DPDK patches and discussions
 help / color / mirror / Atom feed
From: Zhihong Wang <zhihong.wang@intel.com>
To: dev@dpdk.org
Cc: yuanhan.liu@linux.intel.com, thomas@monjalon.net,
	bruce.richardson@intel.com, Zhihong Wang <zhihong.wang@intel.com>
Subject: [dpdk-dev] [PATCH v2] config: make AVX and AVX512 configurable
Date: Thu, 27 Apr 2017 19:00:14 -0400	[thread overview]
Message-ID: <1493334014-69488-1-git-send-email-zhihong.wang@intel.com> (raw)
In-Reply-To: <1493310859-49106-1-git-send-email-zhihong.wang@intel.com>

Making AVX and AVX512 configurable is useful for performance and power
testing.

The similar kernel patch at https://patchwork.kernel.org/patch/9618883/.

AVX512 support like in rte_memcpy has been in DPDK since 16.04, but it's
still unproven in rich use cases in hardware. Therefore it's marked as
experimental for now, will enable it after enough field test and possible
optimization.

Signed-off-by: Zhihong Wang <zhihong.wang@intel.com>
---
Changes in v2:

 1. Add comments and explanation.

---
 config/common_base | 8 ++++++++
 mk/rte.cpuflags.mk | 6 ++++++
 2 files changed, 14 insertions(+)

diff --git a/config/common_base b/config/common_base
index 0b4297c..93e9235 100644
--- a/config/common_base
+++ b/config/common_base
@@ -103,6 +103,14 @@ CONFIG_RTE_EAL_IGB_UIO=n
 CONFIG_RTE_EAL_VFIO=n
 CONFIG_RTE_MALLOC_DEBUG=n
 
+#
+# Recognize/ignore the AVX/AVX512 CPU flags for performance/power testing.
+# AVX512 is marked as experimental for now, will enable it after enough
+# field test and possible optimization.
+#
+CONFIG_RTE_ENABLE_AVX=y
+CONFIG_RTE_ENABLE_AVX512=n
+
 # Default driver path (or "" to disable)
 CONFIG_RTE_EAL_PMD_PATH=""
 
diff --git a/mk/rte.cpuflags.mk b/mk/rte.cpuflags.mk
index e634abc..4288c14 100644
--- a/mk/rte.cpuflags.mk
+++ b/mk/rte.cpuflags.mk
@@ -70,8 +70,10 @@ CPUFLAGS += PCLMULQDQ
 endif
 
 ifneq ($(filter $(AUTO_CPUFLAGS),__AVX__),)
+ifeq ($(CONFIG_RTE_ENABLE_AVX),y)
 CPUFLAGS += AVX
 endif
+endif
 
 ifneq ($(filter $(AUTO_CPUFLAGS),__RDRND__),)
 CPUFLAGS += RDRAND
@@ -86,12 +88,16 @@ CPUFLAGS += F16C
 endif
 
 ifneq ($(filter $(AUTO_CPUFLAGS),__AVX2__),)
+ifeq ($(CONFIG_RTE_ENABLE_AVX),y)
 CPUFLAGS += AVX2
 endif
+endif
 
 ifneq ($(filter $(AUTO_CPUFLAGS),__AVX512F__),)
+ifeq ($(CONFIG_RTE_ENABLE_AVX512),y)
 CPUFLAGS += AVX512F
 endif
+endif
 
 # IBM Power CPU flags
 ifneq ($(filter $(AUTO_CPUFLAGS),__PPC64__),)
-- 
2.7.4

  parent reply	other threads:[~2017-04-27 10:01 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-27 16:34 [dpdk-dev] [PATCH] " Zhihong Wang
2017-04-27  9:08 ` Thomas Monjalon
2017-04-27  9:18   ` Wang, Zhihong
2017-04-27  9:20     ` Thomas Monjalon
2017-04-27 10:03       ` Wang, Zhihong
2017-04-27 23:00 ` Zhihong Wang [this message]
2017-04-28  2:08   ` [dpdk-dev] [PATCH v2] " Yang, Zhiyong
2017-04-30 21:19     ` Thomas Monjalon
2017-04-28  5:07   ` Yuanhan Liu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1493334014-69488-1-git-send-email-zhihong.wang@intel.com \
    --to=zhihong.wang@intel.com \
    --cc=bruce.richardson@intel.com \
    --cc=dev@dpdk.org \
    --cc=thomas@monjalon.net \
    --cc=yuanhan.liu@linux.intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).