From b6c11d494e9b5ceaab75a5858b836e8a8ede41c0 Mon Sep 17 00:00:00 2001 From: Alexei Podtelezhnikov Date: Mon, 30 Aug 2021 07:09:53 -0400 Subject: [PATCH] [smooth] Reduce shift in multiply-shift optimization. * src/smooth/ftgrays.c (FT_UDIVPREP, FT_UDIV): Reduce shift. Smaller shifts that keep the division operands of FT_UDIVPREP within 32 bits result in slightly faster divisions, which is noticeable in the overall performance. The loss of precision is tolerable until the divisors (the components dx and dy) approach 32 - PIXEL_BITS. With PIXEL_BITS = 8, this corresponds to 65,000 pixels or the bitmap size that we refuse to render anyway. Using `ftbench -p -s60 -t5 -bc timesi.ttf`, Before: 8.52 us/op After: 8.32 us/op --- src/smooth/ftgrays.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/src/smooth/ftgrays.c b/src/smooth/ftgrays.c index 576dbb325..b8d680160 100644 --- a/src/smooth/ftgrays.c +++ b/src/smooth/ftgrays.c @@ -386,12 +386,10 @@ typedef ptrdiff_t FT_PtrDist; /* divisors to provide sufficient accuracy of the multiply-shift. */ /* It should not exceed (64 - PIXEL_BITS) to prevent overflowing and */ /* leave enough room for 64-bit unsigned multiplication however. */ -#define FT_UDIVPREP( c, b ) \ - FT_Int64 b ## _r = c ? (FT_Int64)( ~(FT_UInt64)0 >> PIXEL_BITS ) / ( b ) \ - : 0 -#define FT_UDIV( a, b ) \ - (TCoord)( ( (FT_UInt64)( a ) * (FT_UInt64)( b ## _r ) ) >> \ - ( sizeof( FT_UInt64 ) * FT_CHAR_BIT - PIXEL_BITS ) ) +#define FT_UDIVPREP( c, b ) \ + FT_Int64 b ## _r = c ? (FT_Int64)0xFFFFFFFF / ( b ) : 0 +#define FT_UDIV( a, b ) \ + (TCoord)( ( (FT_UInt64)( a ) * (FT_UInt64)( b ## _r ) ) >> 32 ) /* Scale area and apply fill rule to calculate the coverage byte. */