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

[AMDGPU] Don't mark the .note section as ALLOC 

Marking a section as ALLOC tells the ELF loader to load the section into memory.
As we do not want to load the notes into VRAM, the flag should not be there.

On AMDHSA, .note is still marked as ALLOC, apparently this is currently
needed for OpenCL (see https://reviews.llvm.org/D74995).

Differential Revision: https://reviews.llvm.org/D76278
This commit is contained in:
Sebastian Neubauer 2020-03-17 13:14:24 +01:00
parent 8cb5663abd
commit 1de4e56933
3 changed files with 45 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
View File

@ -393,9 +393,9 @@ void AMDGPUTargetAsmStreamer::EmitAmdhsaKernelDescriptor(
// AMDGPUTargetELFStreamer
//===----------------------------------------------------------------------===//
AMDGPUTargetELFStreamer::AMDGPUTargetELFStreamer(
MCStreamer &S, const MCSubtargetInfo &STI)
: AMDGPUTargetStreamer(S), Streamer(S) {
AMDGPUTargetELFStreamer::AMDGPUTargetELFStreamer(MCStreamer &S,
const MCSubtargetInfo &STI)
: AMDGPUTargetStreamer(S), Streamer(S), Os(STI.getTargetTriple().getOS()) {
MCAssembler &MCA = getStreamer().getAssembler();
unsigned EFlags = MCA.getELFHeaderEFlags();
@ -438,9 +438,15 @@ void AMDGPUTargetELFStreamer::EmitNote(
auto NameSZ = Name.size() + 1;
unsigned NoteFlags = 0;
// TODO Apparently, this is currently needed for OpenCL as mentioned in
// https://reviews.llvm.org/D74995
if (Os == Triple::AMDHSA)
NoteFlags = ELF::SHF_ALLOC;
S.PushSection();
S.SwitchSection(Context.getELFSection(
ElfNote::SectionName, ELF::SHT_NOTE, ELF::SHF_ALLOC));
S.SwitchSection(
Context.getELFSection(ElfNote::SectionName, ELF::SHT_NOTE, NoteFlags));
S.emitInt32(NameSZ); // namesz
S.emitValue(DescSZ, 4); // descz
S.emitInt32(NoteType); // type

1
llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
View File

@ -133,6 +133,7 @@ public:
class AMDGPUTargetELFStreamer final : public AMDGPUTargetStreamer {
MCStreamer &Streamer;
Triple::OSType Os;
void EmitNote(StringRef Name, const MCExpr *DescSize, unsigned NoteType,
function_ref<void(MCELFStreamer &)> EmitDesc);

33
llvm/test/CodeGen/AMDGPU/amdpal-elf.ll Normal file
View File

@ -0,0 +1,33 @@
; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=kaveri -filetype=obj -mattr=-code-object-v3 | llvm-readobj -symbols -s -sd | FileCheck --check-prefix=ELF %s
; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=kaveri -mattr=-code-object-v3 | llvm-mc -filetype=obj -triple amdgcn--amdpal -mcpu=kaveri -mattr=-code-object-v3 | llvm-readobj -symbols -s -sd | FileCheck %s --check-prefix=ELF
; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=gfx1010 -mattr=+WavefrontSize32,-WavefrontSize64,-code-object-v3 | FileCheck --check-prefix=GFX10-W32 %s
; RUN: llc < %s -mtriple=amdgcn--amdpal -mcpu=gfx1010 -mattr=-WavefrontSize32,+WavefrontSize64,-code-object-v3 | FileCheck --check-prefix=GFX10-W64 %s
; ELF: Section {
; ELF: Name: .text
; ELF: Type: SHT_PROGBITS (0x1)
; ELF: Flags [ (0x6)
; ELF: SHF_ALLOC (0x2)
; ELF: SHF_EXECINSTR (0x4)
; ELF: }
; ELF: SHT_NOTE
; ELF: Flags [ (0x0)
; ELF: ]
; ELF: Symbol {
; ELF: Name: simple
; ELF: Size: 36
; ELF: Section: .text (0x2)
; ELF: }
; GFX10-W32: NumSGPRsForWavesPerEU: 4
; GFX10-W32: NumVGPRsForWavesPerEU: 3
; GFX10-W64: NumSGPRsForWavesPerEU: 2
; GFX10-W64: NumVGPRsForWavesPerEU: 3
define amdgpu_kernel void @simple(i32 addrspace(1)* %out) {
entry:
store i32 0, i32 addrspace(1)* %out
ret void
}