RFR: 8293416: ZGC: Set mark bit with unconditional atomic ops [v3]

[hev]

On Thu, 8 Sep 2022 08:15:28 GMT, hev <duke at openjdk.org> wrote:

>> **Summary**
>> Support to set ZGC mark bit with unconditional atomic ops.
>> 
>> **Motivation**
>> ZGC currently modify mark-bitmap by a conditional atomic operation (cmpxchg). This way is not optimal, which will retry the loop when cmpxchg fails.
>> 
>> **Description**
>> First, This patch-set add an new unconditional atomic operation: Atomic::fetch_and_or, which is implemented in different ways for different CPU architectures:
>> 
>> * Exclusive access: Non-nested loop
>> 
>> 
>> retry:
>>   ll old_val, addr
>>   or new_val, old_val, set_val
>>   sc new_val, addr
>>   beq retry
>> 
>> 
>> * Atomic access: One instruction
>> 
>> 
>> ldset old_val, set_val, addr
>> 
>> 
>> * Generic: Fallback to cmpxchg or use c++ __atomic_fetch_or
>> 
>> **Testing**
>> * jtreg tests
>> * benchmark tests
>
> hev has updated the pull request with a new target base due to a merge or a rebase. The pull request now contains three commits:
> 
>  - ZGC: Set mark bit with unconditional atomic ops
>  - BitMap: Set bit with unconditional atomic ops
>  - Atomic: Add bitset functions

## Micro Benchmark 2

Benchmark: https://gist.github.com/heiher/a57c787e2f2d4f313df8cdf13086824e

### How to run


gcc -O3 -o bench atomic-mark-bench.c -pthread
perf stat ./bench norm
perf stat ./bench fast

### Results

Real time elapsed in seconds (Less is better)

| CPU/Threads/Mode | Score 1 | Score 2 | Score 3 | Score 4 | Score 5 | Score 6 |
|--------|--------|--------|--------|--------|--------|--------|
| Intel(R) Xeon(R) Silver 4210 CPU @ 2.20GHz |
| 16-Thread NORM | 40.89 | 39.74 | 41.26 | 41.70 | 41.30 | 41.48 |
| 16-Thread FAST | 0.03 | 0.03 | 0.03 | 0.03 | 0.03 | 0.03 |
| HUAWEI Kunpeng 920 @ 2.60GHz |
| 16-Thread NORM | 98.44 | 94.73 | 99.05 | 93.95 | 97.34 | 94.95 |
| 16-Thread FAST | 0.11 | 0.11 | 0.11 | 0.11 | 0.11 | 0.11 |

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

PR: https://git.openjdk.org/jdk/pull/10182