[Mesa-dev] [PATCH 2/2] gallivm: handle srgb-to-linear and linear-to-srgb conversions

[sroland at vmware.com]

From: Roland Scheidegger <sroland at vmware.com>

srgb-to-linear is using 3rd degree polynomial for now which should be _just_
good enough. Reverse is using some rational polynomials and is quite accurate,
though not hooked into llvmpipe's blend code yet and hence unused (untested).
Using a table might also be an option (for srgb-to-linear especially).
This does not enable any new features yet because EXT_texture_srgb was already
supported via util_format fallbacks, but performance was lacking probably due
to the external function call (the table used by the util_format_srgb code may
not be all that much slower on its own).
Some performance figures (taken from modified gloss, replaced both base and
sphere texture to use GL_SRGB instead of GL_RGB, measured on 1Ghz Sandy Bridge,
the numbers aren't terribly accurate):

normal gloss, aos, 8-wide: 47 fps
normal gloss, aos, 4-wide: 48 fps

normal gloss, forced to soa, 8-wide: 48 fps
normal gloss, forced to soa, 4-wide: 47 fps

patched gloss, old code, soa, 8-wide: 21 fps
patched gloss, old code, soa, 4-wide: 24 fps

patched gloss, new code, soa, 8-wide: 41 fps
patched gloss, new code, soa, 4-wide: 38 fps

So there's a performance hit but it seems acceptable, certainly better
than using the fallback.
Note the new code only works for 4x8bit srgb formats, others (L8/L8A8) will
continue to use the old util_format fallback, because I can't be bothered
to write code for formats noone uses anyway (as decoding is done as part of
lp_build_unpack_rgba_soa which can only handle block type width of 32).
Compressed srgb formats should get their own path though eventually (it is
going to be expensive in any case, first decompress, then convert).
No piglit regressions.
---
 src/gallium/auxiliary/Makefile.sources            |    1 +
 src/gallium/auxiliary/gallivm/lp_bld_format.h     |   11 +++++++++
 src/gallium/auxiliary/gallivm/lp_bld_format_soa.c |   25 ++++++++++++++++-----
 3 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/src/gallium/auxiliary/Makefile.sources b/src/gallium/auxiliary/Makefile.sources
index 4751762..8cffeb0 100644
--- a/src/gallium/auxiliary/Makefile.sources
+++ b/src/gallium/auxiliary/Makefile.sources
@@ -172,6 +172,7 @@ GALLIVM_SOURCES := \
         gallivm/lp_bld_format_aos.c \
         gallivm/lp_bld_format_aos_array.c \
 	gallivm/lp_bld_format_float.c \
+        gallivm/lp_bld_format_srgb.c \
         gallivm/lp_bld_format_soa.c \
         gallivm/lp_bld_format_yuv.c \
         gallivm/lp_bld_gather.c \
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_format.h b/src/gallium/auxiliary/gallivm/lp_bld_format.h
index 12a0318..744d002 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_format.h
+++ b/src/gallium/auxiliary/gallivm/lp_bld_format.h
@@ -158,4 +158,15 @@ lp_build_rgb9e5_to_float(struct gallivm_state *gallivm,
                          LLVMValueRef src,
                          LLVMValueRef *dst);
 
+LLVMValueRef
+lp_build_linear_to_srgb(struct gallivm_state *gallivm,
+                        struct lp_type src_type,
+                        LLVMValueRef src);
+
+LLVMValueRef
+lp_build_srgb_to_linear(struct gallivm_state *gallivm,
+                        struct lp_type src_type,
+                        LLVMValueRef src);
+
+
 #endif /* !LP_BLD_FORMAT_H */
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_format_soa.c b/src/gallium/auxiliary/gallivm/lp_bld_format_soa.c
index 4c6bd81..114ce03 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_format_soa.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_format_soa.c
@@ -163,11 +163,23 @@ lp_build_unpack_rgba_soa(struct gallivm_state *gallivm,
           */
 
          if (type.floating) {
-            if(format_desc->channel[chan].normalized)
-               input = lp_build_unsigned_norm_to_float(gallivm, width, type, input);
-            else
-               input = LLVMBuildSIToFP(builder, input,
-                                       lp_build_vec_type(gallivm, type), "");
+            if (format_desc->colorspace == UTIL_FORMAT_COLORSPACE_SRGB) {
+               assert(width == 8);
+               if (format_desc->swizzle[3] == chan) {
+                  input = lp_build_unsigned_norm_to_float(gallivm, width, type, input);
+               }
+               else {
+                  struct lp_type conv_type = lp_uint_type(type);
+                  input = lp_build_srgb_to_linear(gallivm, conv_type, input);
+               }
+            }
+            else {
+               if(format_desc->channel[chan].normalized)
+                  input = lp_build_unsigned_norm_to_float(gallivm, width, type, input);
+               else
+                  input = LLVMBuildSIToFP(builder, input,
+                                          lp_build_vec_type(gallivm, type), "");
+            }
          }
          else if (format_desc->channel[chan].pure_integer) {
             /* Nothing to do */
@@ -344,6 +356,7 @@ lp_build_fetch_rgba_soa(struct gallivm_state *gallivm,
 
    if (format_desc->layout == UTIL_FORMAT_LAYOUT_PLAIN &&
        (format_desc->colorspace == UTIL_FORMAT_COLORSPACE_RGB ||
+        format_desc->colorspace == UTIL_FORMAT_COLORSPACE_SRGB ||
         format_desc->colorspace == UTIL_FORMAT_COLORSPACE_ZS) &&
        format_desc->block.width == 1 &&
        format_desc->block.height == 1 &&
@@ -394,7 +407,7 @@ lp_build_fetch_rgba_soa(struct gallivm_state *gallivm,
       packed = lp_build_gather(gallivm, type.length,
                                format_desc->block.bits,
                                type.width, base_ptr, offset,
-			       FALSE);
+                               FALSE);
       if (format_desc->format == PIPE_FORMAT_R11G11B10_FLOAT) {
          lp_build_r11g11b10_to_float(gallivm, packed, rgba_out);
       }
-- 
1.7.9.5