shithub: riscv

Download patch

ref: e0cf0261d0f81eb1c54c4d4a7636c27de4b00d36
parent: b0e2ea4e5ffaec335c2a61ee98d2c5d3f1052569
author: cinap_lenrek <cinap_lenrek@felloff.net>
date: Sun Apr 25 08:16:40 EDT 2021

resample: improve performance (thanks José Miguel Sánchez García)

Resample is well known for taking a long time to resize an image. This
patch brings an important performance boost (in my test image, time
was reduced from ~2850ms to ~500ms). It does that by extracting FP
multiplication and division out of the innermost loop of
resamplex/resampley.

The results differ slightly from the current implementation: in my
test: ~0.3% of the bytes had a ±2 difference in their value, which I
attribute to rounding errors. I'm personally not concerned with that
deviation, given the performance gains. However, I recommend testing
it just to be sure I didn't overlook anything.

José Miguel Sánchez García

--- a/sys/src/cmd/resample.c
+++ b/sys/src/cmd/resample.c
@@ -67,10 +67,10 @@
 resamplex(uchar *in, int off, int d, int inx, uchar *out, int outx)
 {
 	int i, x, k;
-	double X, xx, v, rat;
+	double X, xx, v, rat, rato10;
 
-
 	rat = (double)inx/(double)outx;
+	rato10 = rat/10.;
 	for(x=0; x<outx; x++){
 		if(inx == outx){
 			/* don't resample if size unchanged */
@@ -79,8 +79,8 @@
 		}
 		v = 0.0;
 		X = x*rat;
+		xx = X + rato10*(-K2);
 		for(k=-K2; k<=K2; k++){
-			xx = X + rat*k/10.;
 			i = xx;
 			if(i < 0)
 				i = 0;
@@ -87,6 +87,7 @@
 			if(i >= inx)
 				i = inx-1;
 			v += in[off+i*d] * K[K2+k];
+			xx += rato10;
 		}
 		out[off+x*d] = v;
 	}
@@ -96,9 +97,10 @@
 resampley(uchar **in, int off, int iny, uchar **out, int outy)
 {
 	int y, i, k;
-	double Y, yy, v, rat;
+	double Y, yy, v, rat, rato10;
 
 	rat = (double)iny/(double)outy;
+	rato10 = rat/10.;
 	for(y=0; y<outy; y++){
 		if(iny == outy){
 			/* don't resample if size unchanged */
@@ -107,8 +109,8 @@
 		}
 		v = 0.0;
 		Y = y*rat;
+		yy = Y + rato10*(-K2);
 		for(k=-K2; k<=K2; k++){
-			yy = Y + rat*k/10.;
 			i = yy;
 			if(i < 0)
 				i = 0;
@@ -115,6 +117,7 @@
 			if(i >= iny)
 				i = iny-1;
 			v += in[i][off] * K[K2+k];
+			yy += rato10;
 		}
 		out[y][off] = v;
 	}