summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Object/IRObjectFile.cpp
diff options
context:
space:
mode:
authorNicolai Haehnle <nhaehnle@gmail.com>2016-04-22 04:04:08 +0000
committerNicolai Haehnle <nhaehnle@gmail.com>2016-04-22 04:04:08 +0000
commitb0c97487094ce0fd14ec4516a382b449a5631bbf (patch)
tree146a88e308ad355886e65ef63de1031dcfff33ba /llvm/lib/Object/IRObjectFile.cpp
parent5dff95c04de0d096563462530160fd5fc221fd8f (diff)
downloadbcm5719-llvm-b0c97487094ce0fd14ec4516a382b449a5631bbf.tar.gz
bcm5719-llvm-b0c97487094ce0fd14ec4516a382b449a5631bbf.zip
AMDGPU/SI: add llvm.amdgcn.ps.live intrinsic
Summary: This intrinsic returns true if the current thread belongs to a live pixel and false if it belongs to a pixel that we are executing only for derivative computation. It will be used by Mesa to implement gl_HelperInvocation. Note that for pixels that are killed during the shader, this implementation also returns true, but it doesn't matter because those pixels are always disabled in the EXEC mask. This unearthed a corner case in the instruction verifier, which complained about a v_cndmask 0, 1, exec, exec<imp-use> instruction. That's stupid but correct code, so make the verifier accept it as such. Reviewers: arsenm, tstellarAMD Subscribers: arsenm, llvm-commits Differential Revision: http://reviews.llvm.org/D19191 llvm-svn: 267102
Diffstat (limited to 'llvm/lib/Object/IRObjectFile.cpp')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud