bcm5719-llvm - Project Ortega BCM5719 LLVM

	Commit message (Collapse)	Author	Age	Files	Lines
*	[AMDGPU] Always use rcp + mul with fast math	Stanislav Mekhanoshin	2017-07-06	1	-28/+10
\| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \|	Regardless of relaxation options such as -cl-fast-relaxed-math we are producing rather long code for fdiv via amdgcn_fdiv_fast intrinsic. This intrinsic is used to replace fdiv with 2.5ulp metadata and does not handle denormals, thus believed to be fast. An fdiv instruction can also have fast math flag either by itself or together with fpmath metadata. Clang used with a relaxation flag always produces both metadata and fast flag: %div = fdiv fast float %v, %0, !fpmath !12 !12 = !{float 2.500000e+00} Current implementation ignores fast flag and favors metadata. An instruction with just fast flag would be lowered to a fastest rcp + mul, but that never happen on practice because of described mutual clang and BE behavior. This change allows an "fdiv fast" to be always lowered as rcp + mul. Differential Revision: https://reviews.llvm.org/D34844 llvm-svn: 307308
*	AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel	Matt Arsenault	2017-03-21	1	-8/+8
\| \| \| \| \| \| \| \| \| \| \| \|	Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
*	[AMDGPU] Promote uniform i16 ops to i32 ops for targets that have 16 bit ↵	Konstantin Zhuravlyov	2016-09-28	1	-0/+246
	instructions Differential Revision: https://reviews.llvm.org/D24125 llvm-svn: 282624