projects / oota-llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 445a12e) | patch
AMDGPU: Fix splitting SMRD with large offset
authorMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 28 Sep 2015 20:54:42 +0000 (20:54 +0000)
committerMatt Arsenault <Matthew.Arsenault@amd.com>
Mon, 28 Sep 2015 20:54:42 +0000 (20:54 +0000)
commit9ed2f311256b1acc4641c35930ca4a4afe28ea93
treef2776e42afc62d4bde1329637ad5a2872f76e698tree | snapshot
parent445a12ee1c5be3b2315c59561aa59db0e30c636bcommit | diff
AMDGPU: Fix splitting SMRD with large offset

The splitting of > 4 dword SMRD instructions
if using an offset in an SGPR instead of an immediate
was not setting the destination register,
resulting an an instruction missing an operand
which would assert later.

Test will be included in a following commit
which fixes a related issue.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@248739 91177308-0d34-0410-b5e6-96231b3b80d8
lib/Target/AMDGPU/SIInstrInfo.cpp diff | blob | history
C/C++ LLVM-based compilers that forbids OOTA behaviors