Commit Graph

8 Commits

Author SHA1 Message Date
Tom Stellard
98ef447825 AMDGPU/SI: Detect uniform branches and emit s_cbranch instructions
Reviewers: arsenm

Subscribers: mareko, MatzeB, qcolombet, arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D16603

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@260765 91177308-0d34-0410-b5e6-96231b3b80d8
2016-02-12 23:45:29 +00:00
Matt Arsenault
5911f21abb AMDGPU: Fix not handling new workitem intrinsics in DivergenceAnalysis
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@260491 91177308-0d34-0410-b5e6-96231b3b80d8
2016-02-11 05:32:51 +00:00
Matt Arsenault
1e79dfc2ee AMDGPU: Fix getRegisterBitWidth for vectors
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@256362 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-24 05:14:55 +00:00
Tom Stellard
688dd45c47 AMDGPU/SI: Fix implemenation of isSourceOfDivergence() for graphics shaders
Summary:
The analysis of shader inputs was completely wrong.  We were passing the
wrong index to AttributeSet::hasAttribute() and the logic for which
inputs where in SGPRs was wrong too.

Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15608

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@256082 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-19 02:54:15 +00:00
Matt Arsenault
b11dd50509 AMDGPU: Override getCFInstrCost
The default cost was 0 with the assumption that it is predictable.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255796 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-16 18:37:19 +00:00
Tom Stellard
6e2ee6c7ea AMDGPU/SI: Implement AMDGPUTargetTransformInfo::isSourceOfDivergence()
Reviewers: arsenm

Subscribers: arsenm, llvm-commits

Differential Revision: http://reviews.llvm.org/D15476

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@255661 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-15 18:04:38 +00:00
Matt Arsenault
2320de6adb AMDGPU: Report extractelement as free in cost model
The cost for scalarized operations is computed as N * (scalar operation
cost + 1 extractelement + 1 insertelement). This partially fixes
inflating the cost of scalarized operations since every operation is
scalarized and free. I don't think we want any cost asociated with
scalarization, but for now insertelement is still counted. I'm not sure
if we should pretend that insertelement is also free, or add a way
to compute a custom scalarization cost.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@254438 91177308-0d34-0410-b5e6-96231b3b80d8
2015-12-01 19:08:39 +00:00
Tom Stellard
953c681473 R600 -> AMDGPU rename
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@239657 91177308-0d34-0410-b5e6-96231b3b80d8
2015-06-13 03:28:10 +00:00