>], align 4
// CHECK-NEXT: [[STOREDV:%.*]] = zext i1 [[VALUE]] to i32
// CHECK-NEXT: store i32 [[STOREDV]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[LOADEDV:%.*]] = icmp ne i32 [[TMP0]], 0
// CHECK-NEXT: [[CONV:%.*]] = uitofp i1 [[LOADEDV]] to float
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <6 x float> poison, float [[CONV]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <6 x float> [[SPLAT_SPLATINSERT]], <6 x float> poison, <6 x i32> zeroinitializer
// CHECK-NEXT: store <6 x float> [[SPLAT_SPLAT]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ExplicitBoolToFloatCastThenSplat(bool Value) {
float3x2 M = (float) Value;
}
// CHECK-LABEL: define hidden void @_Z32ImplicitFloatToBoolCastThenSplatf(
// CHECK-SAME: float noundef nofpclass(nan inf) [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca float, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [3 x <2 x i32>], align 4
// CHECK-NEXT: store float [[VALUE]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load float, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TOBOOL:%.*]] = fcmp reassoc nnan ninf nsz arcp afn une float [[TMP0]], 0.000000e+00
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <6 x i1> poison, i1 [[TOBOOL]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <6 x i1> [[SPLAT_SPLATINSERT]], <6 x i1> poison, <6 x i32> zeroinitializer
// CHECK-NEXT: [[TMP1:%.*]] = zext <6 x i1> [[SPLAT_SPLAT]] to <6 x i32>
// CHECK-NEXT: store <6 x i32> [[TMP1]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ImplicitFloatToBoolCastThenSplat(float Value) {
bool2x3 M = Value;
}
// CHECK-LABEL: define hidden void @_Z32ImplicitBoolToFloatCastThenSplatb(
// CHECK-SAME: i1 noundef [[VALUE:%.*]]) #[[ATTR0]] {
// CHECK-NEXT: [[ENTRY:.*:]]
// CHECK-NEXT: %[[#C_ENTRY:]] = call token @llvm.experimental.convergence.entry()
// CHECK-NEXT: [[VALUE_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[M:%.*]] = alloca [2 x <3 x float>], align 4
// CHECK-NEXT: [[STOREDV:%.*]] = zext i1 [[VALUE]] to i32
// CHECK-NEXT: store i32 [[STOREDV]], ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[VALUE_ADDR]], align 4
// CHECK-NEXT: [[LOADEDV:%.*]] = icmp ne i32 [[TMP0]], 0
// CHECK-NEXT: [[CONV:%.*]] = uitofp i1 [[LOADEDV]] to float
// CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <6 x float> poison, float [[CONV]], i64 0
// CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <6 x float> [[SPLAT_SPLATINSERT]], <6 x float> poison, <6 x i32> zeroinitializer
// CHECK-NEXT: store <6 x float> [[SPLAT_SPLAT]], ptr [[M]], align 4
// CHECK-NEXT: ret void
//
void ImplicitBoolToFloatCastThenSplat(bool Value) {
float3x2 M = Value;
}
Reference in new issue View Git Blame Copy Permalink