date:20190210

Re: [dpdk-dev] [PATCH v2] net/mlx: support firmware version query

2019-02-10 Thread Shahaf Shuler

Thursday, February 7, 2019 12:25 AM, Thomas Monjalon:
> Cc: dev@dpdk.org
> Subject: [PATCH v2] net/mlx: support firmware version query
> 
> The API function rte_eth_dev_fw_version_get() is querying drivers via the
> operation callback fw_version_get().
> The implementation of this operation is added for mlx4 and mlx5.
> Both functions are copying the same ibverbs field fw_ver which is retrieved
> when calling ibv_query_device[_ex]() during the port probing.
> 
> It is tested with command "drvinfo" of examples/ethtool/.
> 
> Signed-off-by: Thomas Monjalon 

Acked-by: Shahaf Shuler 

Applied to next-net-mlx, thanks.

Re: [dpdk-dev] [PATCH v3] net/mlx5: fix Tx metadata for multi-segment packet

2019-02-10 Thread Shahaf Shuler

Wednesday, January 30, 2019 9:24 AM, Yongseok Koh:
> Subject: Re: [PATCH v3] net/mlx5: fix Tx metadata for multi-segment packet
> 
> > On Jan 30, 2019, at 3:43 PM, Dekel Peled  wrote:
> >
> > Original patch implemented the use of match_metadata offload in the
> > different burst functions.
> > The concurrent use of match_metadata and multi_segs offloads was not
> > handled.
> >
> > This patch updates function txq_scatter_v(), to pass metadata value
> > from mbuf to wqe, when indicated by offload flags.
> >
> > Fixes: 6bd7fbd03c62 ("net/mlx5: support metadata as flow rule
> > criteria")
> > Cc: sta...@dpdk.org
> >
> > Signed-off-by: Dekel Peled 

Applied to next-net-mlx, thanks .

> >
> > ---
> 
> Acked-by: Yongseok Koh 
> 
> Thanks
> 
> > v3: Update title, modify indentation.
> > v2: Apply code review comments.
> > ---
> > ---
> > drivers/net/mlx5/mlx5_rxtx_vec_neon.h | 12 +---
> > drivers/net/mlx5/mlx5_rxtx_vec_sse.h  | 11 ---
> > 2 files changed, 17 insertions(+), 6 deletions(-)
> >
> > diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> > b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> > index 883fe1b..38e915c 100644
> > --- a/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> > +++ b/drivers/net/mlx5/mlx5_rxtx_vec_neon.h
> > @@ -104,6 +104,8 @@
> > sizeof(struct mlx5_wqe) / MLX5_WQE_DWORD_SIZE;
> > unsigned int n;
> > volatile struct mlx5_wqe *wqe = NULL;
> > +   bool metadata_ol =
> > +   txq->offloads & DEV_TX_OFFLOAD_MATCH_METADATA ?
> true : false;
> >
> > assert(elts_n > pkts_n);
> > mlx5_tx_complete(txq);
> > @@ -127,6 +129,9 @@
> > uint8x16_t *t_wqe;
> > uint8_t *dseg;
> > uint8x16_t ctrl;
> > +   rte_be32_t metadata =
> > +   metadata_ol && (buf->ol_flags &
> PKT_TX_METADATA) ?
> > +   buf->tx_metadata : 0;
> >
> > assert(segs_n);
> > max_elts = elts_n - (elts_head - txq->elts_tail); @@ -164,9
> +169,10
> > @@
> > ctrl = vqtbl1q_u8(ctrl, ctrl_shuf_m);
> > vst1q_u8((void *)t_wqe, ctrl);
> > /* Fill ESEG in the header. */
> > -   vst1q_u16((void *)(t_wqe + 1),
> > - ((uint16x8_t) { 0, 0, cs_flags,
> rte_cpu_to_be_16(len),
> > - 0, 0, 0, 0 }));
> > +   vst1q_u32((void *)(t_wqe + 1),
> > + ((uint32x4_t){ 0,
> > +cs_flags << 16 |
> rte_cpu_to_be_16(len),
> > +metadata, 0 }));
> > txq->wqe_ci = wqe_ci;
> > }
> > if (!n)
> > diff --git a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> > b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> > index 14117c4..fb384ef 100644
> > --- a/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> > +++ b/drivers/net/mlx5/mlx5_rxtx_vec_sse.h
> > @@ -104,6 +104,8 @@
> > sizeof(struct mlx5_wqe) / MLX5_WQE_DWORD_SIZE;
> > unsigned int n;
> > volatile struct mlx5_wqe *wqe = NULL;
> > +   bool metadata_ol =
> > +   txq->offloads & DEV_TX_OFFLOAD_MATCH_METADATA ?
> true : false;
> >
> > assert(elts_n > pkts_n);
> > mlx5_tx_complete(txq);
> > @@ -125,6 +127,9 @@
> > uint16_t max_wqe;
> > __m128i *t_wqe, *dseg;
> > __m128i ctrl;
> > +   rte_be32_t metadata =
> > +   metadata_ol && (buf->ol_flags &
> PKT_TX_METADATA) ?
> > +   buf->tx_metadata : 0;
> >
> > assert(segs_n);
> > max_elts = elts_n - (elts_head - txq->elts_tail); @@ -165,9
> +170,9
> > @@
> > _mm_store_si128(t_wqe, ctrl);
> > /* Fill ESEG in the header. */
> > _mm_store_si128(t_wqe + 1,
> > -   _mm_set_epi16(0, 0, 0, 0,
> > - rte_cpu_to_be_16(len), cs_flags,
> > - 0, 0));
> > +   _mm_set_epi32(0, metadata,
> > + (rte_cpu_to_be_16(len) << 16) |
> > + cs_flags, 0));
> > txq->wqe_ci = wqe_ci;
> > }
> > if (!n)
> > --
> > 1.8.3.1
> >

[dpdk-dev] [PATCH v1] hash: optimize signature compare by using neon intrinsic

2019-02-10 Thread Ruifeng Wang

Implemented signature compare function based on neon intrinsic.
Hash bulk lookup had 3% - 6% performance gain after optimization.

Signed-off-by: Ruifeng Wang 
---
 lib/librte_hash/rte_cuckoo_hash.c | 32 ++-
 lib/librte_hash/rte_cuckoo_hash.h |  1 +
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/lib/librte_hash/rte_cuckoo_hash.c 
b/lib/librte_hash/rte_cuckoo_hash.c
index c01489ba5..5745a254f 100644
--- a/lib/librte_hash/rte_cuckoo_hash.c
+++ b/lib/librte_hash/rte_cuckoo_hash.c
@@ -26,6 +26,9 @@
 #include 
 #include 
 #include 
+#if defined(RTE_ARCH_ARM64)
+#include 
+#endif
 
 #include "rte_hash.h"
 #include "rte_cuckoo_hash.h"
@@ -407,6 +410,10 @@ rte_hash_create(const struct rte_hash_parameters *params)
if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE2))
h->sig_cmp_fn = RTE_HASH_COMPARE_SSE;
else
+#elif defined(RTE_ARCH_ARM64)
+   if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON))
+   h->sig_cmp_fn = RTE_HASH_COMPARE_NEON;
+   else
 #endif
h->sig_cmp_fn = RTE_HASH_COMPARE_SCALAR;
 
@@ -1578,10 +1585,15 @@ compare_signatures(uint32_t *prim_hash_matches, 
uint32_t *sec_hash_matches,
enum rte_hash_sig_compare_function sig_cmp_fn)
 {
unsigned int i;
+#ifdef RTE_MACHINE_CPUFLAG_NEON
+   uint16x8_t vmat, vsig, x;
+   uint64x2_t x64;
+   int16x8_t shift = {-15, -13, -11, -9, -7, -5, -3, -1};
+#endif
 
/* For match mask the first bit of every two bits indicates the match */
switch (sig_cmp_fn) {
-#ifdef RTE_MACHINE_CPUFLAG_SSE2
+#if defined(RTE_MACHINE_CPUFLAG_SSE2)
case RTE_HASH_COMPARE_SSE:
/* Compare all signatures in the bucket */
*prim_hash_matches = _mm_movemask_epi8(_mm_cmpeq_epi16(
@@ -1594,6 +1606,24 @@ compare_signatures(uint32_t *prim_hash_matches, uint32_t 
*sec_hash_matches,
(__m128i const *)sec_bkt->sig_current),
_mm_set1_epi16(sig)));
break;
+#elif defined(RTE_MACHINE_CPUFLAG_NEON)
+   case RTE_HASH_COMPARE_NEON:
+   vsig = vld1q_dup_u16((uint16_t const *)&sig);
+   /* Compare all signatures in the primary bucket */
+   vmat = vceqq_u16(vsig,
+   vld1q_u16((uint16_t const *)prim_bkt->sig_current));
+   x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
+   x64 = vpaddlq_u32(vpaddlq_u16(x));
+   *prim_hash_matches = (uint32_t)(vgetq_lane_u64(x64, 0) +
+   vgetq_lane_u64(x64, 1));
+   /* Compare all signatures in the secondary bucket */
+   vmat = vceqq_u16(vsig,
+   vld1q_u16((uint16_t const *)sec_bkt->sig_current));
+   x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)), shift);
+   x64 = vpaddlq_u32(vpaddlq_u16(x));
+   *sec_hash_matches = (uint32_t)(vgetq_lane_u64(x64, 0) +
+   vgetq_lane_u64(x64, 1));
+   break;
 #endif
default:
for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
diff --git a/lib/librte_hash/rte_cuckoo_hash.h 
b/lib/librte_hash/rte_cuckoo_hash.h
index eacdaa8d4..0548c97f0 100644
--- a/lib/librte_hash/rte_cuckoo_hash.h
+++ b/lib/librte_hash/rte_cuckoo_hash.h
@@ -141,6 +141,7 @@ struct rte_hash_key {
 enum rte_hash_sig_compare_function {
RTE_HASH_COMPARE_SCALAR = 0,
RTE_HASH_COMPARE_SSE,
+   RTE_HASH_COMPARE_NEON,
RTE_HASH_COMPARE_NUM
 };
 
-- 
2.17.1

Re: [dpdk-dev] [EXT] [PATCH v1] hash: optimize signature compare by using neon intrinsic

2019-02-10 Thread Jerin Jacob Kollanukkaran

On Mon, 2019-02-11 at 15:30 +0800, Ruifeng Wang wrote:
> 
> ---
> ---
> Implemented signature compare function based on neon intrinsic.
> Hash bulk lookup had 3% - 6% performance gain after optimization.
> 
> Signed-off-by: Ruifeng Wang 
> ---
>  lib/librte_hash/rte_cuckoo_hash.c | 32
> ++-
>  lib/librte_hash/rte_cuckoo_hash.h |  1 +
>  2 files changed, 32 insertions(+), 1 deletion(-)
> 
> diff --git a/lib/librte_hash/rte_cuckoo_hash.c
> b/lib/librte_hash/rte_cuckoo_hash.c
> index c01489ba5..5745a254f 100644
> --- a/lib/librte_hash/rte_cuckoo_hash.c
> +++ b/lib/librte_hash/rte_cuckoo_hash.c
> @@ -26,6 +26,9 @@
>  #include 
>  #include 
>  #include 
> +#if defined(RTE_ARCH_ARM64)
> +#include 
> +#endif


The use of rte_vector.h will remove the need for #if defined...


>  
>  #include "rte_hash.h"
>  #include "rte_cuckoo_hash.h"
> @@ -407,6 +410,10 @@ rte_hash_create(const struct rte_hash_parameters
> *params)
>   if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_SSE2))
>   h->sig_cmp_fn = RTE_HASH_COMPARE_SSE;
>   else
> +#elif defined(RTE_ARCH_ARM64)
> + if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_NEON))
> + h->sig_cmp_fn = RTE_HASH_COMPARE_NEON;
> + else
>  #endif
>   h->sig_cmp_fn = RTE_HASH_COMPARE_SCALAR;
>  
> @@ -1578,10 +1585,15 @@ compare_signatures(uint32_t
> *prim_hash_matches, uint32_t *sec_hash_matches,
>   enum rte_hash_sig_compare_function sig_cmp_fn)
>  {
>   unsigned int i;
> +#ifdef RTE_MACHINE_CPUFLAG_NEON
> + uint16x8_t vmat, vsig, x;
> + uint64x2_t x64;
> + int16x8_t shift = {-15, -13, -11, -9, -7, -5, -3, -1};
> +#endif

Is it possible move down the variable declaration? to avoid the need
for #ifdef here

>  
>   /* For match mask the first bit of every two bits indicates the
> match */
>   switch (sig_cmp_fn) {
> -#ifdef RTE_MACHINE_CPUFLAG_SSE2
> +#if defined(RTE_MACHINE_CPUFLAG_SSE2)
>   case RTE_HASH_COMPARE_SSE:
>   /* Compare all signatures in the bucket */
>   *prim_hash_matches = _mm_movemask_epi8(_mm_cmpeq_epi16(
> @@ -1594,6 +1606,24 @@ compare_signatures(uint32_t
> *prim_hash_matches, uint32_t *sec_hash_matches,
>   (__m128i const *)sec_bkt-
> >sig_current),
>   _mm_set1_epi16(sig)));
>   break;
> +#elif defined(RTE_MACHINE_CPUFLAG_NEON)
> + case RTE_HASH_COMPARE_NEON:
> + vsig = vld1q_dup_u16((uint16_t const *)&sig);
> + /* Compare all signatures in the primary bucket */
> + vmat = vceqq_u16(vsig,
> + vld1q_u16((uint16_t const *)prim_bkt-
> >sig_current));
> + x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)),
> shift);
> + x64 = vpaddlq_u32(vpaddlq_u16(x));
> + *prim_hash_matches = (uint32_t)(vgetq_lane_u64(x64, 0)
> +
> + vgetq_lane_u64(x64, 1));
> + /* Compare all signatures in the secondary bucket */
> + vmat = vceqq_u16(vsig,
> + vld1q_u16((uint16_t const *)sec_bkt-
> >sig_current));
> + x = vshlq_u16(vandq_u16(vmat, vdupq_n_u16(0x8000)),
> shift);
> + x64 = vpaddlq_u32(vpaddlq_u16(x));
> + *sec_hash_matches = (uint32_t)(vgetq_lane_u64(x64, 0) +
> + vgetq_lane_u64(x64, 1));
> + break;
>  #endif
>   default:
>   for (i = 0; i < RTE_HASH_BUCKET_ENTRIES; i++) {
> diff --git a/lib/librte_hash/rte_cuckoo_hash.h
> b/lib/librte_hash/rte_cuckoo_hash.h
> index eacdaa8d4..0548c97f0 100644
> --- a/lib/librte_hash/rte_cuckoo_hash.h
> +++ b/lib/librte_hash/rte_cuckoo_hash.h
> @@ -141,6 +141,7 @@ struct rte_hash_key {
>  enum rte_hash_sig_compare_function {
>   RTE_HASH_COMPARE_SCALAR = 0,
>   RTE_HASH_COMPARE_SSE,
> + RTE_HASH_COMPARE_NEON,
>   RTE_HASH_COMPARE_NUM
>  };
>

Re: [dpdk-dev] [PATCH v2] net/mlx: support firmware version query

Re: [dpdk-dev] [PATCH v3] net/mlx5: fix Tx metadata for multi-segment packet

[dpdk-dev] [PATCH v1] hash: optimize signature compare by using neon intrinsic

Re: [dpdk-dev] [EXT] [PATCH v1] hash: optimize signature compare by using neon intrinsic

4 matches

Site Navigation

Mail list logo

Footer information