RFR: 8361582: AArch64: Some ConH values cannot be replicated with SVE [v3]
Bhavana Kilambi
bkilambi at openjdk.org
Thu Aug 7 08:27:34 UTC 2025
On Fri, 1 Aug 2025 09:51:21 GMT, Andrew Haley <aph at openjdk.org> wrote:
>> Bhavana Kilambi has updated the pull request incrementally with one additional commit since the last revision:
>>
>> Addressed review comments
>
> src/hotspot/cpu/aarch64/aarch64_vector.ad line 4903:
>
>> 4901:
>> 4902: // Replicate a 16-bit half precision float which is within the limits
>> 4903: // as specified for the operand - immH8_shift8
>
> Suggestion:
>
> // for the operand - immH8_shift8
Done
> src/hotspot/cpu/aarch64/assembler_aarch64.cpp line 439:
>
>> 437: bool Assembler::operand_valid_for_sve_dup_immediate(int64_t imm) {
>> 438: return ((imm <= 127 && imm >= -128) ||
>> 439: (imm <= 32767 && imm >= -32768 && (imm & 0xff) == 0));
>
> Suggestion:
>
> return ((imm >= -128 && imm <= 127) ||
> (imm & 0xff == 0) && (imm >= -32768 && imm <= 32767));
>
> Reason: it's more conventional, and closer to the mathematical _l ≤ x ≤ h_.
Done
-------------
PR Review Comment: https://git.openjdk.org/jdk/pull/26589#discussion_r2259530180
PR Review Comment: https://git.openjdk.org/jdk/pull/26589#discussion_r2259529427
More information about the hotspot-compiler-dev
mailing list