From: Richard Sandiford Date: Tue, 10 Sep 2013 12:22:45 +0000 (+0000) Subject: [SystemZ] Update README. X-Git-Url: http://demsky.eecs.uci.edu/git/?a=commitdiff_plain;h=4c708e586eecb039811fdd54a8846002324936b2;p=oota-llvm.git [SystemZ] Update README. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190404 91177308-0d34-0410-b5e6-96231b3b80d8 --- diff --git a/lib/Target/SystemZ/README.txt b/lib/Target/SystemZ/README.txt index d5361fb658c..afa6cf090d0 100644 --- a/lib/Target/SystemZ/README.txt +++ b/lib/Target/SystemZ/README.txt @@ -58,14 +58,11 @@ condition codes. For example, we could use LCDFR instead of LCDBR. -- -We don't optimize block memory operations, except using single MVCs -for memcpy and single CLCs for memcmp. +We only use MVC, XC and CLC for constant-length block operations. +We could extend them to variable-length operations too, +using EXECUTE RELATIVE LONG. -It's definitely worth using things like NC, XC and OC with -constant lengths. MVCIN may be worthwhile too. - -We should probably implement general memcpy using MVC with EXECUTE. -Likewise memcmp and CLC. MVCLE and CLCLE could be useful too. +MVCIN, MVCLE and CLCLE may be worthwhile too. -- @@ -93,8 +90,7 @@ We don't use the halfword forms of LOAD REVERSED and STORE REVERSED -- -We could take advantage of the various ... UNDER MASK instructions, -such as ICM and STCM. +We don't use ICM or STCM. --