On Tue, 28 Sep 2021 11:49:28 GMT, Volker Simonis wrote:
>> Does the changes in 9800a99 resolve your concerns?
>
> In principle yes, but shouldn't the condition read:
>
> if (!Matcher::match_rule_supported(Op_EncodeISOArray) ||
> !Matcher::supports_encode_ascii_array) return false;
>
> I.e.
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from a String. The former took a small performance hit in JDK
On Wed, 29 Sep 2021 12:36:23 GMT, Claes Redestad wrote:
>> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
>> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
>> perform on par with (or outperform) similarly getting charset encoded bytes
>>
On Mon, 27 Sep 2021 12:27:32 GMT, Tobias Hartmann wrote:
>>> Should we remove the "iso" part from the method/class names?
>>
>> I'm open to suggestions, but I've not been able to think of anything better.
>> `encodeISOOrASCII` doesn't seem helpful and since ASCII is a subset of the
>>
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from a String. The former took a small performance hit in JDK
On Tue, 28 Sep 2021 11:49:29 GMT, Claes Redestad wrote:
>> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
>> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
>> perform on par with (or outperform) similarly getting charset encoded bytes
>>
otspot-compiler-...@openjdk.java.net ;
nio-...@openjdk.java.net
Subject: Re: RFR: 8274242: Implement fast-path for ASCII-compatible
CharsetEncoders on x86 [v5]
On Tue, 28 Sep 2021 10:01:43 GMT, Claes Redestad wrote:
>> Not too much work. I recently introduced platform-specific `matcher_*.hpp`
On Tue, 28 Sep 2021 10:01:43 GMT, Claes Redestad wrote:
>> Not too much work. I recently introduced platform-specific `matcher_*.hpp`
>> files, so since then adding a boolean constant is easy (no need to muck with
>> the .ad files).
>
> Does the changes in 9800a99 resolve your concerns?
In
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from a String. The former took a small performance hit in JDK
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from a String. The former took a small performance hit in JDK
On Mon, 27 Sep 2021 12:11:22 GMT, Claes Redestad wrote:
>> src/hotspot/share/opto/c2compiler.cpp line 222:
>>
>>> 220: #if !defined(X86)
>>> 221: return false; // not yet implemented
>>> 222: #endif
>>
>> It might be a little more work, but I think it's cleaner to move the
>> decision
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from a String. The former took a small performance hit in JDK
On Mon, 27 Sep 2021 11:59:54 GMT, Claes Redestad wrote:
> > Should we remove the "iso" part from the method/class names?
>
> I'm open to suggestions, but I've not been able to think of anything better.
> `encodeISOOrASCII` doesn't seem helpful and since ASCII is a subset of the
> ISO-8859-1
On Mon, 27 Sep 2021 09:34:21 GMT, Volker Simonis wrote:
>> Claes Redestad has updated the pull request incrementally with one
>> additional commit since the last revision:
>>
>> Add Matcher predicate to avoid changing shared code as non-x86 platforms
>> implements support for the
On Mon, 27 Sep 2021 06:36:50 GMT, Tobias Hartmann wrote:
> Should we remove the "iso" part from the method/class names?
I'm open to suggestions, but I've not been able to think of anything better.
`encodeISOOrASCII` doesn't seem helpful and since ASCII is a subset of the
ISO-8859-1 encoding
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from a String. The former took a small performance hit in JDK
On Tue, 21 Sep 2021 21:58:48 GMT, Claes Redestad wrote:
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from
On Tue, 21 Sep 2021 21:58:48 GMT, Claes Redestad wrote:
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from
On Tue, 21 Sep 2021 21:58:48 GMT, Claes Redestad wrote:
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from
On Tue, 21 Sep 2021 21:58:48 GMT, Claes Redestad wrote:
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from
On Thu, 23 Sep 2021 00:03:55 GMT, Claes Redestad wrote:
> This can probably be simplified further, say by adding a flag to the
> intrinsic of whether we're encoding ASCII only or ISO-8859-1.
Done: Removed the addition of a new C2 Node, merged the macro assembler
encode_iso_array and
This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to work
also for ASCII encoding, which makes for example the `UTF_8$Encoder` perform on
par with (or outperform) similarly getting charset encoded bytes from a String.
The former took a small performance hit in JDK 9, and
On Tue, 21 Sep 2021 21:58:48 GMT, Claes Redestad wrote:
> This patch extends the `ISO_8859_1.implEncodeISOArray` intrinsic on x86 to
> work also for ASCII encoding, which makes for example the `UTF_8$Encoder`
> perform on par with (or outperform) similarly getting charset encoded bytes
> from
23 matches
Mail list logo