JDK-8152907 : Update for x86 tan and log10 in the math lib
  • Type: Bug
  • Component: hotspot
  • Sub-Component: compiler
  • Affected Version: 9
  • Priority: P3
  • Status: Resolved
  • Resolution: Fixed
  • OS: generic
  • CPU: x86
  • Submitted: 2016-03-28
  • Updated: 2025-01-21
  • Resolved: 2016-04-06
The Version table provides details related to the release that this issue/RFE will be addressed.

Unresolved : Release in which this issue/RFE will be addressed.
Resolved: Release in which this issue/RFE has been resolved.
Fixed : Release in which this issue/RFE has been fixed. The release containing this fix may be available for download as an Early Access Release or a General Availability Release.

To download the current JDK release, click here.
JDK 9
9 b120Fixed
Related Reports
Relates :  
JDK-8154473 - Update for CompilerDirectives to control stub generation and intrinsics
Relates :  
JDK-8348186 - C1: Purge fpu_stack_size infrastructure
Relates :  
CODETOOLS-7903094 - JMH: Replace Math.log with predictable code in samples
Relates :  
JDK-8143353 - update for x86 sin and cos in the math lib
Relates :  
JDK-8155864 - api/java_lang/Math/cos_cos6 and sin_sin6 fail
Relates :  
JDK-8160651 - StubRoutines::_dtan does not restore callee save register rbx
Description
This patch updates the tan and log10 intrinsics using Intel LIBM.
Also adds Compiler Directive approach to disable enable the intrinics.
Comments
URL: http://hg.openjdk.java.net/jdk9/jdk9/hotspot/rev/33f10a35ce20 User: lana Date: 2016-05-25 17:36:48 +0000
25-05-2016
URL: http://hg.openjdk.java.net/jdk9/hs-comp/hotspot/rev/33f10a35ce20 User: kvn Date: 2016-04-06 19:42:00 +0000
06-04-2016
Updated webrev: http://cr.openjdk.java.net/~vdeshpande/libm_tanlog10/8152907/webrev.02/
05-04-2016
Updated webrev: http://cr.openjdk.java.net/~vdeshpande/libm_tanlog10/8152907/webrev.01/
05-04-2016
Hi Vivek, I'm assigning this issue to you as you and Shravya have been working on it. Best regards, Zoltan
29-03-2016
I think for the saneness of the macroAssembler_libm_x86_*.cpp files we should put every intrinsic in its own file, like we did for macroAssembler_x86_sha.cpp. They are already too big: $ wc -l hotspot/src/cpu/x86/vm/macroAssembler_libm_x86_*.cpp 4571 hotspot/src/cpu/x86/vm/macroAssembler_libm_x86_32.cpp 3945 hotspot/src/cpu/x86/vm/macroAssembler_libm_x86_64.cpp
29-03-2016
webrev: http://cr.openjdk.java.net/~vdeshpande/libm_tanlog10/8152907/webrev.00/ Peformance gain: 64 bit tan ~7x, 32 bit tan ~4x 64 bit log10 ~75%, 32 bit log10 ~50% Code contributed by: Shravya Rukmannagari (shravya.rukmannagari@itel.com and Vivek Deshpande (vivek.r.deshpande@intel.com)
28-03-2016