[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

diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
index 362952f..a699cd3 100644 (file)
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
@@ -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

diff --git a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
index 683b3e3..5f89da3 100644 (file)
--- a/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
+++ b/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
@@ -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);

diff --git a/llvm/test/CodeGen/AMDGPU/amdpal-elf.ll b/llvm/test/CodeGen/AMDGPU/amdpal-elf.ll
new file mode 100644 (file)
index 0000000..412815f
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/amdpal-elf.ll
@@ -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
+}