RFR: 8332528: Generate code in SwitchBootstraps.generateTypeSwitch that require fewer adaptations
Claes Redestad
redestad at openjdk.org
Mon May 20 20:55:31 UTC 2024
On Mon, 20 May 2024 18:06:32 GMT, Chen Liang <liach at openjdk.org> wrote:
>> We can fold the call to `Objects.checkIndex` into the code generated in generateTypeSwitchSkeleton instead of doing so by filtering the MH argument. This loads 9 less classes (of which 8 generated LFs and Species classes) on a minimal test, while being neutral on a throughput sanity test:
>>
>>
>> Name Cnt Base Error Test Error Unit Change
>> SwitchSanity.switchSum 15 8,162 ± 0,117 8,152 ± 0,131 ns/op 1,00x (p = 0,800 )
>> * = significant
>> ```
>>
>> A few additional optimizations includes generating the switch method using the precise type (to avoid the need for an explicitCast adaptation), and moving some seldom used `findStatic` calls to a holder. All in all this means a reduction by 33-34M cycles to bootstrap a trivial switch expression on my M1.
>
> src/java.base/share/classes/java/lang/runtime/SwitchBootstraps.java line 406:
>
>> 404: cb.iload(RESTART_IDX);
>> 405: cb.loadConstant(labelConstants.length + 1);
>> 406: cb.invokestatic(CD_Objects, "checkIndex", MethodTypeDesc.of(ConstantDescs.CD_int, ConstantDescs.CD_int, ConstantDescs.CD_int));
>
> We should cache this MethodTypeDesc too.
`MethodTypeDesc.of` is actually quite cheap when inputs are `ClassDesc`s. Besides I think the main focus in these bootstraps should be improving the overhead of the first few calls - reduce dependencies, reduce runtime code generation - not treat this code as something that will be run many times over in a hot loop.
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/19307#discussion_r1607207823
More information about the core-libs-dev
mailing list