Mercurial > hg > graal-jvmci-8
diff src/cpu/x86/vm/macroAssembler_x86.cpp @ 17922:400709e275c1
8029302: Performance regression in Math.pow intrinsic
Summary: Added special case for x^y where y == 2
Reviewed-by: kvn
author | adlertz |
---|---|
date | Fri, 25 Apr 2014 12:48:34 +0200 |
parents | 526acaf3626f |
children | 78bbf4d43a14 |
line wrap: on
line diff
--- a/src/cpu/x86/vm/macroAssembler_x86.cpp Thu May 08 23:10:23 2014 -0700 +++ b/src/cpu/x86/vm/macroAssembler_x86.cpp Fri Apr 25 12:48:34 2014 +0200 @@ -3152,10 +3152,12 @@ // if fast computation is not possible, result is NaN. Requires // fallback from user of this macro. // increase precision for intermediate steps of the computation + BLOCK_COMMENT("fast_pow {"); increase_precision(); fyl2x(); // Stack: (Y*log2(X)) ... pow_exp_core_encoding(); // Stack: exp(X) ... restore_precision(); + BLOCK_COMMENT("} fast_pow"); } void MacroAssembler::fast_exp() {