qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Gerd Hoffmann <kraxel@redhat.com>
To: qemu-devel@nongnu.org
Cc: qemu-ppc@nongnu.org, Gerd Hoffmann <kraxel@redhat.com>
Subject: [PULL 05/13] sm501: Optimise 1 pixel 2d ops
Date: Wed,  1 Jul 2020 17:04:17 +0200	[thread overview]
Message-ID: <20200701150425.13739-6-kraxel@redhat.com> (raw)
In-Reply-To: <20200701150425.13739-1-kraxel@redhat.com>

From: BALATON Zoltan <balaton@eik.bme.hu>

Some guests do 1x1 blits which is faster to do directly than calling a
function for it so avoid overhead in this case.

Signed-off-by: BALATON Zoltan <balaton@eik.bme.hu>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Message-id: 7cccc302d7b4c5c313bad7681ac4686417143c3e.1592686588.git.balaton@eik.bme.hu
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
---
 hw/display/sm501.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/hw/display/sm501.c b/hw/display/sm501.c
index 3ced2c42db3a..2098e6981014 100644
--- a/hw/display/sm501.c
+++ b/hw/display/sm501.c
@@ -794,6 +794,14 @@ static void sm501_2d_operation(SM501State *s)
                 src_x == dst_x && src_y == dst_y) {
                 break;
             }
+            /* Some clients also do 1 pixel blits, avoid overhead for these */
+            if (width == 1 && height == 1) {
+                unsigned int si = (src_x + src_y * src_pitch) * bypp;
+                unsigned int di = (dst_x + dst_y * dst_pitch) * bypp;
+                stn_he_p(&s->local_mem[dst_base + di], bypp,
+                         ldn_he_p(&s->local_mem[src_base + si], bypp));
+                break;
+            }
             /* Check for overlaps, this could be made more exact */
             uint32_t sb, se, db, de;
             sb = src_base + src_x + src_y * (width + src_pitch);
@@ -842,9 +850,14 @@ static void sm501_2d_operation(SM501State *s)
             color = cpu_to_le16(color);
         }
 
-        pixman_fill((uint32_t *)&s->local_mem[dst_base],
-                    dst_pitch * bypp / sizeof(uint32_t),
-                    8 * bypp, dst_x, dst_y, width, height, color);
+        if (width == 1 && height == 1) {
+            unsigned int i = (dst_x + dst_y * dst_pitch) * bypp;
+            stn_he_p(&s->local_mem[dst_base + i], bypp, color);
+        } else {
+            pixman_fill((uint32_t *)&s->local_mem[dst_base],
+                        dst_pitch * bypp / sizeof(uint32_t),
+                        8 * bypp, dst_x, dst_y, width, height, color);
+        }
         break;
     }
     default:
-- 
2.18.4



  parent reply	other threads:[~2020-07-01 15:17 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-01 15:04 [PULL 00/13] Vga 20200701 patches Gerd Hoffmann
2020-07-01 15:04 ` [PULL 01/13] sm501: Fix bounds checks Gerd Hoffmann
2020-07-01 15:04 ` [PULL 02/13] sm501: Drop unneded variable Gerd Hoffmann
2020-07-01 15:04 ` [PULL 03/13] sm501: Ignore no-op blits Gerd Hoffmann
2020-07-01 15:04 ` [PULL 04/13] sm501: Introduce variable for commonly used value for better readability Gerd Hoffmann
2020-07-01 15:04 ` Gerd Hoffmann [this message]
2020-07-01 15:04 ` [PULL 06/13] sm501: Use stn_he_p/ldn_he_p instead of switch/case Gerd Hoffmann
2020-07-01 15:04 ` [PULL 07/13] sm501: Do not allow guest to set invalid format Gerd Hoffmann
2020-07-01 15:04 ` [PULL 08/13] sm501: Convert debug printfs to traces Gerd Hoffmann
2020-07-01 15:04 ` [PULL 09/13] sm501: Fix and optimize overlap check Gerd Hoffmann
2020-07-01 15:04 ` [PULL 10/13] ati-vga: Support unaligned access to hardware cursor registers Gerd Hoffmann
2020-07-01 15:04 ` [PULL 11/13] ati-vga: Do not assert on error Gerd Hoffmann
2020-07-01 15:04 ` [PULL 12/13] ati-vga: Add dummy MEM_SDRAM_MODE_REG Gerd Hoffmann
2020-07-01 15:04 ` [PULL 13/13] configure: vgabios cleanups Gerd Hoffmann
2020-07-02 14:53 ` [PULL 00/13] Vga 20200701 patches Peter Maydell

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=20200701150425.13739-6-kraxel@redhat.com \
    --to=kraxel@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-ppc@nongnu.org \
    /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).