On Fri, 1 Nov 2024 07:53:03 GMT, Per Minborg wrote:
>> This PR proposes to improve `MemorySegment::ofBuffer` making it more
>> amenable to inlining and generally improving performance.
>>
>> Testing successfully on tier1-6
>
> Per Minborg has updated the pull request incrementally with one addi
On Fri, 1 Nov 2024 07:42:34 GMT, Per Minborg wrote:
>> Because heap segments don’t have to be backed by an array.
>
> The reason was what @ExE-Boss mentioned but for me, I am happy with either
> name. I will update to `heapSegment()`.
The method has been moved into Buffer implementations now.
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-6
Per Minborg has updated the pull request incrementally with one additional
commit since the last revision:
Rename methods
--
On Thu, 31 Oct 2024 19:06:16 GMT, ExE Boss wrote:
>> src/java.base/share/classes/jdk/internal/foreign/AbstractMemorySegmentImpl.java
>> line 526:
>>
>>> 524: final Object base = NIO_ACCESS.getBufferBase(b);
>>> 525: return (base == null)
>>> 526: ? nativeSegment(
On Thu, 31 Oct 2024 19:06:16 GMT, ExE Boss wrote:
> Because heap segments don’t have to be backed by an array.
I don't really know how to read this. We're asking a nio buffer to give us back
a memory segment. There's two kinds of memory segment: heap segments and native
segments (as the javado
On Thu, 31 Oct 2024 17:20:11 GMT, Maurizio Cimadamore
wrote:
>> Per Minborg has updated the pull request with a new target base due to a
>> merge or a rebase. The incremental webrev excludes the unrelated changes
>> brought in by the merge/rebase. The pull request contains 12 additional
>> co
On Thu, 31 Oct 2024 14:04:01 GMT, Per Minborg wrote:
>> This PR proposes to improve `MemorySegment::ofBuffer` making it more
>> amenable to inlining and generally improving performance.
>>
>> Testing successfully on tier1-3
>
> Per Minborg has updated the pull request with a new target base due
On Thu, 31 Oct 2024 12:56:54 GMT, Per Minborg wrote:
>> This PR proposes to improve `MemorySegment::ofBuffer` making it more
>> amenable to inlining and generally improving performance.
>>
>> Testing successfully on tier1-3
>
> Per Minborg has updated the pull request incrementally with one add
On Thu, 31 Oct 2024 10:25:11 GMT, Maurizio Cimadamore
wrote:
> Do you refer to char buffers backed by Strings?
If so, I wouldn't worry much about that -- after all, the logic in the code
already detects this condition and throws an exception... so it's still heap
buffer vs. direct buffer IMHO
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
Per Minborg has updated the pull request with a new target base due to a merge
or a rebase. The incremental webrev excludes the
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
Per Minborg has updated the pull request incrementally with one additional
commit since the last revision:
Rename method
---
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
Per Minborg has updated the pull request incrementally with one additional
commit since the last revision:
Fix issue in scale
On Thu, 31 Oct 2024 07:10:29 GMT, Per Minborg wrote:
>> src/java.base/share/classes/jdk/internal/foreign/AbstractMemorySegmentImpl.java
>> line 541:
>>
>>> 539:
>>> 540: @ForceInline
>>> 541: private static AbstractMemorySegmentImpl arrayFreeSegment(Buffer
>>> b, long offset, long len
On Wed, 30 Oct 2024 18:34:49 GMT, Maurizio Cimadamore
wrote:
>> Per Minborg has updated the pull request incrementally with one additional
>> commit since the last revision:
>>
>> Update from comments and add benchmark
>
> src/java.base/share/classes/jdk/internal/foreign/AbstractMemorySegmen
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
Per Minborg has updated the pull request incrementally with one additional
commit since the last revision:
Update from commen
On Tue, 29 Oct 2024 14:51:33 GMT, Per Minborg wrote:
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
I've added a very similar benchmark to the PR which I've run with a Mac M1
On Tue, 29 Oct 2024 14:51:33 GMT, Per Minborg wrote:
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
It might be possible to move even more logic into the various Buffer
impl
On Wed, 30 Oct 2024 18:36:37 GMT, Maurizio Cimadamore
wrote:
>> This PR proposes to improve `MemorySegment::ofBuffer` making it more
>> amenable to inlining and generally improving performance.
>>
>> Testing successfully on tier1-3
>
> src/java.base/share/classes/jdk/internal/foreign/AbstractM
On Wed, 30 Oct 2024 18:43:45 GMT, Maurizio Cimadamore
wrote:
>> This PR proposes to improve `MemorySegment::ofBuffer` making it more
>> amenable to inlining and generally improving performance.
>>
>> Testing successfully on tier1-3
>
> It would be great if we could find a benchmark where inlin
On Tue, 29 Oct 2024 14:51:33 GMT, Per Minborg wrote:
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
It would be great if we could find a benchmark where inlining doesn't happ
On Tue, 29 Oct 2024 14:51:33 GMT, Per Minborg wrote:
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
src/java.base/share/classes/java/nio/Buffer.java line 33:
> 31: import jd
On Tue, 29 Oct 2024 14:51:33 GMT, Per Minborg wrote:
> This PR proposes to improve `MemorySegment::ofBuffer` making it more amenable
> to inlining and generally improving performance.
>
> Testing successfully on tier1-3
src/java.base/share/classes/jdk/internal/foreign/AbstractMemorySegmentImpl
22 matches
Mail list logo
