Math trig intrinsics and compiler options (original) (raw)

gustav trede gustav.trede at gmail.com
Wed Jul 15 11:52:25 UTC 2009


Hello,

Azeem Jiva told me an easy way to improve trig performance. Changing the intrinsics to use an existing but faster path gives me a boost of roughly 40% for the Math cos and sin on solaris x64.

library_call.cpp

bool LibraryCallKit::inline_math_native(vmIntrinsics::ID id) { switch (id) {

case vmIntrinsics::_dcos: return Matcher::has_match_rule(Op_CosD) ? runtime_math(OptoRuntime::Math_D_D_Type(), CAST_FROM_FN_PTR(address, SharedRuntime::dcos), "COS") : false; case vmIntrinsics::_dsin: return Matcher::has_match_rule(Op_SinD) ? runtime_math(OptoRuntime::Math_D_D_Type(), CAST_FROM_FN_PTR(address, SharedRuntime::dsin), "SIN") : false; case vmIntrinsics::_dtan: return Matcher::has_match_rule(Op_TanD) ? runtime_math(OptoRuntime::Math_D_D_Type(), CAST_FROM_FN_PTR(address, SharedRuntime::dtan), "TAN") : false; case vmIntrinsics::_dlog: return Matcher::has_match_rule(Op_LogD) ? runtime_math(OptoRuntime::Math_D_D_Type(), CAST_FROM_FN_PTR(address, SharedRuntime::dlog), "LOG") : false; case vmIntrinsics::_dlog10: return Matcher::has_match_rule(Op_Log10D) ? runtime_math(OptoRuntime::Math_D_D_Type(), CAST_FROM_FN_PTR(address, SharedRuntime::dlog10), "LOG10") : false;

Is there any potential problem with such a patch ?

Compiler flags is another area of interest. Both linux and windows platforms seems to turn off optimizations for sharedRuntimeTrig.cpp : sharedRuntimeTrig.cpp has #ifdef WIN32

pragma optimize ( "", off )

#endif

hotspot/make/linux/makefiles/i486.make:# The copied fdlibm routines in sharedRuntimeTrig.o must not be optimized hotspot/make/linux/makefiles/i486.make:OPT_CFLAGS/sharedRuntimeTrig.o = $(OPT_CFLAGS/NOOPT) hotspot/make/linux/makefiles/amd64.make:# The copied fdlibm routines in sharedRuntimeTrig.o must not be optimized hotspot/make/linux/makefiles/amd64.make:OPT_CFLAGS/sharedRuntimeTrig.o = $(OPT_CFLAGS/NOOPT)

Do we know if the situation has changed for these platforms ?

-- regards gustav trede -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://mail.openjdk.java.net/pipermail/core-libs-dev/attachments/20090715/98e80f89/attachment.html>



More information about the core-libs-dev mailing list