Revert "AMDGPU: Fix handling of alignment padding in DAG argument lowering"

This reverts commit r337021.

WARNING: MemorySanitizer: use-of-uninitialized-value
    #0 0x1415cd65 in void write_signed<long>(llvm::raw_ostream&, long, unsigned long, llvm::IntegerStyle) /code/llvm-project/llvm/lib/Support/NativeFormatting.cpp:95:7
    #1 0x1415c900 in llvm::write_integer(llvm::raw_ostream&, long, unsigned long, llvm::IntegerStyle) /code/llvm-project/llvm/lib/Support/NativeFormatting.cpp:121:3
    #2 0x1472357f in llvm::raw_ostream::operator<<(long) /code/llvm-project/llvm/lib/Support/raw_ostream.cpp:117:3
    #3 0x13bb9d4 in llvm::raw_ostream::operator<<(int) /code/llvm-project/llvm/include/llvm/Support/raw_ostream.h:210:18
    #4 0x3c2bc18 in void printField<unsigned int, &(amd_kernel_code_s::amd_kernel_code_version_major)>(llvm::StringRef, amd_kernel_code_s const&, llvm::raw_ostream&) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:78:23
    #5 0x3c250ba in llvm::printAmdKernelCodeField(amd_kernel_code_s const&, int, llvm::raw_ostream&) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:104:5
    #6 0x3c27ca3 in llvm::dumpAmdKernelCode(amd_kernel_code_s const*, llvm::raw_ostream&, char const*) /code/llvm-project/llvm/lib/Target/AMDGPU/Utils/AMDKernelCodeTUtils.cpp:113:5
    #7 0x3a46e6c in llvm::AMDGPUTargetAsmStreamer::EmitAMDKernelCodeT(amd_kernel_code_s const&) /code/llvm-project/llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp:161:3
    #8 0xd371e4 in llvm::AMDGPUAsmPrinter::EmitFunctionBodyStart() /code/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp:204:26

[...]

Uninitialized value was created by an allocation of 'KernelCode' in the stack frame of function '_ZN4llvm16AMDGPUAsmPrinter21EmitFunctionBodyStartEv'
    #0 0xd36650 in llvm::AMDGPUAsmPrinter::EmitFunctionBodyStart() /code/llvm-project/llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp:192

llvm-svn: 337079

1 files changed, 14 insertions, 14 deletions

diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
index 62310973365..d9806d6133c 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -51,7 +51,7 @@ public:
   enum Generation {
     R600 = 0,
     R700 = 1,
-    EVERGREEN = 2,
+    EVERGREEN = 2, 
     NORTHERN_ISLANDS = 3,
     SOUTHERN_ISLANDS = 4,
     SEA_ISLANDS = 5,
@@ -82,7 +82,7 @@ public:
 
   static const AMDGPUSubtarget &get(const MachineFunction &MF);
   static const AMDGPUSubtarget &get(const TargetMachine &TM,
-                                    const Function &F);
+                                          const Function &F);
 
   /// \returns Default range flat work group size for a calling convention.
   std::pair<unsigned, unsigned> getDefaultFlatWorkGroupSize(CallingConv::ID CC) const;
@@ -231,18 +231,6 @@ public:
   /// Creates value range metadata on an workitemid.* inrinsic call or load.
   bool makeLIDRangeMetadata(Instruction *I) const;
 
-  /// \returns Number of bytes of arguments that are passed to a shader or
-  /// kernel in addition to the explicit ones declared for the function.
-  unsigned getImplicitArgNumBytes(const Function &F) const {
-    if (isMesaKernel(F))
-      return 16;
-    return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", 0);
-  }
-  uint64_t getExplicitKernArgSize(const Function &F,
-                                  unsigned &MaxAlign) const;
-  unsigned getKernArgSegmentSize(const Function &F,
-                                 unsigned &MaxAlign) const;
-
   virtual ~AMDGPUSubtarget() {}
 };
 
@@ -681,6 +669,14 @@ public:
     return D16PreservesUnusedBits;
   }
 
+  /// \returns Number of bytes of arguments that are passed to a shader or
+  /// kernel in addition to the explicit ones declared for the function.
+  unsigned getImplicitArgNumBytes(const Function &F) const {
+    if (isMesaKernel(F))
+      return 16;
+    return AMDGPU::getIntegerAttribute(F, "amdgpu-implicitarg-num-bytes", 0);
+  }
+
   // Scratch is allocated in 256 dword per wave blocks for the entire
   // wavefront. When viewed from the perspecive of an arbitrary workitem, this
   // is 4-byte aligned.
@@ -829,6 +825,10 @@ public:
     return getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS;
   }
 
+  uint64_t getExplicitKernArgSize(const Function &F) const;
+  unsigned getKernArgSegmentSize(const Function &F,
+                                 int64_t ExplicitArgBytes = -1) const;
+
   /// Return the maximum number of waves per SIMD for kernels using \p SGPRs
   /// SGPRs
   unsigned getOccupancyWithNumSGPRs(unsigned SGPRs) const;