maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[OpenCL] Respect calling convention for builtin 

`__translate_sampler_initializer` has a calling convention of
`spir_func`, but clang generated calls to it using the default CC.

Instruction Combining was lowering these mismatching calling conventions
to `store i1* undef` which itself was subsequently lowered to a trap
instruction by simplifyCFG resulting in runtime `SIGILL`

There are arguably two bugs here: but whether there's any wisdom in
converting an obviously invalid call into a runtime crash over aborting
with a sensible error message will require further discussion. So for
now it's enough to set the right calling convention on the runtime
helper.

Reviewed By: svenh, bader

Differential Revision: https://reviews.llvm.org/D98411
This commit is contained in:
Luke Drummond 2021-03-10 18:14:42 +00:00
parent da408d98d7
commit fcfd3fda71
2 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
clang/lib/CodeGen/CodeGenModule.cpp
View File

@ -6258,15 +6258,17 @@ llvm::SanitizerStatReport &CodeGenModule::getSanStats() {
return *SanStats;
}
llvm::Value *
CodeGenModule::createOpenCLIntToSamplerConversion(const Expr *E,
CodeGenFunction &CGF) {
llvm::Constant *C = ConstantEmitter(CGF).emitAbstract(E, E->getType());
auto SamplerT = getOpenCLRuntime().getSamplerType(E->getType().getTypePtr());
auto FTy = llvm::FunctionType::get(SamplerT, {C->getType()}, false);
return CGF.Builder.CreateCall(CreateRuntimeFunction(FTy,
"__translate_sampler_initializer"),
{C});
auto *SamplerT = getOpenCLRuntime().getSamplerType(E->getType().getTypePtr());
auto *FTy = llvm::FunctionType::get(SamplerT, {C->getType()}, false);
auto *Call = CGF.Builder.CreateCall(
CreateRuntimeFunction(FTy, "__translate_sampler_initializer"), {C});
Call->setCallingConv(Call->getCalledFunction()->getCallingConv());
return Call;
}
CharUnits CodeGenModule::getNaturalPointeeTypeAlignment(

12
clang/test/CodeGenOpenCL/sampler.cl
View File

@ -39,7 +39,7 @@ kernel void foo(sampler_t smp_par) {
// Case 2b
sampler_t smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_NEAREST;
// CHECK: [[smp_ptr:%[A-Za-z0-9_\.]+]] = alloca %opencl.sampler_t addrspace(2)*
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 19)
// CHECK: [[SAMP:%[0-9]+]] = call spir_func %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 19)
// CHECK: store %opencl.sampler_t addrspace(2)* [[SAMP]], %opencl.sampler_t addrspace(2)** [[smp_ptr]]
// Case 1b
@ -56,12 +56,12 @@ kernel void foo(sampler_t smp_par) {
// Case 1a/2a
fnc4smp(glb_smp);
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: [[SAMP:%[0-9]+]] = call spir_func %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: call spir_func void [[FUNCNAME]](%opencl.sampler_t addrspace(2)* [[SAMP]])
// Case 1a/2c
fnc4smp(glb_smp_const);
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: [[SAMP:%[0-9]+]] = call spir_func %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: call spir_func void [[FUNCNAME]](%opencl.sampler_t addrspace(2)* [[SAMP]])
// Case 1c
@ -70,12 +70,12 @@ kernel void foo(sampler_t smp_par) {
// CHECK: call spir_func void [[FUNCNAME]](%opencl.sampler_t addrspace(2)* [[SAMP]])
fnc4smp(5);
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 5)
// CHECK: [[SAMP:%[0-9]+]] = call spir_func %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 5)
// CHECK: call spir_func void [[FUNCNAME]](%opencl.sampler_t addrspace(2)* [[SAMP]])
const sampler_t const_smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;
fnc4smp(const_smp);
// CHECK: [[CONST_SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: [[CONST_SAMP:%[0-9]+]] = call spir_func %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: store %opencl.sampler_t addrspace(2)* [[CONST_SAMP]], %opencl.sampler_t addrspace(2)** [[CONST_SMP_PTR:%[a-zA-Z0-9]+]]
fnc4smp(const_smp);
// CHECK: [[SAMP:%[0-9]+]] = load %opencl.sampler_t addrspace(2)*, %opencl.sampler_t addrspace(2)** [[CONST_SMP_PTR]]
@ -83,7 +83,7 @@ kernel void foo(sampler_t smp_par) {
constant sampler_t constant_smp = CLK_ADDRESS_CLAMP_TO_EDGE | CLK_NORMALIZED_COORDS_TRUE | CLK_FILTER_LINEAR;
fnc4smp(constant_smp);
// CHECK: [[SAMP:%[0-9]+]] = call %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: [[SAMP:%[0-9]+]] = call spir_func %opencl.sampler_t addrspace(2)* @__translate_sampler_initializer(i32 35)
// CHECK: call spir_func void [[FUNCNAME]](%opencl.sampler_t addrspace(2)* [[SAMP]])
// TODO: enable sampler initialization with non-constant integer.