Gavin, That's impressive problem-solving and analytical work.
However, for performance reasons the pre-increment (and pre-decrement) operators are preferable unless one actually needs to obtain a variable's value before updating it. void fasterUnsignedCharToFloatString(unsigned char uc, char* out) { const unsigned char* data = unsignedCharToFloatData[uc]; *out = '0' + (uc == 255); *++out = '.'; *++out = '0' + (data[0] >> 4); *++out = '0' + (data[0] & 0xF); *++out = '0' + (data[1] >> 4); *++out = '0' + (data[1] & 0xF); *++out = '0' + (data[2] >> 4); *++out = '0' + (data[2] & 0xF); // Remove trailing zeros. while (*out == '0') --out; if (*out == '.') --out; *++out = '\0'; } was ~20% faster on my machine. Alfonso On Wed, Nov 4, 2015 at 1:29 AM, Gavin Barraclough <barraclo...@apple.com> wrote: > I’m too addicted to this. > > I tested a few variants of BCD conversion, and based on some quick > benchmarking on my machine it appears any would be a 40X – 50X improvement > compared to an equivalent sprintf(_, “%f”, x/255.0). > > The following chart shows the speedup, table size required to hold the > BCD, and resulting string lengths for a few different policies. > > *Precision* > *Speedup vs* > *sprintf* > *Table Size* > *String Length,* > *Min* > *String Length,* > *Average* > *String Length,* > *Max* > *default,* > *with trailing zeros* > ~50X > 768 bytes > 8 > 8 > 8 > *default,* > *no trailing zeros* > ~40X > 768 bytes > 1 > 7.8 > 8 > *±1% tolerance* > ~40X > 768 bytes > 1 > 6.1 > 7 > *±5% tolerance* > ~45X > 512 bytes > 1 > 5.5 > 6 > *minimal* > ~45X > 512 bytes > 1 > 4.5 > 5 > > The first configuration matches printf default precision. > The second maintains the same accuracy but strips trailing zeros. > The third ensures accuracy within ±1% of the granularity of the step > between values – so 1 converts to 0.003922 ±0.00003922, and 2 converts to > 0.007843 ±0.00003922, etc. > The fourth is similar, with slightly looser tolerance. > The fifth is the minimal precision required for values to round trip. > > Code for default precision with no trailing zeros below. > > cheers, > G. > > > > void unsignedCharToFloatString(unsigned char uc, char* out) > { > const unsigned char* data = unsignedCharToFloatData[uc]; > > *out++ = uc == 255 ? '1' : '0'; > *out++ = '.'; > *out++ = '0' + (data[0] >> 4); > *out++ = '0' + (data[0] & 0xF); > *out++ = '0' + (data[1] >> 4); > *out++ = '0' + (data[1] & 0xF); > *out++ = '0' + (data[2] >> 4); > *out++ = '0' + (data[2] & 0xF); > > // Remove trailing zeros. > while (out[-1] == '0') > --out; > if (out[-1] == '.') > --out; > > *out = '\0'; > } > > static const unsigned char unsignedCharToFloatData[256][3] = { > { 0x00, 0x00, 0x00 }, > { 0x00, 0x39, 0x22 }, > { 0x00, 0x78, 0x43 }, > { 0x01, 0x17, 0x65 }, > { 0x01, 0x56, 0x86 }, > { 0x01, 0x96, 0x08 }, > { 0x02, 0x35, 0x29 }, > { 0x02, 0x74, 0x51 }, > { 0x03, 0x13, 0x73 }, > { 0x03, 0x52, 0x94 }, > { 0x03, 0x92, 0x16 }, > { 0x04, 0x31, 0x37 }, > { 0x04, 0x70, 0x59 }, > { 0x05, 0x09, 0x80 }, > { 0x05, 0x49, 0x02 }, > { 0x05, 0x88, 0x24 }, > { 0x06, 0x27, 0x45 }, > { 0x06, 0x66, 0x67 }, > { 0x07, 0x05, 0x88 }, > { 0x07, 0x45, 0x10 }, > { 0x07, 0x84, 0x31 }, > { 0x08, 0x23, 0x53 }, > { 0x08, 0x62, 0x75 }, > { 0x09, 0x01, 0x96 }, > { 0x09, 0x41, 0x18 }, > { 0x09, 0x80, 0x39 }, > { 0x10, 0x19, 0x61 }, > { 0x10, 0x58, 0x82 }, > { 0x10, 0x98, 0x04 }, > { 0x11, 0x37, 0x25 }, > { 0x11, 0x76, 0x47 }, > { 0x12, 0x15, 0x69 }, > { 0x12, 0x54, 0x90 }, > { 0x12, 0x94, 0x12 }, > { 0x13, 0x33, 0x33 }, > { 0x13, 0x72, 0x55 }, > { 0x14, 0x11, 0x76 }, > { 0x14, 0x50, 0x98 }, > { 0x14, 0x90, 0x20 }, > { 0x15, 0x29, 0x41 }, > { 0x15, 0x68, 0x63 }, > { 0x16, 0x07, 0x84 }, > { 0x16, 0x47, 0x06 }, > { 0x16, 0x86, 0x27 }, > { 0x17, 0x25, 0x49 }, > { 0x17, 0x64, 0x71 }, > { 0x18, 0x03, 0x92 }, > { 0x18, 0x43, 0x14 }, > { 0x18, 0x82, 0x35 }, > { 0x19, 0x21, 0x57 }, > { 0x19, 0x60, 0x78 }, > { 0x20, 0x00, 0x00 }, > { 0x20, 0x39, 0x22 }, > { 0x20, 0x78, 0x43 }, > { 0x21, 0x17, 0x65 }, > { 0x21, 0x56, 0x86 }, > { 0x21, 0x96, 0x08 }, > { 0x22, 0x35, 0x29 }, > { 0x22, 0x74, 0x51 }, > { 0x23, 0x13, 0x73 }, > { 0x23, 0x52, 0x94 }, > { 0x23, 0x92, 0x16 }, > { 0x24, 0x31, 0x37 }, > { 0x24, 0x70, 0x59 }, > { 0x25, 0x09, 0x80 }, > { 0x25, 0x49, 0x02 }, > { 0x25, 0x88, 0x24 }, > { 0x26, 0x27, 0x45 }, > { 0x26, 0x66, 0x67 }, > { 0x27, 0x05, 0x88 }, > { 0x27, 0x45, 0x10 }, > { 0x27, 0x84, 0x31 }, > { 0x28, 0x23, 0x53 }, > { 0x28, 0x62, 0x75 }, > { 0x29, 0x01, 0x96 }, > { 0x29, 0x41, 0x18 }, > { 0x29, 0x80, 0x39 }, > { 0x30, 0x19, 0x61 }, > { 0x30, 0x58, 0x82 }, > { 0x30, 0x98, 0x04 }, > { 0x31, 0x37, 0x25 }, > { 0x31, 0x76, 0x47 }, > { 0x32, 0x15, 0x69 }, > { 0x32, 0x54, 0x90 }, > { 0x32, 0x94, 0x12 }, > { 0x33, 0x33, 0x33 }, > { 0x33, 0x72, 0x55 }, > { 0x34, 0x11, 0x76 }, > { 0x34, 0x50, 0x98 }, > { 0x34, 0x90, 0x20 }, > { 0x35, 0x29, 0x41 }, > { 0x35, 0x68, 0x63 }, > { 0x36, 0x07, 0x84 }, > { 0x36, 0x47, 0x06 }, > { 0x36, 0x86, 0x27 }, > { 0x37, 0x25, 0x49 }, > { 0x37, 0x64, 0x71 }, > { 0x38, 0x03, 0x92 }, > { 0x38, 0x43, 0x14 }, > { 0x38, 0x82, 0x35 }, > { 0x39, 0x21, 0x57 }, > { 0x39, 0x60, 0x78 }, > { 0x40, 0x00, 0x00 }, > { 0x40, 0x39, 0x22 }, > { 0x40, 0x78, 0x43 }, > { 0x41, 0x17, 0x65 }, > { 0x41, 0x56, 0x86 }, > { 0x41, 0x96, 0x08 }, > { 0x42, 0x35, 0x29 }, > { 0x42, 0x74, 0x51 }, > { 0x43, 0x13, 0x73 }, > { 0x43, 0x52, 0x94 }, > { 0x43, 0x92, 0x16 }, > { 0x44, 0x31, 0x37 }, > { 0x44, 0x70, 0x59 }, > { 0x45, 0x09, 0x80 }, > { 0x45, 0x49, 0x02 }, > { 0x45, 0x88, 0x24 }, > { 0x46, 0x27, 0x45 }, > { 0x46, 0x66, 0x67 }, > { 0x47, 0x05, 0x88 }, > { 0x47, 0x45, 0x10 }, > { 0x47, 0x84, 0x31 }, > { 0x48, 0x23, 0x53 }, > { 0x48, 0x62, 0x75 }, > { 0x49, 0x01, 0x96 }, > { 0x49, 0x41, 0x18 }, > { 0x49, 0x80, 0x39 }, > { 0x50, 0x19, 0x61 }, > { 0x50, 0x58, 0x82 }, > { 0x50, 0x98, 0x04 }, > { 0x51, 0x37, 0x25 }, > { 0x51, 0x76, 0x47 }, > { 0x52, 0x15, 0x69 }, > { 0x52, 0x54, 0x90 }, > { 0x52, 0x94, 0x12 }, > { 0x53, 0x33, 0x33 }, > { 0x53, 0x72, 0x55 }, > { 0x54, 0x11, 0x76 }, > { 0x54, 0x50, 0x98 }, > { 0x54, 0x90, 0x20 }, > { 0x55, 0x29, 0x41 }, > { 0x55, 0x68, 0x63 }, > { 0x56, 0x07, 0x84 }, > { 0x56, 0x47, 0x06 }, > { 0x56, 0x86, 0x27 }, > { 0x57, 0x25, 0x49 }, > { 0x57, 0x64, 0x71 }, > { 0x58, 0x03, 0x92 }, > { 0x58, 0x43, 0x14 }, > { 0x58, 0x82, 0x35 }, > { 0x59, 0x21, 0x57 }, > { 0x59, 0x60, 0x78 }, > { 0x60, 0x00, 0x00 }, > { 0x60, 0x39, 0x22 }, > { 0x60, 0x78, 0x43 }, > { 0x61, 0x17, 0x65 }, > { 0x61, 0x56, 0x86 }, > { 0x61, 0x96, 0x08 }, > { 0x62, 0x35, 0x29 }, > { 0x62, 0x74, 0x51 }, > { 0x63, 0x13, 0x73 }, > { 0x63, 0x52, 0x94 }, > { 0x63, 0x92, 0x16 }, > { 0x64, 0x31, 0x37 }, > { 0x64, 0x70, 0x59 }, > { 0x65, 0x09, 0x80 }, > { 0x65, 0x49, 0x02 }, > { 0x65, 0x88, 0x24 }, > { 0x66, 0x27, 0x45 }, > { 0x66, 0x66, 0x67 }, > { 0x67, 0x05, 0x88 }, > { 0x67, 0x45, 0x10 }, > { 0x67, 0x84, 0x31 }, > { 0x68, 0x23, 0x53 }, > { 0x68, 0x62, 0x75 }, > { 0x69, 0x01, 0x96 }, > { 0x69, 0x41, 0x18 }, > { 0x69, 0x80, 0x39 }, > { 0x70, 0x19, 0x61 }, > { 0x70, 0x58, 0x82 }, > { 0x70, 0x98, 0x04 }, > { 0x71, 0x37, 0x25 }, > { 0x71, 0x76, 0x47 }, > { 0x72, 0x15, 0x69 }, > { 0x72, 0x54, 0x90 }, > { 0x72, 0x94, 0x12 }, > { 0x73, 0x33, 0x33 }, > { 0x73, 0x72, 0x55 }, > { 0x74, 0x11, 0x76 }, > { 0x74, 0x50, 0x98 }, > { 0x74, 0x90, 0x20 }, > { 0x75, 0x29, 0x41 }, > { 0x75, 0x68, 0x63 }, > { 0x76, 0x07, 0x84 }, > { 0x76, 0x47, 0x06 }, > { 0x76, 0x86, 0x27 }, > { 0x77, 0x25, 0x49 }, > { 0x77, 0x64, 0x71 }, > { 0x78, 0x03, 0x92 }, > { 0x78, 0x43, 0x14 }, > { 0x78, 0x82, 0x35 }, > { 0x79, 0x21, 0x57 }, > { 0x79, 0x60, 0x78 }, > { 0x80, 0x00, 0x00 }, > { 0x80, 0x39, 0x22 }, > { 0x80, 0x78, 0x43 }, > { 0x81, 0x17, 0x65 }, > { 0x81, 0x56, 0x86 }, > { 0x81, 0x96, 0x08 }, > { 0x82, 0x35, 0x29 }, > { 0x82, 0x74, 0x51 }, > { 0x83, 0x13, 0x73 }, > { 0x83, 0x52, 0x94 }, > { 0x83, 0x92, 0x16 }, > { 0x84, 0x31, 0x37 }, > { 0x84, 0x70, 0x59 }, > { 0x85, 0x09, 0x80 }, > { 0x85, 0x49, 0x02 }, > { 0x85, 0x88, 0x24 }, > { 0x86, 0x27, 0x45 }, > { 0x86, 0x66, 0x67 }, > { 0x87, 0x05, 0x88 }, > { 0x87, 0x45, 0x10 }, > { 0x87, 0x84, 0x31 }, > { 0x88, 0x23, 0x53 }, > { 0x88, 0x62, 0x75 }, > { 0x89, 0x01, 0x96 }, > { 0x89, 0x41, 0x18 }, > { 0x89, 0x80, 0x39 }, > { 0x90, 0x19, 0x61 }, > { 0x90, 0x58, 0x82 }, > { 0x90, 0x98, 0x04 }, > { 0x91, 0x37, 0x25 }, > { 0x91, 0x76, 0x47 }, > { 0x92, 0x15, 0x69 }, > { 0x92, 0x54, 0x90 }, > { 0x92, 0x94, 0x12 }, > { 0x93, 0x33, 0x33 }, > { 0x93, 0x72, 0x55 }, > { 0x94, 0x11, 0x76 }, > { 0x94, 0x50, 0x98 }, > { 0x94, 0x90, 0x20 }, > { 0x95, 0x29, 0x41 }, > { 0x95, 0x68, 0x63 }, > { 0x96, 0x07, 0x84 }, > { 0x96, 0x47, 0x06 }, > { 0x96, 0x86, 0x27 }, > { 0x97, 0x25, 0x49 }, > { 0x97, 0x64, 0x71 }, > { 0x98, 0x03, 0x92 }, > { 0x98, 0x43, 0x14 }, > { 0x98, 0x82, 0x35 }, > { 0x99, 0x21, 0x57 }, > { 0x99, 0x60, 0x78 }, > { 0x00, 0x00, 0x00 }, > }; > > > > > > On Nov 3, 2015, at 11:37 AM, Darin Adler <da...@apple.com> wrote: > > On Nov 3, 2015, at 11:10 AM, Maciej Stachowiak <m...@apple.com> wrote: > > Minimal strings should round trip ok, but will it still be accurate enough > if the client attempts to do math with them? > > > I was thinking about the same thing this morning. > > If we don’t want them minimal, then how many digits of precision would be > the right number? I think we currently are just using the printf default > precision. > > — Darin > _______________________________________________ > webkit-dev mailing list > webkit-dev@lists.webkit.org > https://lists.webkit.org/mailman/listinfo/webkit-dev > > > > _______________________________________________ > webkit-dev mailing list > webkit-dev@lists.webkit.org > https://lists.webkit.org/mailman/listinfo/webkit-dev > >
_______________________________________________ webkit-dev mailing list webkit-dev@lists.webkit.org https://lists.webkit.org/mailman/listinfo/webkit-dev