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

AMDGPU: Add support for R_AMDGPU_REL32 relocations 

Reviewers: arsenm, kzhuravl, rafael

Subscribers: arsenm, llvm-commits, kzhuravl

Differential Revision: http://reviews.llvm.org/D21401

llvm-svn: 273168
This commit is contained in:
Tom Stellard 2016-06-20 17:33:43 +00:00
parent 9935766458
commit 5350894265
4 changed files with 20 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUELFObjectWriter.cpp
View File

@ -45,6 +45,12 @@ unsigned AMDGPUELFObjectWriter::getRelocType(MCContext &Ctx,
if (Target.getSymA()->getSymbol().getName() == "SCRATCH_RSRC_DWORD1")
return ELF::R_AMDGPU_ABS32_HI;
switch (Fixup.getKind()) {
default: break;
case FK_PCRel_4:
return ELF::R_AMDGPU_REL32;
}
llvm_unreachable("unhandled relocation type");
}

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

@ -1420,7 +1420,8 @@ SDValue SITargetLowering::LowerGlobalAddress(AMDGPUMachineFunction *MFI,
SelectionDAG &DAG) const {
GlobalAddressSDNode *GSD = cast<GlobalAddressSDNode>(Op);
if (GSD->getAddressSpace() != AMDGPUAS::CONSTANT_ADDRESS)
if (GSD->getAddressSpace() != AMDGPUAS::CONSTANT_ADDRESS &&
GSD->getAddressSpace() != AMDGPUAS::GLOBAL_ADDRESS)
return AMDGPUTargetLowering::LowerGlobalAddress(MFI, Op, DAG);
SDLoc DL(GSD);

17
llvm/test/CodeGen/AMDGPU/global-zero-initializer.ll
View File

@ -1,12 +1,17 @@
; RUN: not llc -march=amdgcn -mcpu=SI < %s 2>&1 | FileCheck %s
; RUN: not llc -march=amdgcn -mcpu=tonga < %s 2>&1 | FileCheck %s
; RUN: llc -march=amdgcn -mcpu=SI < %s 2>&1 | FileCheck %s
; RUN: llc -march=amdgcn -mcpu=tonga < %s 2>&1 | FileCheck %s
; CHECK: in function load_init_global_global{{.*}}: unsupported initializer for address space
@lds = addrspace(1) global [256 x i32] zeroinitializer
; CHECK: {{^}}load_init_global_global:
; CHECK: s_getpc_b64 s{{\[}}[[PC_LO:[0-9]+]]:[[PC_HI:[0-9]+]]{{\]}}
; CHECK: s_add_u32 s[[ADDR_LO:[0-9]+]], s[[PC_LO]], global+4
; CHECK: s_addc_u32 s5, s[[PC_HI]], 0
; CHECK: buffer_load_dword v{{[0-9]+}}, off, s{{\[}}[[ADDR_LO]]:7], 0 offset:40
; CHECK: global:
; CHECK: .zero 1024
@global = addrspace(1) global [256 x i32] zeroinitializer
define void @load_init_global_global(i32 addrspace(1)* %out, i1 %p) {
%gep = getelementptr [256 x i32], [256 x i32] addrspace(1)* @lds, i32 0, i32 10
%gep = getelementptr [256 x i32], [256 x i32] addrspace(1)* @global, i32 0, i32 10
%ld = load i32, i32 addrspace(1)* %gep
store i32 %ld, i32 addrspace(1)* %out
ret void

1
llvm/test/CodeGen/AMDGPU/wqm.ll
View File

@ -40,6 +40,7 @@ main_body:
;CHECK: s_and_b64 exec, exec, [[ORIG]]
;CHECK: store
;CHECK-NOT: exec
;CHECK: .size test3
define amdgpu_ps <4 x float> @test3(<8 x i32> inreg %rsrc, <4 x i32> inreg %sampler, float addrspace(1)* inreg %ptr, <4 x i32> %c) {
main_body:
%tex = call <4 x float> @llvm.SI.image.sample.v4i32(<4 x i32> %c, <8 x i32> %rsrc, <4 x i32> %sampler, i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0)