summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
diff options
context:
space:
mode:
authorMatt Arsenault <Matthew.Arsenault@amd.com>2016-02-12 02:40:47 +0000
committerMatt Arsenault <Matthew.Arsenault@amd.com>2016-02-12 02:40:47 +0000
commit24ee0785dd1bb1a2f5cb6cb398d697080a92803b (patch)
treec7ec2cfa1749a3f65c017c05897d620f2ae7207b /llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
parent9d14e4bb1523f9d29ea1f26af7d0294013682cea (diff)
downloadbcm5719-llvm-24ee0785dd1bb1a2f5cb6cb398d697080a92803b.tar.gz
bcm5719-llvm-24ee0785dd1bb1a2f5cb6cb398d697080a92803b.zip
AMDGPU: Set element_size in private resource descriptor
Introduce a subtarget feature for this, and leave the default with the current behavior which assumes up to 16-byte loads/stores can be used. The field also seems to have the ability to be set to 2 bytes, but I'm not sure what that would be used for. llvm-svn: 260651
Diffstat (limited to 'llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp')
-rw-r--r--llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp19
1 files changed, 19 insertions, 0 deletions
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
index 913f3f53ff1..2af7a2ccbfe 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
@@ -593,6 +593,20 @@ void AMDGPUAsmPrinter::EmitProgramInfoSI(const MachineFunction &MF,
}
}
+// This is supposed to be log2(Size)
+static amd_element_byte_size_t getElementByteSizeValue(unsigned Size) {
+ switch (Size) {
+ case 4:
+ return AMD_ELEMENT_4_BYTES;
+ case 8:
+ return AMD_ELEMENT_8_BYTES;
+ case 16:
+ return AMD_ELEMENT_16_BYTES;
+ default:
+ llvm_unreachable("invalid private_element_size");
+ }
+}
+
void AMDGPUAsmPrinter::EmitAmdKernelCodeT(const MachineFunction &MF,
const SIProgramInfo &KernelInfo) const {
const SIMachineFunctionInfo *MFI = MF.getInfo<SIMachineFunctionInfo>();
@@ -606,6 +620,11 @@ void AMDGPUAsmPrinter::EmitAmdKernelCodeT(const MachineFunction &MF,
(KernelInfo.ComputePGMRSrc2 << 32);
header.code_properties = AMD_CODE_PROPERTY_IS_PTR64;
+
+ AMD_HSA_BITS_SET(header.code_properties,
+ AMD_CODE_PROPERTY_PRIVATE_ELEMENT_SIZE,
+ getElementByteSizeValue(STM.getMaxPrivateElementSize()));
+
if (MFI->hasPrivateSegmentBuffer()) {
header.code_properties |=
AMD_CODE_PROPERTY_ENABLE_SGPR_PRIVATE_SEGMENT_BUFFER;
OpenPOWER on IntegriCloud