LGTM
http://codereview.chromium.org/6910021/diff/1/src/ia32/lithium-codegen-ia32.cc File src/ia32/lithium-codegen-ia32.cc (right): http://codereview.chromium.org/6910021/diff/1/src/ia32/lithium-codegen-ia32.cc#newcode2721 src/ia32/lithium-codegen-ia32.cc:2721: __ pxor(scratch, scratch); Change all pxor to xorps as well (I think this is the only one in this file, and there is one in full-codegen-ia32.cc too). The pxor uses integer arithmetic, and it introduces a 1-2 cycle latency when the next instruction is a double instruction (and all our XMM operations are double operations). http://codereview.chromium.org/6910021/ -- v8-dev mailing list [email protected] http://groups.google.com/group/v8-dev
