From 7c1d0a7bfba52ad078a0c383095a25cdba406d9d Mon Sep 17 00:00:00 2001
From: John Cupitt <jcupitt@gmail.com>
Date: Sun, 14 Mar 2010 20:12:41 +0000
Subject: [PATCH] scale output buffers with nthr for smalltile

---
 ChangeLog                     | 2 ++
 TODO                          | 6 ++++++
 libvips/iofuncs/region.c      | 3 +--
 libvips/iofuncs/threadgroup.c | 8 +++++++-
 4 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/ChangeLog b/ChangeLog
index 1a1b4d11..0ea4c39d 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -30,6 +30,8 @@
 - set VIPS_ICC_DIR in configure
 - ICC profiles are looked for in VIPS_ICC_DIR as a fallback
 - im_render() mask image generation no longer triggers image calc
+- threadgroups scale output buffers with number of threads for smalltile ...
+  improves SMP scaling for narrow images on many-way machines
 
 15/1/10 started 7.21.1
 - added "written" callbacks, used to implement write to non-vips formats
diff --git a/TODO b/TODO
index 0f94d31e..77a573c7 100644
--- a/TODO
+++ b/TODO
@@ -1,3 +1,9 @@
+- try
+
+	vips im_rot90 babe.jpg test2.v
+
+  wtf, thinstrip output o.O
+
 - doing im_create_fmask() and friends
 
 - how about im_invalidate_area()? we currently repaint the whole window on
diff --git a/libvips/iofuncs/region.c b/libvips/iofuncs/region.c
index 2bc17633..4a69aa11 100644
--- a/libvips/iofuncs/region.c
+++ b/libvips/iofuncs/region.c
@@ -460,9 +460,8 @@ im_region_buffer( REGION *reg, Rect *r )
 	 */
 	if( reg->invalid ) {
 		im_region_reset( reg );
-		if( !(reg->buffer = im_buffer_ref( im, &clipped )) ) 
+		if( !(reg->buffer = im_buffer_new( im, &clipped )) ) 
 			return( -1 );
-		im_buffer_undone( reg->buffer );
 	}
 	else {
 		/* Don't call im_region_reset() ... we combine buffer unref 
diff --git a/libvips/iofuncs/threadgroup.c b/libvips/iofuncs/threadgroup.c
index f9da7068..5151bf17 100644
--- a/libvips/iofuncs/threadgroup.c
+++ b/libvips/iofuncs/threadgroup.c
@@ -15,6 +15,8 @@
  * 	  work function
  * 22/10/09
  * 	- gtkdoc
+ * 14/3/10
+ * 	- scale nlines with nthr for smalltile
  */
 
 /*
@@ -588,7 +590,11 @@ im_threadgroup_create( IMAGE *im )
 	case IM_SMALLTILE:
 		tg->pw = im__tile_width;
 		tg->ph = im__tile_height;
-		tg->nlines = tg->ph;
+
+		/* Enough lines of tiles that we can expect to be able to keep
+		 * nthr busy.
+		 */
+		tg->nlines = tg->ph * (1 + tg->nthr / (tg->im->Xsize / tg->pw));
 		break;
 
 	case IM_FATSTRIP: