From 8241b8edaf1f100b0d9f308fdf921b2ab548f3dc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Alex=20Villac=C3=ADs=20Lasso?= <a_villacis@palosanto.com>
Date: Fri, 16 Jan 2009 16:22:42 -0500
Subject: EXA: UTS Optimization

use one memcpy per scanline instead of a conditional inside
a loop for every dword
---
 src/savage_exa.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

(limited to 'src')

diff --git a/src/savage_exa.c b/src/savage_exa.c
index 7c6efb3..538e000 100644
--- a/src/savage_exa.c
+++ b/src/savage_exa.c
@@ -495,13 +495,21 @@ SavageUploadToScreen(PixmapPtr pDst, int x, int y, int w, int h, char *src, int
     dwords = (((w * Bpp) + 3) >> 2);
     for (i = 0; i < h; i++) {
 	srcp = (CARD32 *)src;
-	for (j = 0; j < dwords; j++) {
-	    if (queue < 4) {
-		BCI_RESET;
-		queue = 120 * 1024;
+
+	if (4 * dwords <= queue) {
+	    /* WARNING: breaking BCI_PTR abstraction here */
+	    memcpy(bci_ptr, srcp, 4 * dwords);
+	    bci_ptr += dwords;
+	    queue -= 4 * dwords;
+	} else {
+	    for (j = 0; j < dwords; j++) {
+		if (queue < 4) {
+		    BCI_RESET;
+		    queue = 120 * 1024;
+		}
+		BCI_SEND(*srcp++);
+		queue -= 4;
 	    }
-	    BCI_SEND(*srcp++);
-	    queue -= 4;
 	}
 	src += src_pitch;
     }
-- 
cgit v1.2.3