RFR: 8318158: RISC-V: implement roundD/roundF intrinsics [v8]

[Ludovic Henry]

On Mon, 18 Dec 2023 16:05:54 GMT, Olga Mikhaltsova <omikhaltcova at openjdk.org> wrote:

>> Please, review this Implementation of the roundD/roundF intrinsics for RISC-V platform.
>> 
>> In the table below it is shown that NaN argument should be processed as a special case.
>> 
>>                                                   RISC-V                            Java
>>                                         (FCVT.W.S)    (FCVT.L.D)  (long round(double a)) (int round(float a))
>> Minimum valid input (after rounding)     −2^31         −2^63         Long.MIN_VALUE       Integer.MIN_VALUE
>> Maximum valid input (after rounding)      2^31 − 1      2^63 − 1     Long.MAX_VALUE       Integer.MAX_VALUE
>> Output for out-of-range negative input   −2^31         −2^63         Long.MIN_VALUE       Integer.MIN_VALUE
>> Output for −∞                            −2^31         −2^63         Long.MIN_VALUE       Integer.MIN_VALUE
>> Output for out-of-range positive input    2^31 − 1      2^63 - 1     Long.MAX_VALUE       Integer.MAX_VALUE
>> Output for +∞                             2^31 − 1      2^63 - 1     Long.MAX_VALUE       Integer.MAX_VALUE
>> Output for NaN                            2^31 − 1      2^63 - 1           0                      0
>> 
>> The benchmark running with the 2nd fixed implementation on the T-Head RVB-ICE board shows the following performance improvement::
>> 
>> **Before**
>> 
>> Benchmark                              (TESTSIZE)   Mode  Cnt    Score   Error   Units
>> FpRoundingBenchmark.test_round_double        2048  thrpt   15   59.555  0.179  ops/ms
>> FpRoundingBenchmark.test_round_float         2048  thrpt   15   49.760  0.103  ops/ms
>> 
>> 
>> **After**
>> 
>> Benchmark                              (TESTSIZE)   Mode  Cnt    Score   Error   Units
>> FpRoundingBenchmark.test_round_double        2048  thrpt   15  110.956  0.186  ops/ms
>> FpRoundingBenchmark.test_round_float         2048  thrpt   15  115.947  0.122  ops/ms
>
> Olga Mikhaltsova has updated the pull request incrementally with one additional commit since the last revision:
> 
>   Used jint_cast/julong_cast; moved mv between feq and beqz

Given the check over the entire f32 bits space, happy to see it's giving the right results.

On the static vs dynamic rounding mode, AFAICT here it's using static rounding mode as the rounding mode gets embedded into the instruction. Did I misunderstand something here? And static mode will generally be better than dynamic mode for all the reasons outlined in the RVI spec.

-------------

Marked as reviewed by luhenry (Committer).

PR Review: https://git.openjdk.org/jdk/pull/16382#pullrequestreview-1789544966