summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h')
-rw-r--r--llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h25
1 files changed, 24 insertions, 1 deletions
diff --git a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
index a59571c49c6..2ee19741acc 100644
--- a/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
+++ b/llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
@@ -16,6 +16,7 @@
#include "llvm/ADT/StringRef.h"
#include "llvm/IR/CallingConv.h"
#include "llvm/MC/MCInstrDesc.h"
+#include "llvm/Support/AMDHSAKernelDescriptor.h"
#include "llvm/Support/Compiler.h"
#include "llvm/Support/ErrorHandling.h"
#include <cstdint>
@@ -28,12 +29,12 @@ class Argument;
class FeatureBitset;
class Function;
class GlobalValue;
-class MachineMemOperand;
class MCContext;
class MCRegisterClass;
class MCRegisterInfo;
class MCSection;
class MCSubtargetInfo;
+class MachineMemOperand;
class Triple;
namespace AMDGPU {
@@ -138,6 +139,22 @@ unsigned getMinNumSGPRs(const FeatureBitset &Features, unsigned WavesPerEU);
unsigned getMaxNumSGPRs(const FeatureBitset &Features, unsigned WavesPerEU,
bool Addressable);
+/// \returns Number of extra SGPRs implicitly required by given subtarget \p
+/// Features when the given special registers are used.
+unsigned getNumExtraSGPRs(const FeatureBitset &Features, bool VCCUsed,
+ bool FlatScrUsed, bool XNACKUsed);
+
+/// \returns Number of extra SGPRs implicitly required by given subtarget \p
+/// Features when the given special registers are used. XNACK is inferred from
+/// \p Features.
+unsigned getNumExtraSGPRs(const FeatureBitset &Features, bool VCCUsed,
+ bool FlatScrUsed);
+
+/// \returns Number of SGPR blocks needed for given subtarget \p Features when
+/// \p NumSGPRs are used. \p NumSGPRs should already include any special
+/// register counts.
+unsigned getNumSGPRBlocks(const FeatureBitset &Features, unsigned NumSGPRs);
+
/// \returns VGPR allocation granularity for given subtarget \p Features.
unsigned getVGPRAllocGranule(const FeatureBitset &Features);
@@ -158,6 +175,10 @@ unsigned getMinNumVGPRs(const FeatureBitset &Features, unsigned WavesPerEU);
/// execution unit requirement for given subtarget \p Features.
unsigned getMaxNumVGPRs(const FeatureBitset &Features, unsigned WavesPerEU);
+/// \returns Number of VGPR blocks needed for given subtarget \p Features when
+/// \p NumVGPRs are used.
+unsigned getNumVGPRBlocks(const FeatureBitset &Features, unsigned NumSGPRs);
+
} // end namespace IsaInfo
LLVM_READONLY
@@ -203,6 +224,8 @@ int getMCOpcode(uint16_t Opcode, unsigned Gen);
void initDefaultAMDKernelCodeT(amd_kernel_code_t &Header,
const FeatureBitset &Features);
+amdhsa::kernel_descriptor_t getDefaultAmdhsaKernelDescriptor();
+
bool isGroupSegment(const GlobalValue *GV);
bool isGlobalSegment(const GlobalValue *GV);
bool isReadOnlySegment(const GlobalValue *GV);
OpenPOWER on IntegriCloud