Hi Pablo,
> -----Original Message-----
> From: De Lara Guarch, Pablo <pablo.de.lara.gua...@intel.com>
> Sent: Monday, October 5, 2020 2:20 PM
> To: O'loingsigh, Mairtin <mairtin.oloings...@intel.com>; Singh, Jasvinder
> <jasvinder.si...@intel.com>; Richardson, Bruce
> <bruce.richard...@intel.com>
> Cc: dev@dpdk.org; Ryan, Brendan <brendan.r...@intel.com>; Coyle, David
> <david.co...@intel.com>
> Subject: RE: [PATCH v3 2/2] net: add support for AVX512/VPCLMULQDQ
> based CRC
>
> Hi Mairtin,
>
> > -----Original Message-----
> > From: O'loingsigh, Mairtin <mairtin.oloings...@intel.com>
> > Sent: Tuesday, September 29, 2020 4:36 PM
> > To: Singh, Jasvinder <jasvinder.si...@intel.com>; Richardson, Bruce
> > <bruce.richard...@intel.com>; De Lara Guarch, Pablo
> > <pablo.de.lara.gua...@intel.com>
> > Cc: dev@dpdk.org; Ryan, Brendan <brendan.r...@intel.com>; Coyle,
> David
> > <david.co...@intel.com>; O'loingsigh, Mairtin
> > <mairtin.oloings...@intel.com>
> > Subject: [PATCH v3 2/2] net: add support for AVX512/VPCLMULQDQ based
> > CRC
> >
> > This patch enables the optimized calculation of CRC32-Ethernet and
> > CRC16- CCITT using the AVX512 and VPCLMULQDQ instruction sets. This
> > CRC implementation is built if the compiler supports the required
> > instruction sets. It is selected at run-time if the host CPU, again,
> > supports the required instruction sets.
> >
> > Signed-off-by: Mairtin o Loingsigh <mairtin.oloings...@intel.com>
> > Signed-off-by: David Coyle <david.co...@intel.com>
>
> ...
>
> > +static __rte_always_inline uint32_t
> > +crc32_eth_calc_vpclmulqdq(const uint8_t *data, uint32_t data_len,
> > +uint32_t
> > crc,
> > + const struct crc_vpclmulqdq_ctx *params) {
> > + __m128i res, d;
> > + __m256i b;
> > + __m512i temp, k;
> > + __m512i qw0 = _mm512_set1_epi64(0), qw1, qw2, qw3;
> > + __m512i fold0, fold1, fold2, fold3;
> > + __mmask16 mask;
> > + uint32_t n = 0;
> > + int reduction = 0;
> > +
> > + /* Get CRC init value */
> > + b = _mm256_insert_epi32(_mm256_setzero_si256(), crc, 0);
> > + temp = _mm512_inserti32x8(_mm512_setzero_si512(), b, 0);
>
> You can replace this with the following, which produces less instructions (b
> needs to be changed to __m128i):
>
> b = _mm_cvtsi32_si128(crc);
> temp = _mm512_castsi128_si512(b);
>
> > +
> > + if (data_len > 255) {
> > + fold0 = _mm512_loadu_si512((const __m512i *)data);
>
> ...
>
> > + } else {
> > + if (data_len > 31) {
> > + res = _mm_insert_epi32(_mm_setzero_si128(), crc,
> 0);
>
> Should work better with:
>
> res = _mm_cvtsi32_si128(crc);
>
> > + d = _mm_loadu_si128((const __m128i *)data);
> > + res = _mm_xor_si128(res, d);
> > + n += 16;
> > +
> > + reduction = 240 - ((n+256)-data_len);
> > +
> > + while (reduction > 0)
> > + reduction_loop(&res, &reduction, data, &n,
> > + params);
> > +
> > + if (n != data_len)
> > + res = last_two_xmm(data, data_len, n, res,
> > + params);
> > + } else if (data_len > 16) {
> > + res = _mm_insert_epi32(_mm_setzero_si128(), crc,
> 0);
>
> Same as above.
>
> > + d = _mm_loadu_si128((const __m128i *)data);
> > + res = _mm_xor_si128(res, d);
> > + n += 16;
> > +
> > + if (n != data_len)
> > + res = last_two_xmm(data, data_len, n, res,
> > + params);
> > + } else if (data_len == 16) {
> > + res = _mm_insert_epi32(_mm_setzero_si128(), crc,
> 0);
>
> Same.
>
> > + d = _mm_loadu_si128((const __m128i *)data);
> > + res = _mm_xor_si128(res, d);
> > + } else {
> > + res = _mm_insert_epi32(_mm_setzero_si128(), crc,
> 0);
>
> Same.
>
> > + mask = byte_len_to_mask_table[data_len];
> > + d = _mm_maskz_loadu_epi8(mask, data);
Thanks for the feedback.
Ill make these changes and submit a v4 patch
Regards,
Mairtin
