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

[AMDGPU] Change enqueue kernel handle type 

Currently the handle type is a global pointer which holds 8 bytes.
We need a larger type which hold 16 bytes, therefore change it
to [i64 x 2].

Differential Revision: https://reviews.llvm.org/D48094

llvm-svn: 334625
This commit is contained in:
Yaxun Liu 2018-06-13 17:31:51 +00:00
parent 4bf9b5612a
commit fb17bf60dd
2 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/Target/AMDGPU/AMDGPUOpenCLEnqueuedBlockLowering.cpp
View File

@ -36,6 +36,7 @@
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/IR/Constants.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/Instructions.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/Module.h"
@ -116,7 +117,7 @@ bool AMDGPUOpenCLEnqueuedBlockLowering::runOnModule(Module &M) {
}
LLVM_DEBUG(dbgs() << "found enqueued kernel: " << F.getName() << '\n');
auto RuntimeHandle = (F.getName() + ".runtime_handle").str();
auto T = Type::getInt8Ty(C)->getPointerTo(AMDGPUAS::GLOBAL_ADDRESS);
auto T = ArrayType::get(Type::getInt64Ty(C), 2);
auto *GV = new GlobalVariable(
M, T,
/*IsConstant=*/false, GlobalValue::ExternalLinkage,

10
llvm/test/CodeGen/AMDGPU/enqueue-kernel.ll
View File

@ -1,9 +1,9 @@
; RUN: opt -data-layout=A5 -amdgpu-lower-enqueued-block -S < %s | FileCheck %s
; CHECK: @__test_block_invoke_kernel.runtime_handle = addrspace(1) global i8 addrspace(1)* null
; CHECK: @__test_block_invoke_2_kernel.runtime_handle = addrspace(1) global i8 addrspace(1)* null
; CHECK: @__amdgpu_enqueued_kernel.runtime_handle = addrspace(1) global i8 addrspace(1)* null
; CHECK: @__amdgpu_enqueued_kernel.1.runtime_handle = addrspace(1) global i8 addrspace(1)* null
; CHECK: @__test_block_invoke_kernel.runtime_handle = addrspace(1) global [2 x i64] zeroinitializer
; CHECK: @__test_block_invoke_2_kernel.runtime_handle = addrspace(1) global [2 x i64] zeroinitializer
; CHECK: @__amdgpu_enqueued_kernel.runtime_handle = addrspace(1) global [2 x i64] zeroinitializer
; CHECK: @__amdgpu_enqueued_kernel.1.runtime_handle = addrspace(1) global [2 x i64] zeroinitializer
%struct.ndrange_t = type { i32 }
%opencl.queue_t = type opaque
@ -84,7 +84,7 @@ entry:
; CHECK-LABEL: define amdgpu_kernel void @inlined_caller
; CHECK-SAME: #[[AT_CALLER]]
; CHECK-NOT: @__test_block_invoke_kernel
; CHECK: load i64, i64 addrspace(1)* bitcast (i8 addrspace(1)* addrspace(1)* @__test_block_invoke_kernel.runtime_handle to i64 addrspace(1)*)
; CHECK: load i64, i64 addrspace(1)* getelementptr inbounds ([2 x i64], [2 x i64] addrspace(1)* @__test_block_invoke_kernel.runtime_handle, i32 0, i32 0)
define amdgpu_kernel void @inlined_caller(i8 addrspace(1)* %a, i8 %b, i64 addrspace(1)* %c, i64 %d) local_unnamed_addr
!kernel_arg_addr_space !3 !kernel_arg_access_qual !4 !kernel_arg_type !5 !kernel_arg_base_type !5 !kernel_arg_type_qual !6 {
entry: