[Mesa-dev] [PATCH 2/2] i965/tex_image: Flush certain subnormal ASTC channel values

[Nanley Chery]

On Fri, Apr 22, 2016 at 04:23:59PM -0700, Kenneth Graunke wrote:
> On Tuesday, April 12, 2016 3:30:14 PM PDT Nanley Chery wrote:
> > From: Nanley Chery <nanley.g.chery at intel.com>
> > 
> > When uploading a linear, void-extent, ASTC LDR block on Skylake, we are
> > required to flush to zero the UNORM16 channel values that would be
> > denormalized. This is specifically required for the values: 1, 2, and 3.
> > 
> > Fixes the 14 failing tests in:
> >    dEQP-GLES3.functional.texture.compressed.astc.void_extent_ldr.*
> > 
> > v2: Split out flushing function (Kristian Høgsberg)
> > 
> > Signed-off-by: Nanley Chery <nanley.g.chery at intel.com>
> > ---
> >  src/mesa/drivers/dri/i965/intel_tex_image.c | 87 ++++++++++++++++++++++++++
> +++
> >  1 file changed, 87 insertions(+)
> > 
> > diff --git a/src/mesa/drivers/dri/i965/intel_tex_image.c b/src/mesa/drivers/
> dri/i965/intel_tex_image.c
> > index 1601edd..9a26450 100644
> > --- a/src/mesa/drivers/dri/i965/intel_tex_image.c
> > +++ b/src/mesa/drivers/dri/i965/intel_tex_image.c
> > @@ -5,6 +5,7 @@
> >  #include "main/bufferobj.h"
> >  #include "main/context.h"
> >  #include "main/formats.h"
> > +#include "main/glformats.h"
> >  #include "main/image.h"
> >  #include "main/pbo.h"
> >  #include "main/renderbuffer.h"
> > @@ -511,10 +512,96 @@ intel_get_tex_sub_image(struct gl_context *ctx,
> >     DBG("%s - DONE\n", __func__);
> >  }
> >  
> > +static void
> > +flush_astc_denorms(struct gl_context *ctx, GLuint dims,
> > +                   struct gl_texture_image *texImage,
> > +                   GLint xoffset, GLint yoffset, GLint zoffset,
> > +                   GLsizei width, GLsizei height, GLsizei depth)
> > +{
> > +   struct compressed_pixelstore store;
> > +   _mesa_compute_compressed_pixelstore(dims, texImage->TexFormat,
> > +                                       width, height, depth,
> > +                                       &ctx->Unpack, &store);
> > +
> > +   for (int slice = 0; slice < store.CopySlices; slice++) {
> > +
> > +      /* Map dest texture buffer */
> > +      GLubyte *dstMap;
> > +      GLint dstRowStride;
> > +      ctx->Driver.MapTextureImage(ctx, texImage, slice + zoffset,
> > +                                  xoffset, yoffset, width, height,
> > +                                  GL_MAP_WRITE_BIT | 
> GL_MAP_INVALIDATE_RANGE_BIT,
> 
> It looks like you're reading the data from the buffer and rewriting it,
> so shouldn't this be GL_MAP_READ_BIT | GL_MAP_WRITE_BIT?
> 

Thanks for catching this. It was leftover from a copy-paste of the
_mesa_store_compressed_texsubimage function internals.

- Nanley

> With that fixed, this patch is:
> Acked-by: Kenneth Graunke <kenneth at whitecape.org>
> 
> > +                                  &dstMap, &dstRowStride);
> > +      if (!dstMap)
> > +         continue;
> > +
> > +      for (int i = 0; i < store.CopyRowsPerSlice; i++) {
> > +
> > +         /* An ASTC block is stored in little endian mode. The byte that
> > +          * contains bits 0..7 is stored at the lower address in memory.
> > +          */
> > +         struct astc_void_extent {
> > +            uint16_t header : 12;
> > +            uint16_t dontcare[3];
> > +            uint16_t R;
> > +            uint16_t G;
> > +            uint16_t B;
> > +            uint16_t A;
> > +         } *blocks = (struct astc_void_extent*) dstMap;
> > +
> > +         /* Iterate over every copied block in the row */
> > +         for (int j = 0; j < store.CopyBytesPerRow / 16; j++) {
> > +
> > +            /* Check if the header matches that of an LDR void-extent block 
> */
> > +            if (blocks[j].header == 0xDFC) {
> > +
> > +               /* Flush UNORM16 values that would be denormalized */
> > +               if (blocks[j].A < 4) blocks[j].A = 0;
> > +               if (blocks[j].B < 4) blocks[j].B = 0;
> > +               if (blocks[j].G < 4) blocks[j].G = 0;
> > +               if (blocks[j].R < 4) blocks[j].R = 0;
> > +            }
> > +         }
> > +
> > +         dstMap += dstRowStride;
> > +      }
> > +
> > +      ctx->Driver.UnmapTextureImage(ctx, texImage, slice + zoffset);
> > +   }
> > +}
> > +
> > +
> > +static void
> > +intelCompressedTexSubImage(struct gl_context *ctx, GLuint dims,
> > +                        struct gl_texture_image *texImage,
> > +                        GLint xoffset, GLint yoffset, GLint zoffset,
> > +                        GLsizei width, GLsizei height, GLsizei depth,
> > +                        GLenum format,
> > +                        GLsizei imageSize, const GLvoid *data)
> > +{
> > +   /* Upload the compressed data blocks */
> > +   _mesa_store_compressed_texsubimage(ctx, dims, texImage,
> > +                                      xoffset, yoffset, zoffset,
> > +                                      width, height, depth,
> > +                                      format, imageSize, data);
> > +
> > +   /* Fix up copied ASTC blocks if necessary */
> > +   GLenum gl_format = _mesa_compressed_format_to_glenum(ctx,
> > +                                                        texImage-
> >TexFormat);
> > +   bool is_linear_astc = _mesa_is_astc_format(gl_format) &&
> > +                        !_mesa_is_srgb_format(gl_format);
> > +   struct brw_context *brw = (struct brw_context*) ctx;
> > +   if (brw->gen == 9 && is_linear_astc)
> > +      flush_astc_denorms(ctx, dims, texImage,
> > +                         xoffset, yoffset, zoffset,
> > +                         width, height, depth);
> > +}
> > +
> >  void
> >  intelInitTextureImageFuncs(struct dd_function_table *functions)
> >  {
> >     functions->TexImage = intelTexImage;
> > +   functions->CompressedTexSubImage = intelCompressedTexSubImage;
> >     functions->EGLImageTargetTexture2D = intel_image_target_texture_2d;
> >     functions->BindRenderbufferTexImage = intel_bind_renderbuffer_tex_image;
> >     functions->GetTexSubImage = intel_get_tex_sub_image;
> > 
>