diff mbox

[dpdk-dev,v3,3/3] efd: run-time dispatch over x86 EFD functions

Message ID 1506411689-94690-4-git-send-email-xiaoyun.li@intel.com (mailing list archive)
State Superseded, archived
Headers

Checks

Context Check Description
ci/checkpatch success coding style OK
ci/Intel-compilation success Compilation OK

Commit Message

Li, Xiaoyun Sept. 26, 2017, 7:41 a.m. UTC 
  This patch dynamically selects x86 EFD functions at run-time.
This patch uses function pointer and binds it to the relative
function based on CPU flags at constructor time.

Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
---
 lib/librte_efd/rte_efd_x86.h | 41 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 38 insertions(+), 3 deletions(-)

Comments

Ananyev, Konstantin Oct. 2, 2017, 12:08 a.m. UTC | #1 
> 
> This patch dynamically selects x86 EFD functions at run-time.

I don't think it really does.
In fact, I am not sure that we need to touch EFD at all here -
from what I can see, it already does dynamic selection properly.
Konstantin 

> This patch uses function pointer and binds it to the relative
> function based on CPU flags at constructor time.
> 
> Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
> ---
>  lib/librte_efd/rte_efd_x86.h | 41 ++++++++++++++++++++++++++++++++++++++---
>  1 file changed, 38 insertions(+), 3 deletions(-)
> 
> diff --git a/lib/librte_efd/rte_efd_x86.h b/lib/librte_efd/rte_efd_x86.h
> index 34f37d7..93b6743 100644
> --- a/lib/librte_efd/rte_efd_x86.h
> +++ b/lib/librte_efd/rte_efd_x86.h
> @@ -43,12 +43,29 @@
>  #define EFD_LOAD_SI128(val) _mm_lddqu_si128(val)
>  #endif
> 
> +typedef efd_value_t
> +(*efd_lookup_internal_avx2_t)(const efd_hashfunc_t *group_hash_idx,
> +		const efd_lookuptbl_t *group_lookup_table,
> +		const uint32_t hash_val_a, const uint32_t hash_val_b);
> +
> +static efd_lookup_internal_avx2_t efd_lookup_internal_avx2_ptr;
> +
>  static inline efd_value_t
>  efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
>  		const efd_lookuptbl_t *group_lookup_table,
>  		const uint32_t hash_val_a, const uint32_t hash_val_b)
>  {
> -#ifdef RTE_MACHINE_CPUFLAG_AVX2
> +	return (*efd_lookup_internal_avx2_ptr)(group_hash_idx,
> +					       group_lookup_table,
> +					       hash_val_a, hash_val_b);
> +}
> +
> +#ifdef CC_SUPPORT_AVX2
> +static inline efd_value_t
> +efd_lookup_internal_avx2_AVX2(const efd_hashfunc_t *group_hash_idx,
> +		const efd_lookuptbl_t *group_lookup_table,
> +		const uint32_t hash_val_a, const uint32_t hash_val_b)
> +{
>  	efd_value_t value = 0;
>  	uint32_t i = 0;
>  	__m256i vhash_val_a = _mm256_set1_epi32(hash_val_a);
> @@ -74,13 +91,31 @@ efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
>  	}
> 
>  	return value;
> -#else
> +}
> +#endif
> +
> +static inline efd_value_t
> +efd_lookup_internal_avx2_DEFAULT(const efd_hashfunc_t *group_hash_idx,
> +		const efd_lookuptbl_t *group_lookup_table,
> +		const uint32_t hash_val_a, const uint32_t hash_val_b)
> +{
>  	RTE_SET_USED(group_hash_idx);
>  	RTE_SET_USED(group_lookup_table);
>  	RTE_SET_USED(hash_val_a);
>  	RTE_SET_USED(hash_val_b);
>  	/* Return dummy value, only to avoid compilation breakage */
>  	return 0;
> -#endif
> +}
> 
> +static void __attribute__((constructor))
> +rte_efd_x86_init(void)
> +{
> +#ifdef CC_SUPPORT_AVX2
> +	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
> +		efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_AVX2;
> +	else
> +		efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
> +#else
> +	efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
> +#endif
>  }
> --
> 2.7.4
Li, Xiaoyun Oct. 2, 2017, 12:09 a.m. UTC | #2 
OK.
Won't touch it in next version.

Best Regards,
Xiaoyun Li



> -----Original Message-----
> From: Ananyev, Konstantin
> Sent: Monday, October 2, 2017 08:08
> To: Li, Xiaoyun <xiaoyun.li@intel.com>; Richardson, Bruce
> <bruce.richardson@intel.com>
> Cc: Lu, Wenzhuo <wenzhuo.lu@intel.com>; Zhang, Helin
> <helin.zhang@intel.com>; dev@dpdk.org
> Subject: RE: [PATCH v3 3/3] efd: run-time dispatch over x86 EFD functions
> 
> 
> 
> >
> > This patch dynamically selects x86 EFD functions at run-time.
> 
> I don't think it really does.
> In fact, I am not sure that we need to touch EFD at all here - from what I can
> see, it already does dynamic selection properly.
> Konstantin
> 
> > This patch uses function pointer and binds it to the relative function
> > based on CPU flags at constructor time.
> >
> > Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
> > ---
> >  lib/librte_efd/rte_efd_x86.h | 41
> > ++++++++++++++++++++++++++++++++++++++---
> >  1 file changed, 38 insertions(+), 3 deletions(-)
> >
> > diff --git a/lib/librte_efd/rte_efd_x86.h
> > b/lib/librte_efd/rte_efd_x86.h index 34f37d7..93b6743 100644
> > --- a/lib/librte_efd/rte_efd_x86.h
> > +++ b/lib/librte_efd/rte_efd_x86.h
> > @@ -43,12 +43,29 @@
> >  #define EFD_LOAD_SI128(val) _mm_lddqu_si128(val)  #endif
> >
> > +typedef efd_value_t
> > +(*efd_lookup_internal_avx2_t)(const efd_hashfunc_t *group_hash_idx,
> > +		const efd_lookuptbl_t *group_lookup_table,
> > +		const uint32_t hash_val_a, const uint32_t hash_val_b);
> > +
> > +static efd_lookup_internal_avx2_t efd_lookup_internal_avx2_ptr;
> > +
> >  static inline efd_value_t
> >  efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
> >  		const efd_lookuptbl_t *group_lookup_table,
> >  		const uint32_t hash_val_a, const uint32_t hash_val_b)  { -
> #ifdef
> > RTE_MACHINE_CPUFLAG_AVX2
> > +	return (*efd_lookup_internal_avx2_ptr)(group_hash_idx,
> > +					       group_lookup_table,
> > +					       hash_val_a, hash_val_b);
> > +}
> > +
> > +#ifdef CC_SUPPORT_AVX2
> > +static inline efd_value_t
> > +efd_lookup_internal_avx2_AVX2(const efd_hashfunc_t *group_hash_idx,
> > +		const efd_lookuptbl_t *group_lookup_table,
> > +		const uint32_t hash_val_a, const uint32_t hash_val_b) {
> >  	efd_value_t value = 0;
> >  	uint32_t i = 0;
> >  	__m256i vhash_val_a = _mm256_set1_epi32(hash_val_a); @@ -
> 74,13
> > +91,31 @@ efd_lookup_internal_avx2(const efd_hashfunc_t
> *group_hash_idx,
> >  	}
> >
> >  	return value;
> > -#else
> > +}
> > +#endif
> > +
> > +static inline efd_value_t
> > +efd_lookup_internal_avx2_DEFAULT(const efd_hashfunc_t
> *group_hash_idx,
> > +		const efd_lookuptbl_t *group_lookup_table,
> > +		const uint32_t hash_val_a, const uint32_t hash_val_b) {
> >  	RTE_SET_USED(group_hash_idx);
> >  	RTE_SET_USED(group_lookup_table);
> >  	RTE_SET_USED(hash_val_a);
> >  	RTE_SET_USED(hash_val_b);
> >  	/* Return dummy value, only to avoid compilation breakage */
> >  	return 0;
> > -#endif
> > +}
> >
> > +static void __attribute__((constructor))
> > +rte_efd_x86_init(void)
> > +{
> > +#ifdef CC_SUPPORT_AVX2
> > +	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
> > +		efd_lookup_internal_avx2_ptr =
> efd_lookup_internal_avx2_AVX2;
> > +	else
> > +		efd_lookup_internal_avx2_ptr =
> efd_lookup_internal_avx2_DEFAULT;
> > +#else
> > +	efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
> > +#endif
> >  }
> > --
> > 2.7.4
Ananyev, Konstantin Oct. 2, 2017, 9:35 a.m. UTC | #3 
> 
> >
> > This patch dynamically selects x86 EFD functions at run-time.
> 
> I don't think it really does.
> In fact, I am not sure that we need to touch EFD at all here -
> from what I can see, it already does dynamic selection properly.

Actually I was wrong here - in some cases it doesn't work properly.
As I can see for default target proper avx2 code wouldn't be compiled.
So some work still needed here - same as for memcpy().
Konstantin


> Konstantin
> 
> > This patch uses function pointer and binds it to the relative
> > function based on CPU flags at constructor time.
> >
> > Signed-off-by: Xiaoyun Li <xiaoyun.li@intel.com>
> > ---
> >  lib/librte_efd/rte_efd_x86.h | 41 ++++++++++++++++++++++++++++++++++++++---
> >  1 file changed, 38 insertions(+), 3 deletions(-)
> >
> > diff --git a/lib/librte_efd/rte_efd_x86.h b/lib/librte_efd/rte_efd_x86.h
> > index 34f37d7..93b6743 100644
> > --- a/lib/librte_efd/rte_efd_x86.h
> > +++ b/lib/librte_efd/rte_efd_x86.h
> > @@ -43,12 +43,29 @@
> >  #define EFD_LOAD_SI128(val) _mm_lddqu_si128(val)
> >  #endif
> >
> > +typedef efd_value_t
> > +(*efd_lookup_internal_avx2_t)(const efd_hashfunc_t *group_hash_idx,
> > +		const efd_lookuptbl_t *group_lookup_table,
> > +		const uint32_t hash_val_a, const uint32_t hash_val_b);
> > +
> > +static efd_lookup_internal_avx2_t efd_lookup_internal_avx2_ptr;
> > +
> >  static inline efd_value_t
> >  efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
> >  		const efd_lookuptbl_t *group_lookup_table,
> >  		const uint32_t hash_val_a, const uint32_t hash_val_b)
> >  {
> > -#ifdef RTE_MACHINE_CPUFLAG_AVX2
> > +	return (*efd_lookup_internal_avx2_ptr)(group_hash_idx,
> > +					       group_lookup_table,
> > +					       hash_val_a, hash_val_b);
> > +}
> > +
> > +#ifdef CC_SUPPORT_AVX2
> > +static inline efd_value_t
> > +efd_lookup_internal_avx2_AVX2(const efd_hashfunc_t *group_hash_idx,
> > +		const efd_lookuptbl_t *group_lookup_table,
> > +		const uint32_t hash_val_a, const uint32_t hash_val_b)
> > +{
> >  	efd_value_t value = 0;
> >  	uint32_t i = 0;
> >  	__m256i vhash_val_a = _mm256_set1_epi32(hash_val_a);
> > @@ -74,13 +91,31 @@ efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
> >  	}
> >
> >  	return value;
> > -#else
> > +}
> > +#endif
> > +
> > +static inline efd_value_t
> > +efd_lookup_internal_avx2_DEFAULT(const efd_hashfunc_t *group_hash_idx,
> > +		const efd_lookuptbl_t *group_lookup_table,
> > +		const uint32_t hash_val_a, const uint32_t hash_val_b)
> > +{
> >  	RTE_SET_USED(group_hash_idx);
> >  	RTE_SET_USED(group_lookup_table);
> >  	RTE_SET_USED(hash_val_a);
> >  	RTE_SET_USED(hash_val_b);
> >  	/* Return dummy value, only to avoid compilation breakage */
> >  	return 0;
> > -#endif
> > +}
> >
> > +static void __attribute__((constructor))
> > +rte_efd_x86_init(void)
> > +{
> > +#ifdef CC_SUPPORT_AVX2
> > +	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
> > +		efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_AVX2;
> > +	else
> > +		efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
> > +#else
> > +	efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
> > +#endif
> >  }
> > --
> > 2.7.4
diff mbox

Patch

diff --git a/lib/librte_efd/rte_efd_x86.h b/lib/librte_efd/rte_efd_x86.h
index 34f37d7..93b6743 100644
--- a/lib/librte_efd/rte_efd_x86.h
+++ b/lib/librte_efd/rte_efd_x86.h
@@ -43,12 +43,29 @@ 
 #define EFD_LOAD_SI128(val) _mm_lddqu_si128(val)
 #endif
 
+typedef efd_value_t
+(*efd_lookup_internal_avx2_t)(const efd_hashfunc_t *group_hash_idx,
+		const efd_lookuptbl_t *group_lookup_table,
+		const uint32_t hash_val_a, const uint32_t hash_val_b);
+
+static efd_lookup_internal_avx2_t efd_lookup_internal_avx2_ptr;
+
 static inline efd_value_t
 efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
 		const efd_lookuptbl_t *group_lookup_table,
 		const uint32_t hash_val_a, const uint32_t hash_val_b)
 {
-#ifdef RTE_MACHINE_CPUFLAG_AVX2
+	return (*efd_lookup_internal_avx2_ptr)(group_hash_idx,
+					       group_lookup_table,
+					       hash_val_a, hash_val_b);
+}
+
+#ifdef CC_SUPPORT_AVX2
+static inline efd_value_t
+efd_lookup_internal_avx2_AVX2(const efd_hashfunc_t *group_hash_idx,
+		const efd_lookuptbl_t *group_lookup_table,
+		const uint32_t hash_val_a, const uint32_t hash_val_b)
+{
 	efd_value_t value = 0;
 	uint32_t i = 0;
 	__m256i vhash_val_a = _mm256_set1_epi32(hash_val_a);
@@ -74,13 +91,31 @@  efd_lookup_internal_avx2(const efd_hashfunc_t *group_hash_idx,
 	}
 
 	return value;
-#else
+}
+#endif
+
+static inline efd_value_t
+efd_lookup_internal_avx2_DEFAULT(const efd_hashfunc_t *group_hash_idx,
+		const efd_lookuptbl_t *group_lookup_table,
+		const uint32_t hash_val_a, const uint32_t hash_val_b)
+{
 	RTE_SET_USED(group_hash_idx);
 	RTE_SET_USED(group_lookup_table);
 	RTE_SET_USED(hash_val_a);
 	RTE_SET_USED(hash_val_b);
 	/* Return dummy value, only to avoid compilation breakage */
 	return 0;
-#endif
+}
 
+static void __attribute__((constructor))
+rte_efd_x86_init(void)
+{
+#ifdef CC_SUPPORT_AVX2
+	if (rte_cpu_get_flag_enabled(RTE_CPUFLAG_AVX2))
+		efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_AVX2;
+	else
+		efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
+#else
+	efd_lookup_internal_avx2_ptr = efd_lookup_internal_avx2_DEFAULT;
+#endif
 }