AMDGPU: Round up kernel argument allocation size
AFAIK the driver's allocation will actually have to round this
up anyway. It is useful to track the rounded up size, so that
the end of the kernel segment is known to be dereferencable so
a wider s_load_dword can be used for a short argument at the end
of the segment.
llvm-svn: 333456
diff --git a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
index 495a853..61b6cb3 100644
--- a/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIMachineFunctionInfo.cpp
@@ -71,8 +71,11 @@
if (F.hasFnAttribute("amdgpu-implicitarg-ptr"))
ImplicitArgPtr = true;
} else {
- if (F.hasFnAttribute("amdgpu-implicitarg-ptr"))
+ if (F.hasFnAttribute("amdgpu-implicitarg-ptr")) {
KernargSegmentPtr = true;
+ assert(MaxKernArgAlign == 0);
+ MaxKernArgAlign = ST.getAlignmentForImplicitArgPtr();
+ }
}
CallingConv::ID CC = F.getCallingConv();