RFR: 8317720: RISC-V: Implement Adler32 intrinsic [v10]

[Fei Yang]

On Mon, 3 Jun 2024 19:38:44 GMT, ArsenyBochkarev <duke at openjdk.org> wrote:

>> Hello everyone! Please review this ~non-vectorized~ implementation of `_updateBytesAdler32` intrinsic. Reference implementation for AArch64 can be found [here](https://github.com/openjdk/jdk9/blob/master/hotspot/src/cpu/aarch64/vm/stubGenerator_aarch64.cpp#L3281).
>> 
>> ### Correctness checks
>> 
>> Test `test/hotspot/jtreg/compiler/intrinsics/zip/TestAdler32.java` is ok. All tier1 also passed.
>> 
>> ### Performance results on T-Head board
>> 
>> Enabled intrinsic:
>> 
>> | Benchmark                          |    (count) |  Mode |  Cnt  |   Score  |  Error |  Units |
>> | ------------------------------------- | ----------- | ------ | --------- | ------ | --------- | ---------- |
>> | Adler32.TestAdler32.testAdler32Update |      64 | thrpt  | 25 | 5522.693 | 23.387 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |     128 | thrpt |  25 | 3430.761 |  9.210 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |     256 | thrpt |  25 | 1962.888 |  5.323 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |     512 | thrpt  | 25 | 1050.938 |  0.144 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |    1024 | thrpt  | 25 |  549.227 |  0.375 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |    2048 | thrpt  | 25 |  280.829 |  0.170 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |    5012 | thrpt  | 25 |  116.333 |  0.057 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |    8192 | thrpt  | 25  |  71.392 |  0.060 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |   16384 | thrpt |  25  |  35.784 |  0.019 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update |   32768 | thrpt |  25  |  17.924 |  0.010 | ops/ms |
>> | Adler32.TestAdler32.testAdler32Update  |  65536 | thrpt |  25  |   8.940 |  0.003 | ops/ms |
>> 
>> Disabled intrinsic:
>> 
>> | Benchmark                          |    (count) |  Mode |  Cnt  |   Score  |  Error |  Units |
>> | ------------------------------------- | ----------- | ------ | --------- | ------ | --------- | ---------- |
>> |Adler32.TestAdler32.testAdler32Update|64|thrpt|25|655.633|5.845|ops/ms|
>> |Adler32.TestAdler32.testAdler32Update|128|thrpt|25|587.418|10.062|ops/ms|
>> |Adler32.TestAdler32.testAdler32Update|256|thrpt|25|546.675|11.598|ops/ms|
>> |Adler32.TestAdler32.testAdler32Update|512|thrpt|25|432.328|11.517|ops/ms|
>> |Adler32.TestAdler32.testAdler32Update|1024|thrpt|25|311.771|4.238|ops/ms|
>> |Adler32.TestAdler32.testAdler32Update|2048|thrpt|25|202.648|2.486|ops/ms|
>> |Adler32.TestAdler32.testAdler32Update|5012|thrpt|...
>
> ArsenyBochkarev has updated the pull request incrementally with two additional commits since the last revision:
> 
>  - Fix vrsub_vi for case of vlen > 128
>  - Add process_bytes_by32 function

Hi, Thanks for the update.

src/hotspot/cpu/riscv/stubGenerator_riscv.cpp line 5168:

> 5166:   void adler32_process_bytes_by16(Register buff, Register s1, Register s2, Register right_16_bits,
> 5167:     VectorRegister vtable, VectorRegister vzero, VectorRegister *vbytes, VectorRegister *vs1acc, VectorRegister *vs2acc, 
> 5168:     Register temp0, Register temp1, Register temp2, VectorRegister vtemp1, VectorRegister vtemp2, int LMUL) {

Let's remove this `LMUL` param as all the callsites now passes value 1. 

Question: Did you consider unifying adler32_process_bytes_by16/32/64 into one function with one extra param indicating the size? Seems to me that they duplicate most of the code. And I guess there should be no big difference for the 16 variant to do vector-widening reduction sum at the end just like the other two?

BTW: I can help test the performance difference as I have just added Banana-PI into my RV testing army.

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

PR Review: https://git.openjdk.org/jdk/pull/18382#pullrequestreview-2100636299
PR Review Comment: https://git.openjdk.org/jdk/pull/18382#discussion_r1628660207