From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com (mga14.intel.com [192.55.52.115]) by gabe.freedesktop.org (Postfix) with ESMTPS id 15AD810E072 for ; Tue, 25 Jul 2023 10:17:23 +0000 (UTC) Content-Type: multipart/alternative; boundary="------------8TxquYcxs2w6qxML8a00K435" Message-ID: <74f54cd8-cbeb-a97f-9af1-4b64072ad2d6@intel.com> Date: Tue, 25 Jul 2023 15:46:19 +0530 Content-Language: en-US To: =?UTF-8?Q?Zbigniew_Kempczy=c5=84ski?= References: <20230718121443.445343-1-kunal1.joshi@intel.com> <20230718121443.445343-3-kunal1.joshi@intel.com> <20230720100245.2lref6sw6j7btr7k@zkempczy-mobl2> From: "Joshi, Kunal1" In-Reply-To: <20230720100245.2lref6sw6j7btr7k@zkempczy-mobl2> MIME-Version: 1.0 Subject: Re: [igt-dev] [PATCH i-g-t 2/2] lib/igt_fb: on xe driver switch from rendercopy to blitcopy List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: igt-dev@lists.freedesktop.org Errors-To: igt-dev-bounces@lists.freedesktop.org Sender: "igt-dev" List-ID: --------------8TxquYcxs2w6qxML8a00K435 Content-Type: text/plain; charset="UTF-8"; format=flowed Content-Transfer-Encoding: 8bit On 7/20/2023 3:32 PM, Zbigniew Kempczyński wrote: > On Tue, Jul 18, 2023 at 05:44:43PM +0530, Kunal Joshi wrote: >> on xe driver use blitcopy for everything where otherwise would >> use rendercopy. >> >> Signed-off-by: Juha-Pekka Heikkila >> --- >> lib/igt_fb.c | 8 +++----- >> 1 file changed, 3 insertions(+), 5 deletions(-) >> >> diff --git a/lib/igt_fb.c b/lib/igt_fb.c >> index 6ce4b735a..f4bc800fe 100644 >> --- a/lib/igt_fb.c >> +++ b/lib/igt_fb.c >> @@ -2529,7 +2529,7 @@ static bool use_enginecopy(const struct igt_fb *fb) >> if (!is_intel_device(fb->fd)) >> return false; >> >> - if (!is_xe_device(fb->fd) && blitter_ok(fb)) >> + if (blitter_ok(fb)) >> return false; > I stared to this and for me it looks we disable rendercopy at all > for i915 as well for xe even if rendercopy is same for i915 and xe > (intel-bb should handle this). > > -- > Zbigniew > Hello Zbigniew, Blitter is preferred over render copy for perf/power and render copy is preferred for feature. JP's changes are considering that fact. With this info does this patch look good? Thanks and Regards Kunal Joshi --------------8TxquYcxs2w6qxML8a00K435 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: 8bit

On 7/20/2023 3:32 PM, Zbigniew Kempczyński wrote:

On Tue, Jul 18, 2023 at 05:44:43PM +0530, Kunal Joshi wrote:

on xe driver use blitcopy for everything where otherwise would
use rendercopy.

Signed-off-by: Juha-Pekka Heikkila <juhapekka.heikkila@gmail.com>
---
 lib/igt_fb.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/lib/igt_fb.c b/lib/igt_fb.c
index 6ce4b735a..f4bc800fe 100644
--- a/lib/igt_fb.c
+++ b/lib/igt_fb.c
@@ -2529,7 +2529,7 @@ static bool use_enginecopy(const struct igt_fb *fb)
 	if (!is_intel_device(fb->fd))
 		return false;
 
-	if (!is_xe_device(fb->fd) && blitter_ok(fb))
+	if (blitter_ok(fb))
 		return false;

I stared to this and for me it looks we disable rendercopy at all
for i915 as well for xe even if rendercopy is same for i915 and xe
(intel-bb should handle this).

--
Zbigniew

Hello Zbigniew,

Blitter is preferred over render copy for perf/power and render copy is preferred for feature.
JP's changes are considering that fact. With this info does this patch look good?

Thanks and Regards
Kunal Joshi

--------------8TxquYcxs2w6qxML8a00K435--