Math trig intrinsics and compiler options
gustav trede
gustav.trede at gmail.com
Wed Jul 15 05:43:52 PDT 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 :
Is it known what specific bugs or problems that is the cause ?
I would like to be able to check if the problems are gone in newer compiler
versions so targeted compiler flags can be added to make files.
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)
--
regards
gustav trede
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.openjdk.java.net/pipermail/hotspot-dev/attachments/20090715/57f927af/attachment.html
More information about the hotspot-dev
mailing list