RFR: 8255455: Pre-generate ThreadHeapSampler::_log_table [v6]
Ioi Lam
iklam at openjdk.java.net
Thu Oct 29 20:06:49 UTC 2020
On Thu, 29 Oct 2020 14:23:04 GMT, Claes Redestad <redestad at openjdk.org> wrote:
>> The static `ThreadHeapSampler::_log_table` is currently initialized on JVM bootstrap to an overhead of ~67k instructions (linux-x64). By turning the initialization into a constexpr, we can precalculate the helper table at compile time, which trades a runtime overhead for a small, 8kb, static footprint increase.
>>
>> I compared `fast_log2` with the `log2` builtin with a naive benchmarking experiment[1] (not included in this PR) and show that the `fast_log2` is ~2.5x faster than `log2` on my system. And that without the lookup table we'd be much worse. So I think it makes sense to preserve this optimization, but get rid of the startup overhead:
>>
>> [5.428s][debug][heapsampling] log2, 0.0751173 secs
>> [5.457s][debug][heapsampling] fast_log2, 0.0298244 secs
>> [5.622s][debug][heapsampling] fast_log2_uncached, 0.1645569 secs
>>
>> I've verified that this refactoring does not affect performance in this naive setup.
>>
>> [1] https://github.com/openjdk/jdk/compare/master...cl4es:log2_micro?expand=1
>
> Claes Redestad has updated the pull request incrementally with two additional commits since the last revision:
>
> - Add explicit include of logging
> - Add const, fix copyright
Marked as reviewed by iklam (Reviewer).
src/hotspot/share/runtime/threadHeapSampler.cpp line 353:
> 351: const uint32_t y = x_high >> (20 - FastLogNumBits) & FastLogMask;
> 352: const int32_t exponent = ((x_high >> 20) & 0x7FF) - 1023;
> 353: return exponent + log_table[y];
The pre-generated values look good to me. Just a small nit. You can decide whether to take this or not:
C++ will generate an error if you have too many elements in `log_table[FastLogCount] = { ...`, but won't complain if you have not enough elements. Any uninitialized elements will take up the default value of 0.
To prevent cut-and-paste errors in the future, I would suggest adding something like
assert(FastLogCount > 0 && log_table[FastLogCount-1] != 0, "table should be full");
-------------
PR: https://git.openjdk.java.net/jdk/pull/880
More information about the serviceability-dev
mailing list