[dpdk-dev,v2,01/20] mk: change to cortex-a72

Message ID 1494851864-26029-2-git-send-email-hemant.agrawal@nxp.com (mailing list archive)
State Changes Requested, archived
Delegated to: Ferruh Yigit
Headers

Checks

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

Commit Message

Hemant Agrawal May 15, 2017, 12:37 p.m. UTC
  Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
---
 config/defconfig_arm64-dpaa2-linuxapp-gcc | 2 +-
 mk/machine/dpaa2/rte.vars.mk              | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
  

Comments

Ferruh Yigit May 15, 2017, 4:49 p.m. UTC | #1
On 5/15/2017 1:37 PM, Hemant Agrawal wrote:
> Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
> ---
>  config/defconfig_arm64-dpaa2-linuxapp-gcc | 2 +-
>  mk/machine/dpaa2/rte.vars.mk              | 2 +-
>  2 files changed, 2 insertions(+), 2 deletions(-)
> 
> diff --git a/config/defconfig_arm64-dpaa2-linuxapp-gcc b/config/defconfig_arm64-dpaa2-linuxapp-gcc
> index 314a0ec..2304ab6 100644
> --- a/config/defconfig_arm64-dpaa2-linuxapp-gcc
> +++ b/config/defconfig_arm64-dpaa2-linuxapp-gcc
> @@ -34,7 +34,7 @@
>  
>  # NXP (Freescale) - Soc Architecture with WRIOP and QBMAN support
>  CONFIG_RTE_MACHINE="dpaa2"
> -CONFIG_RTE_ARCH_ARM_TUNE="cortex-a57+fp+simd"
> +CONFIG_RTE_ARCH_ARM_TUNE="cortex-a72"

Can you please describe reasoning and effect in commit log:

What will happen when cortex-a72 used instead of cortex-a57+fp+simd? And
what is the motivation for change?

Thanks,
ferruh
  
Hemant Agrawal May 16, 2017, 3:06 p.m. UTC | #2
On 5/15/2017 10:19 PM, Ferruh Yigit wrote:
> On 5/15/2017 1:37 PM, Hemant Agrawal wrote:
>> Signed-off-by: Hemant Agrawal <hemant.agrawal@nxp.com>
>> ---
>>  config/defconfig_arm64-dpaa2-linuxapp-gcc | 2 +-
>>  mk/machine/dpaa2/rte.vars.mk              | 2 +-
>>  2 files changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/config/defconfig_arm64-dpaa2-linuxapp-gcc b/config/defconfig_arm64-dpaa2-linuxapp-gcc
>> index 314a0ec..2304ab6 100644
>> --- a/config/defconfig_arm64-dpaa2-linuxapp-gcc
>> +++ b/config/defconfig_arm64-dpaa2-linuxapp-gcc
>> @@ -34,7 +34,7 @@
>>
>>  # NXP (Freescale) - Soc Architecture with WRIOP and QBMAN support
>>  CONFIG_RTE_MACHINE="dpaa2"
>> -CONFIG_RTE_ARCH_ARM_TUNE="cortex-a57+fp+simd"
>> +CONFIG_RTE_ARCH_ARM_TUNE="cortex-a72"
>
> Can you please describe reasoning and effect in commit log:
>
> What will happen when cortex-a72 used instead of cortex-a57+fp+simd? And
> what is the motivation for change?
>

We will update the commit log for this and other patches as you commented.

W.r.t this patch, the revision of  LS2 devices now have cortex-a72, we 
have stopped A57.  fp and simd is no more required to be stated 
explicitly and supported by default in standard a72 core.

Regards,
Hemant

> Thanks,
> ferruh
>
  

Patch

diff --git a/config/defconfig_arm64-dpaa2-linuxapp-gcc b/config/defconfig_arm64-dpaa2-linuxapp-gcc
index 314a0ec..2304ab6 100644
--- a/config/defconfig_arm64-dpaa2-linuxapp-gcc
+++ b/config/defconfig_arm64-dpaa2-linuxapp-gcc
@@ -34,7 +34,7 @@ 
 
 # NXP (Freescale) - Soc Architecture with WRIOP and QBMAN support
 CONFIG_RTE_MACHINE="dpaa2"
-CONFIG_RTE_ARCH_ARM_TUNE="cortex-a57+fp+simd"
+CONFIG_RTE_ARCH_ARM_TUNE="cortex-a72"
 
 #
 # Compile Environment Abstraction Layer
diff --git a/mk/machine/dpaa2/rte.vars.mk b/mk/machine/dpaa2/rte.vars.mk
index a60819f..675cd5a 100644
--- a/mk/machine/dpaa2/rte.vars.mk
+++ b/mk/machine/dpaa2/rte.vars.mk
@@ -57,5 +57,5 @@ 
 MACHINE_CFLAGS += -march=armv8-a+crc
 
 ifdef CONFIG_RTE_ARCH_ARM_TUNE
-MACHINE_CFLAGS += -mcpu=$(CONFIG_RTE_ARCH_ARM_TUNE:"%"=%)
+MACHINE_CFLAGS += -mtune=$(CONFIG_RTE_ARCH_ARM_TUNE:"%"=%)
 endif