On Thu, 24 Feb 2022 02:43:46 GMT, Vamsi Parasa <d...@openjdk.java.net> wrote:
>> Optimizes the divideUnsigned() and remainderUnsigned() methods in >> java.lang.Integer and java.lang.Long classes using x86 intrinsics. This >> change shows 3x improvement for Integer methods and upto 25% improvement for >> Long. This change also implements the DivMod optimization which fuses >> division and modulus operations if needed. The DivMod optimization shows 3x >> improvement for Integer and ~65% improvement for Long. > > Vamsi Parasa has updated the pull request incrementally with one additional > commit since the last revision: > > fix 32bit build issues src/hotspot/cpu/x86/c2_MacroAssembler_x86.cpp line 4408: > 4406: jmp(done); > 4407: bind(neg_divisor_fastpath); > 4408: // Fastpath for divisor < 0: How about checking if divisor is +ve or -ve constant and non-constant dividend in identity routine and setting a flag in IR node, which can be used to either emit fast / slow path in a new instruction selection pattern. It will save emitting redundant instructions. src/hotspot/share/opto/divnode.cpp line 881: > 879: return (phase->type( in(2) )->higher_equal(TypeLong::ONE)) ? in(1) : > this; > 880: } > 881: > //------------------------------Value------------------------------------------ Ideal transform to replace unsigned divide by cheaper logical right shift instruction if divisor is POW will be useful. src/hotspot/share/opto/divnode.cpp line 897: > 895: > 896: // Either input is BOTTOM ==> the result is the local BOTTOM > 897: const Type *bot = bottom_type(); Can we add constant folding handling when both dividend and divisor are constants. ------------- PR: https://git.openjdk.java.net/jdk/pull/7572
