head	1.1;
branch	1.1.1;
access;
symbols
	netbsd-11-0-RC5:1.1.1.1
	netbsd-11-0-RC4:1.1.1.1
	netbsd-11-0-RC3:1.1.1.1
	netbsd-11-0-RC2:1.1.1.1
	netbsd-11-0-RC1:1.1.1.1
	netbsd-11:1.1.1.1.0.4
	netbsd-11-base:1.1.1.1
	netbsd-10-1-RELEASE:1.1.1.1
	netbsd-10-0-RELEASE:1.1.1.1
	netbsd-10-0-RC6:1.1.1.1
	netbsd-10-0-RC5:1.1.1.1
	netbsd-10-0-RC4:1.1.1.1
	netbsd-10-0-RC3:1.1.1.1
	netbsd-10-0-RC2:1.1.1.1
	netbsd-10-0-RC1:1.1.1.1
	netbsd-10:1.1.1.1.0.2
	netbsd-10-base:1.1.1.1
	mesa-21-3-7:1.1.1.1
	mesalib-19-1-7:1.1.1.1
	xorg:1.1.1;
locks; strict;
comment	@# @;


1.1
date	2019.09.24.16.40.25;	author maya;	state Exp;
branches
	1.1.1.1;
next	;
commitid	KJXusGl8fi9AAhEB;

1.1.1.1
date	2019.09.24.16.40.25;	author maya;	state Exp;
branches;
next	;
commitid	KJXusGl8fi9AAhEB;


desc
@@


1.1
log
@Initial revision
@
text
@/* Compile with:
 *
 * glsl_compiler --version 400 --dump-builder int64.glsl > builtin_int64.h
 *
 * Version 4.00+ is required for umulExtended.
 */
#version 400
#extension GL_ARB_gpu_shader_int64: require
#extension GL_ARB_shading_language_420pack: require

uvec2
umul64(uvec2 a, uvec2 b)
{
   uvec2 result;

   umulExtended(a.x, b.x, result.y, result.x);
   result.y += a.x * b.y + a.y * b.x;

   return result;
}

ivec2
sign64(ivec2 a)
{
   ivec2 result;

   result.y = a.y >> 31;
   result.x = result.y | int((a.x | a.y) != 0);

   return result;
}

uvec4
udivmod64(uvec2 n, uvec2 d)
{
   uvec2 quot = uvec2(0U, 0U);
   int log2_denom = findMSB(d.y) + 32;

   /* If the upper 32 bits of denom are non-zero, it is impossible for shifts
    * greater than 32 bits to occur.  If the upper 32 bits of the numerator
    * are zero, it is impossible for (denom << [63, 32]) <= numer unless
    * denom == 0.
    */
   if (d.y == 0 && n.y >= d.x) {
      log2_denom = findMSB(d.x);

      /* Since the upper 32 bits of denom are zero, log2_denom <= 31 and we
       * don't have to compare log2_denom inside the loop as is done in the
       * general case (below).
       */
      for (int i = 31; i >= 1; i--) {
	 if (log2_denom <= 31 - i && (d.x << i) <= n.y) {
	    n.y -= d.x << i;
	    quot.y |= 1U << i;
	 }
      }

      /* log2_denom is always <= 31, so manually peel the last loop
       * iteration.
       */
      if (d.x <= n.y) {
	 n.y -= d.x;
	 quot.y |= 1U;
      }
   }

   uint64_t d64 = packUint2x32(d);
   uint64_t n64 = packUint2x32(n);
   for (int i = 31; i >= 1; i--) {
      if (log2_denom <= 63 - i && (d64 << i) <= n64) {
	 n64 -= d64 << i;
	 quot.x |= 1U << i;
      }
   }

   /* log2_denom is always <= 63, so manually peel the last loop
    * iteration.
    */
   if (d64 <= n64) {
      n64 -= d64;
      quot.x |= 1U;
   }

   return uvec4(quot, unpackUint2x32(n64));
}

uvec2
udiv64(uvec2 n, uvec2 d)
{
   return udivmod64(n, d).xy;
}

ivec2
idiv64(ivec2 _n, ivec2 _d)
{
   const bool negate = (_n.y < 0) != (_d.y < 0);
   uvec2 n = unpackUint2x32(uint64_t(abs(packInt2x32(_n))));
   uvec2 d = unpackUint2x32(uint64_t(abs(packInt2x32(_d))));

   uvec2 quot = udivmod64(n, d).xy;

   return negate ? unpackInt2x32(-int64_t(packUint2x32(quot))) : ivec2(quot);
}

uvec2
umod64(uvec2 n, uvec2 d)
{
   return udivmod64(n, d).zw;
}

ivec2
imod64(ivec2 _n, ivec2 _d)
{
   const bool negate = (_n.y < 0) != (_d.y < 0);
   uvec2 n = unpackUint2x32(uint64_t(abs(packInt2x32(_n))));
   uvec2 d = unpackUint2x32(uint64_t(abs(packInt2x32(_d))));

   uvec2 rem = udivmod64(n, d).zw;

   return negate ? unpackInt2x32(-int64_t(packUint2x32(rem))) : ivec2(rem);
}
@


1.1.1.1
log
@Import mesa 19.1.7

New features in mesa 19.1.0:

    GL_ARB_parallel_shader_compile on all drivers.
    GL_EXT_gpu_shader4 on all GL 3.1 drivers.
    GL_EXT_shader_image_load_formatted on radeonsi.
    GL_EXT_texture_buffer_object on all GL 3.1 drivers.
    GL_EXT_texture_compression_s3tc_srgb on Gallium drivers and i965 (ES extension).
    GL_NV_compute_shader_derivatives on iris and i965.
    GL_KHR_parallel_shader_compile on all drivers.
    VK_EXT_buffer_device_address on Intel and RADV.
    VK_EXT_depth_clip_enable on Intel and RADV.
    VK_KHR_ycbcr_image_arrays on Intel.
    VK_EXT_inline_uniform_block on Intel and RADV.
    VK_EXT_external_memory_host on Intel.
    VK_EXT_host_query_reset on Intel and RADV.
    VK_KHR_surface_protected_capabilities on Intel and RADV.
    VK_EXT_pipeline_creation_feedback on Intel and RADV.
    VK_KHR_8bit_storage on RADV.
    VK_AMD_gpu_shader_int16 on RADV.
    VK_AMD_gpu_shader_half_float on RADV.
    VK_NV_compute_shader_derivatives on Intel.
    VK_KHR_shader_float16_int8 on Intel and RADV (RADV only supports int8).
    VK_KHR_shader_atomic_int64 on Intel.
    VK_EXT_descriptor_indexing on Intel.
    VK_KHR_shader_float16_int8 on Intel and RADV.
    GL_INTEL_conservative_rasterization on iris.
    VK_EXT_memory_budget on Intel.

New features in mesa 19.0.0:

    GL_AMD_texture_texture4 on all GL 4.0 drivers.
    GL_EXT_shader_implicit_conversions on all drivers (ES extension).
    GL_EXT_texture_compression_bptc on all GL 4.0 drivers (ES extension).
    GL_EXT_texture_compression_rgtc on all GL 3.0 drivers (ES extension).
    GL_EXT_render_snorm on gallium drivers (ES extension).
    GL_EXT_texture_view on drivers supporting texture views (ES extension).
    GL_OES_texture_view on drivers supporting texture views (ES extension).
    GL_NV_shader_atomic_float on nvc0 (Fermi/Kepler only).
    Shader-based software implementations of GL_ARB_gpu_shader_fp64, GL_ARB_gpu_shader_int64, GL_ARB_vertex_attrib_64bit, and GL_ARB_shader_ballot on i965.
    VK_ANDROID_external_memory_android_hardware_buffer on Intel
    Fixed and re-exposed VK_EXT_pci_bus_info on Intel and RADV
    VK_EXT_scalar_block_layout on Intel and RADV
    VK_KHR_depth_stencil_resolve on Intel
    VK_KHR_draw_indirect_count on Intel
    VK_EXT_conditional_rendering on Intel
    VK_EXT_memory_budget on RADV

Also, bug fixes.
@
text
@@