AMDGPU: Don't use struct type for argument layout
This was introducing unnecessary padding after the explicit
arguments, depending on the alignment of the total struct type.
Also has the side effect of avoiding creating an extra GEP for
the offset from the base kernel argument to the explicit kernel
argument offset.
llvm-svn: 335999
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
index 9c8b82c..d21301a 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
@@ -862,8 +862,9 @@
return getGeneration() >= AMDGPUSubtarget::VOLCANIC_ISLANDS;
}
+ uint64_t getExplicitKernArgSize(const Function &F) const;
unsigned getKernArgSegmentSize(const Function &F,
- unsigned ExplictArgBytes) const;
+ int64_t ExplicitArgBytes = -1) const;
/// Return the maximum number of waves per SIMD for kernels using \p SGPRs
/// SGPRs