]> git.ipfire.org Git - thirdparty/valgrind.git/commit
projects / thirdparty / valgrind.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: a35eac3) | patch
Implement the most important cases for amd64 direct-reload optimisation:
authorJulian Seward <jseward@acm.org>
Tue, 28 Mar 2017 14:57:17 +0000 (14:57 +0000)
committerJulian Seward <jseward@acm.org>
Tue, 28 Mar 2017 14:57:17 +0000 (14:57 +0000)
commit4a6236aaa1acfa44f2f17d331443ccdbf835ac35
tree1f26d16e178656ceb6f5a50c3e1e2deeec74aa5etree | snapshot
parenta35eac3bf9a502c242007b64c73a5f1acc28d8a5commit | diff
Implement the most important cases for amd64 direct-reload optimisation:

   cmpq $imm32, %vreg  ->  cmpq $imm32, (stack-slot-of-vreg)
   orq %vreg, %reg     ->  orq (stack-slot-of-vreg), %reg

This is in support of "Bug 375839 - Temporary storage exhausted, when long
sequence of vfmadd231ps instructions to be executed", and reduces code size by
around 3% in that case.

git-svn-id: svn://svn.valgrind.org/vex/trunk@3335
VEX/priv/host_amd64_defs.c diff | blob | blame | history
VEX/priv/host_amd64_defs.h diff | blob | blame | history
VEX/priv/main_main.c diff | blob | blame | history
Mirror of https://sourceware.org/git/valgrind.git