bcm5719-llvm - Project Ortega BCM5719 LLVM

	Commit message (Collapse)	Author	Age	Files	Lines
*	[AMDGPU] Fix SGPR fixing through SCC chaining	Michael Liao	2019-03-15	1	-0/+14
\| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \| \|	Summary: - During the fixing of SGPR copying from VGPR, ensure users of SCC is properly propagated, i.e. * only propagate through live def of SCC, * skip the SCC-def inst itself, and * stop the propagation on the other SCC-def inst after checking its SCC-use first. Subscribers: arsenm, kzhuravl, jvesely, wdng, nhaehnle, yaxunl, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D59362 llvm-svn: 356258
*	AMDGPU: Use gfx9 carry-less add/sub instructions	Matt Arsenault	2017-11-30	1	-0/+1
\| \| \| \|	llvm-svn: 319491
*	[AMDGPU] New 64 bit div/rem expansion	Stanislav Mekhanoshin	2017-10-06	1	-66/+12
\| \| \| \| \| \| \| \| \| \| \|	Old expansion was 20 VGPRs, 78 SGPRs and ~380 instructions. This expansion is 11 VGPRs, 12 SGPRs and ~120 instructions. Passes OpenCL conformance test_integer_ops quick_[u]long_math Differential Revision: https://reviews.llvm.org/D38607 llvm-svn: 315081
*	AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel	Matt Arsenault	2017-03-21	1	-6/+6
\| \| \| \| \| \| \| \| \| \| \| \|	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
*	Enable FeatureFlatForGlobal on Volcanic Islands	Matt Arsenault	2017-01-24	1	-1/+1
\| \| \| \| \| \| \| \| \| \| \|	This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
*	AMDGPU: Fix high bits after division optimization	Matt Arsenault	2016-05-21	1	-9/+9
\| \| \| \| \| \| \|	This is essentially doing a 24-bit signed division with FP. We need to truncate to the N bit result. llvm-svn: 270305
*	R600 -> AMDGPU rename	Tom Stellard	2015-06-13	1	-0/+223
	llvm-svn: 239657