bcm5719-llvm - Project Ortega BCM5719 LLVM

	Commit message (Collapse)	Author	Age	Files	Lines
*	AMDGPU: Form more FMAs if fusion is allowed	Matt Arsenault	2016-12-22	1	-420/+0
\| \| \| \| \| \| \|	Extend the existing fadd/fsub->fmad combines to produce FMA if allowed. llvm-svn: 290311
*	AMDGPU: Enable some f32 fadd/fsub combines for f16	Matt Arsenault	2016-12-22	1	-1/+194
\| \| \| \|	llvm-svn: 290308
*	AMDGPU: Run fp combine tests on VI	Matt Arsenault	2016-12-20	1	-41/+53
\| \| \| \|	llvm-svn: 290192
*	AMDGPU: Add volatile to test loads and stores	Matt Arsenault	2016-04-12	1	-25/+25
\| \| \| \| \| \| \| \|	When the memory vectorizer is enabled, these tests break. These tests don't really care about the memory instructions, and it's easier to write check lines with the unmerged loads. llvm-svn: 266071
*	AMDGPU: Remove some old intrinsic uses from tests	Matt Arsenault	2016-02-11	1	-11/+11
\| \| \| \|	llvm-svn: 260493
*	AMDGPU/SI: Select mad patterns to v_mac_f32	Tom Stellard	2015-07-13	1	-3/+3
\| \| \| \| \| \| \| \| \|	The two-address instruction pass will convert these back to v_mad_f32 if necessary. Differential Revision: http://reviews.llvm.org/D11060 llvm-svn: 242038
*	R600 -> AMDGPU rename	Tom Stellard	2015-06-13	1	-0/+215
	llvm-svn: 239657