AMDGPU: Redefine clamp node as clamp 0.0-1.0
Change implementation to use max instead of add.
min/max/med3 do not flush denormals regardless of the mode,
so it is OK to use it whether or not they are enabled.
Also allow using clamp with f16, and use knowledge
of dx10_clamp.
llvm-svn: 295788
diff --git a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
index 32b04fe..a719931 100644
--- a/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
@@ -42,7 +42,7 @@
// for SI has the unhelpful behavior that it unsets everything else if you
// disable it.
- SmallString<256> FullFS("+promote-alloca,+fp64-fp16-denormals,+load-store-opt,");
+ SmallString<256> FullFS("+promote-alloca,+fp64-fp16-denormals,+dx10-clamp,+load-store-opt,");
if (isAmdHsaOS()) // Turn on FlatForGlobal for HSA.
FullFS += "+flat-for-global,+unaligned-buffer-access,+trap-handler,";
@@ -89,6 +89,7 @@
FP32Denormals(false),
FP64FP16Denormals(false),
FPExceptions(false),
+ DX10Clamp(false),
FlatForGlobal(false),
UnalignedScratchAccess(false),
UnalignedBufferAccess(false),