On Tue, Apr 14, 2015 at 11:32 PM, Pawel Wodkowski <
pawelx.wodkowski at intel.com> wrote:
> On 2015-04-14 23:31, Ravi Kerur wrote:
>
>> +
>> + for (i = 0; i < 8; i++) {
>> + ymm = _mm256_loadu_si256((const __m256i *)(src +
>> i * 32));
>> + _mm256_storeu_si256((__m256i *)(dst + i * 32),
>> ymm);
>> + }
>> +
>> n -= 256;
>> - ymm1 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 1 * 32));
>> - ymm2 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 2 * 32));
>> - ymm3 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 3 * 32));
>> - ymm4 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 4 * 32));
>> - ymm5 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 5 * 32));
>> - ymm6 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 6 * 32));
>> - ymm7 = _mm256_loadu_si256((const __m256i *)((const
>> uint8_t *)src + 7 * 32));
>> - src = (const uint8_t *)src + 256;
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 0 * 32),
>> ymm0);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 1 * 32),
>> ymm1);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 2 * 32),
>> ymm2);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 3 * 32),
>> ymm3);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 4 * 32),
>> ymm4);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 5 * 32),
>> ymm5);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 6 * 32),
>> ymm6);
>> - _mm256_storeu_si256((__m256i *)((uint8_t *)dst + 7 * 32),
>> ymm7);
>> - dst = (uint8_t *)dst + 256;
>> + src = src + 256;
>> + dst = dst + 256;
>> }
>>
>
> Did you perform a performance test on that part?
>
>
I ran "make test" which runs "memcpy perf" results were given in
"cover-letter". I am pasting it here again.
/**********************With changes*************************************/
Start memcpy_perf: Success [00m 00s]
Memcpy performance autotest: Success [09m 36s] [17m 45s]
/**********************Without changes**********************************/
Start memcpy_perf: Success [00m 00s]
Memcpy performance autotest: Success [09m 35s] [13m 57s]
--
> Pawel
>
