rygorous

#include <stdio.h>
#include <stdint.h>
#include <stdlib.h>
#include <string.h>

static uint32_t float_to_bits(float x)
{
	uint32_t u;
	memcpy(&u, &x, sizeof(x));
	return u;

rygorous

	// ep1 - ep0 >= 0: four-interpolated color mode
	// ep1 - ep0 < 0: six-interpolated-color mode
	//
	// we want to avoid ep0 = ep1 in general (because it gives us no useful
	// interpolated values). That means in four-interp mode we want ep1 - ep0 > 0,
	// and in six-interp mode we want ep1 - ep0 < 0. If they're identical or
	// have the wrong sign, we need to fix it!
	int ep_diff = ((ep1_int - ep0_int) ^ target_sign) - target_sign;
	if (ep_diff <= 0)
	{

rygorous

template <int t_nbits>
static inline void quant_endpoint_with_pbit(U8 *deq0, U8 *deq1, int val)
{
	const int expanded_nbits = t_nbits + 1;
	const U32 range = 1u << expanded_nbits;
	const U32 recip255 = 0x8081; // enough bits for our value range
	const int postscale = (0x10000 >> t_nbits) + (0x10000 >> (t_nbits*2 + 1));

	// The reconstruction here adds the pbit as the lowest bit and then reconstructs
	// it as a (nbits+1)-bit value to float, i.e. (quant*2 + pbit) / (range - 1).

rygorous

File Type: DLL

  Section contains the following imports:

    KERNEL32.dll
             180085000 Import Address Table
             18009B1B8 Import Name Table
                     0 time date stamp
                     0 Index of first forwarder reference

rygorous

inName : c:\devel\media\verybig\enwik9
inSize64 : 1000000000
building LRM...
done!
ref_sink: 0x9f93e2e0
SimpleProf         :seconds    calls     count :     clk/call    clk/count
search_one         :  1.2668        1   8388480 : 5320774726.0       634.30
search_one_pf      :  0.9975        1   8388480 : 4189319442.0       499.41
search_multi2      :  1.1072        1   8388480 : 4650070068.0       554.34
search_multi4      :  1.1205        1   8388480 : 4706202060.0       561.03

rygorous

  00000000000001BC: D2802009  mov         x9,#0x100
  00000000000001C0: F2C00809  movk        x9,#0x40,lsl #0x20
  00000000000001C4: F90003E9  str         x9,[sp]
  00000000000001C8: D2800209  mov         x9,#0x10
  00000000000001CC: F2C00089  movk        x9,#4,lsl #0x20
  00000000000001D0: F90007E9  str         x9,[sp,#8]
  00000000000001D4: 58000869  ldr         x9,$LN356
  00000000000001D8: F9000BE9  str         x9,[sp,#0x10]
  00000000000001DC: 58000869  ldr         x9,$LN357
  00000000000001E0: F9000FE9  str         x9,[sp,#0x18]

rygorous

---- "Low" effort level (OodleTex_EncodeEffortLevel_Low = 10)

CompressBCN      : 5.258 millis
kodim01.bmp BC7-RGB: rmse=2.4325 hash=0x5dcf9106f8f4415d
CompressBCN      : 5.040 millis
kodim02.bmp BC7-RGB: rmse=2.1168 hash=0x79f45423cd9d3ec0
CompressBCN      : 5.165 millis
kodim03.bmp BC7-RGB: rmse=1.6793 hash=0x806dce71d1ff8293
CompressBCN      : 5.092 millis
kodim04.bmp BC7-RGB: rmse=2.1611 hash=0x681ebb3045e254ec

rygorous

    // advance
    for (int i = 0; i < num_streams; ++i)
    {
        std::string desc = formatf("advance %d", i);
        bool is_reverse_stream = (i % 3) == 1;
        if (EARLY_CLZ != 2)
        {
            if (EARLY_CLZ == 0)
                bb->append(CLZ(bits[i], bits[i]).set_comment(desc)); // figure out how many bits we consumed
            if (is_reverse_stream)

rygorous

void bc7_encode_single_color_block(U8 * output_bc7, const U8 rgba[4])
{
	U64 r = rgba[0];
	U64 g = rgba[1];
	U64 b = rgba[2];
	U64 a = rgba[3];

	const U64 bit6_mask = (0x40 << 8) | (0x40 << 22) | (0x40ull << 36);
	const U64 lo7_mask  = (0x7f << 8) | (0x7f << 22) | (0x7full << 36);
	U64 color_bits;

rygorous

reading: c:\devel\media\bc1speedlevel/M_MED_Kurohomura_Backpack_Textures_T_Kurohomura_BP_backpack_D.uasset_build.mip0.png
CompressBC7      : 65.720 millis, 3.51 kc/B, rate= 997.20 kB/s
per-pixel rmse : 0.6425
mode stats (8=invalid 9=solid):
[0]     567 (  0.87%)
[1]    5465 (  8.34%)
[2]     126 (  0.19%)
[3]   15855 ( 24.19%)
[4]     909 (  1.39%)
[5]   15072 ( 23.00%)