aboutsummaryrefslogtreecommitdiffstats
path: root/utils/TableGen/StringToOffsetTable.h
diff options
context:
space:
mode:
authorPreston Gurd <preston.gurd@intel.com>2013-03-27 19:14:02 +0000
committerPreston Gurd <preston.gurd@intel.com>2013-03-27 19:14:02 +0000
commit1edadea42f6f5c393b4fdb9d7ce1cf7eb9c24ab4 (patch)
tree0703e20d41246fa36a72779d0d1ba5b58b6ee2d7 /utils/TableGen/StringToOffsetTable.h
parente915047fed99221afb8c540d8a7e81038a6483f1 (diff)
downloadexternal_llvm-1edadea42f6f5c393b4fdb9d7ce1cf7eb9c24ab4.zip
external_llvm-1edadea42f6f5c393b4fdb9d7ce1cf7eb9c24ab4.tar.gz
external_llvm-1edadea42f6f5c393b4fdb9d7ce1cf7eb9c24ab4.tar.bz2
For the current Atom processor, the fastest way to handle a call
indirect through a memory address is to load the memory address into a register and then call indirect through the register. This patch implements this improvement by modifying SelectionDAG to force a function address which is a memory reference to be loaded into a virtual register. Patch by Sriram Murali. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@178171 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'utils/TableGen/StringToOffsetTable.h')
0 files changed, 0 insertions, 0 deletions