On Fri, 13 Oct 2023 15:36:56 GMT, Ilya Gavrilin wrote:
> Hi all, please review this changes into risc-v floating point copysign and
> signum intrinsics.
> CopySign - returns first argument with the sign of second. On risc-v we have
> `fsgnj.x` instruction, which can implement th
return Math.copySign(double81, doubleNegative12) +
> Math.copySign(double81, double2) + Math.copySign(double4Dot1,
> doubleNegative12);
> }
>
> @Benchmark
> public float copySignFloat() {
> -return Math.copySign(floatNegative99, float1);
> +retur
return Math.copySign(double81, doubleNegative12) +
> Math.copySign(double81, double2) + Math.copySign(double4Dot1,
> doubleNegative12);
> }
>
> @Benchmark
> public float copySignFloat() {
> -return Math.copySign(floatNegative99, float1);
> +retur
On Thu, 19 Oct 2023 12:22:29 GMT, Fei Yang wrote:
> Still good. You might want to correct the remaining typo.
Thanks for review!
-
PR Comment: https://git.openjdk.org/jdk/pull/16186#issuecomment-1770876188
On Thu, 19 Oct 2023 12:14:52 GMT, Ilya Gavrilin wrote:
>> Hi all, please review this changes into risc-v floating point copysign and
>> signum intrinsics.
>> CopySign - returns first argument with the sign of second. On risc-v we have
>> `fsgnj.x` instruction,
return Math.copySign(double81, doubleNegative12) +
> Math.copySign(double81, double2) + Math.copySign(double4Dot1,
> doubleNegative12);
> }
>
> @Benchmark
> public float copySignFloat() {
> -return Math.copySign(floatNegative99, float1);
> +retur
return Math.copySign(double81, doubleNegative12) +
> Math.copySign(double81, double2) + Math.copySign(double4Dot1,
> doubleNegative12);
> }
>
> @Benchmark
> public float copySignFloat() {
> -return Math.copySign(floatNegative99, float1);
> +retur
On Tue, 17 Oct 2023 09:09:52 GMT, Fei Yang wrote:
>> Ilya Gavrilin has updated the pull request incrementally with one additional
>> commit since the last revision:
>>
>> Fix some registers usages and typos
>
> src/hotspot/cpu/riscv/c2_MacroAssembler_riscv.cpp l
return Math.copySign(double81, doubleNegative12) +
> Math.copySign(double81, double2) + Math.copySign(double4Dot1,
> doubleNegative12);
> }
>
> @Benchmark
> public float copySignFloat() {
> -return Math.copySign(floatNegative99, float1);
> +retur
Hi all, please review this changes into risc-v floating point copysign and
signum intrinsics.
CopySign - returns first argument with the sign of second. On risc-v we have
`fsgnj.x` instruction, which can implement this intrinsic.
Signum - returns input value if it is +/- 0.0 or NaN, otherwise 1.0
10 matches
Mail list logo