From: Brian Paul <brianp@vmware.com>
Date: Thu, 15 Oct 2015 17:54:06 +0000 (-0600)
Subject: st/mesa: optimize 4-component ubyte glDrawPixels
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=d11fefa96165836ffeed531a74319a64aa98a696;p=mesa.git

st/mesa: optimize 4-component ubyte glDrawPixels

If we didn't find a gallium surface format that exactly matched the
glDrawPixels format/type combination, we used some other 32-bit packed
RGBA format and swizzled the whole image in the mesa texstore/format code.

That slow path can be avoided in some common cases by using the
pipe_samper_view's swizzle terms to do the swizzling at texture sampling
time instead.

For now, only GL_RGBA/ubyte and GL_BGRA/ubyte combinations are supported.
In the future other formats and types like GL_UNSIGNED_INT_8_8_8_8 could
be added.

v2: fix incorrect swizzle setup (need to invert the tex format's swizzle)

Reviewed by: Jose Fonseca <jfonseca@vmware.com>
---

diff --git a/src/mesa/state_tracker/st_cb_drawpixels.c b/src/mesa/state_tracker/st_cb_drawpixels.c
index de7d1f6489a..262ad809c58 100644
--- a/src/mesa/state_tracker/st_cb_drawpixels.c
+++ b/src/mesa/state_tracker/st_cb_drawpixels.c
@@ -395,15 +395,35 @@ make_texture(struct st_context *st,
        * Note that the image is actually going to be upside down in
        * the texture.  We deal with that with texcoords.
        */
-      success = _mesa_texstore(ctx, 2,           /* dims */
-                               baseInternalFormat, /* baseInternalFormat */
-                               mformat,          /* mesa_format */
-                               transfer->stride, /* dstRowStride, bytes */
-                               &dest,            /* destSlices */
-                               width, height, 1, /* size */
-                               format, type,     /* src format/type */
-                               pixels,           /* data source */
-                               unpack);
+      if ((format == GL_RGBA || format == GL_BGRA)
+          && type == GL_UNSIGNED_BYTE) {
+         /* Use a memcpy-based texstore to avoid software pixel swizzling.
+          * We'll do the necessary swizzling with the pipe_sampler_view to
+          * give much better performance.
+          * XXX in the future, expand this to accomodate more format and
+          * type combinations.
+          */
+         _mesa_memcpy_texture(ctx, 2,
+                              mformat,          /* mesa_format */
+                              transfer->stride, /* dstRowStride, bytes */
+                              &dest,            /* destSlices */
+                              width, height, 1, /* size */
+                              format, type,     /* src format/type */
+                              pixels,           /* data source */
+                              unpack);
+         success = GL_TRUE;
+      }
+      else {
+         success = _mesa_texstore(ctx, 2,           /* dims */
+                                  baseInternalFormat, /* baseInternalFormat */
+                                  mformat,          /* mesa_format */
+                                  transfer->stride, /* dstRowStride, bytes */
+                                  &dest,            /* destSlices */
+                                  width, height, 1, /* size */
+                                  format, type,     /* src format/type */
+                                  pixels,           /* data source */
+                                  unpack);
+      }
 
       /* unmap */
       pipe_transfer_unmap(pipe, transfer);
@@ -957,6 +977,69 @@ clamp_size(struct pipe_context *pipe, GLsizei *width, GLsizei *height,
 }
 
 
+/**
+ * Search the array of 4 swizzle components for the named component and return
+ * its position.
+ */
+static unsigned
+search_swizzle(const unsigned char swizzle[4], unsigned component)
+{
+   unsigned i;
+   for (i = 0; i < 4; i++) {
+      if (swizzle[i] == component)
+         return i;
+   }
+   assert(!"search_swizzle() failed");
+   return 0;
+}
+
+
+/**
+ * Set the sampler view's swizzle terms.  This is used to handle RGBA
+ * swizzling when the incoming image format isn't an exact match for
+ * the actual texture format.  For example, if we have glDrawPixels(
+ * GL_RGBA, GL_UNSIGNED_BYTE) and we chose the texture format
+ * PIPE_FORMAT_B8G8R8A8 then we can do use the sampler view swizzle to
+ * avoid swizzling all the pixels in software in the texstore code.
+ */
+static void
+setup_sampler_swizzle(struct pipe_sampler_view *sv, GLenum format, GLenum type)
+{
+   if ((format == GL_RGBA || format == GL_BGRA) && type == GL_UNSIGNED_BYTE) {
+      const struct util_format_description *desc =
+         util_format_description(sv->texture->format);
+      unsigned c0, c1, c2, c3;
+
+      /* Every gallium driver supports at least one 32-bit packed RGBA format.
+       * We must have chosen one for (GL_RGBA, GL_UNSIGNED_BYTE).
+       */
+      assert(desc->block.bits == 32);
+
+      /* invert the format's swizzle to setup the sampler's swizzle */
+      if (format == GL_RGBA) {
+         c0 = UTIL_FORMAT_SWIZZLE_X;
+         c1 = UTIL_FORMAT_SWIZZLE_Y;
+         c2 = UTIL_FORMAT_SWIZZLE_Z;
+         c3 = UTIL_FORMAT_SWIZZLE_W;
+      }
+      else {
+         assert(format == GL_BGRA);
+         c0 = UTIL_FORMAT_SWIZZLE_Z;
+         c1 = UTIL_FORMAT_SWIZZLE_Y;
+         c2 = UTIL_FORMAT_SWIZZLE_X;
+         c3 = UTIL_FORMAT_SWIZZLE_W;
+      }
+      sv->swizzle_r = search_swizzle(desc->swizzle, c0);
+      sv->swizzle_g = search_swizzle(desc->swizzle, c1);
+      sv->swizzle_b = search_swizzle(desc->swizzle, c2);
+      sv->swizzle_a = search_swizzle(desc->swizzle, c3);
+   }
+   else {
+      /* use the default sampler swizzle */
+   }
+}
+
+
 /**
  * Called via ctx->Driver.DrawPixels()
  */
@@ -1046,6 +1129,9 @@ st_DrawPixels(struct gl_context *ctx, GLint x, GLint y,
       return;
    }
 
+   /* Set up the sampler view's swizzle */
+   setup_sampler_swizzle(sv[0], format, type);
+
    /* Create a second sampler view to read stencil.  The stencil is
     * written using the shader stencil export functionality.
     */