tgsi: clarify the semantics of DFRACEXP

The status quo is quite the mess:

1. tgsi_exec will do a per-channel computation, and store the dst[0]
   result (significand) correctly for each channel. The dst[1] result
   (exponent) will be written to the first bit set in the writemask.
   So per-component calculation only works partially.

2. r600 will only do a single computation. It will replicate the
   exponent but not the significand.

3. The docs pretend that there's per-component calculation, but even
   get dst[0] and dst[1] confused.

4. Luckily, st_glsl_to_tgsi only ever emits single-component instructions,
   and kind-of assumes that everything is replicated, generating this for
   the dvec4 case:

     DFRACEXP TEMP[0].xy, TEMP[1].x, CONST[0][0].xyxy
     DFRACEXP TEMP[0].zw, TEMP[1].y, CONST[0][0].zwzw
     DFRACEXP TEMP[2].xy, TEMP[1].z, CONST[0][1].xyxy
     DFRACEXP TEMP[2].zw, TEMP[1].w, CONST[0][1].zwzw

Settle on the simplest behavior, which is single-component calculation
with replication, document it, and adjust tgsi_exec and r600.

Reviewed-by: Marek Olšák <[email protected]>
Tested-by: Dieter Nützel <[email protected]>

1 files changed, 4 insertions, 6 deletions

diff --git a/src/gallium/docs/source/tgsi.rst b/src/gallium/docs/source/tgsi.rst
index 8633c929b9f..fd78c40ba3c 100644
--- a/src/gallium/docs/source/tgsi.rst
+++ b/src/gallium/docs/source/tgsi.rst
@@ -1838,17 +1838,15 @@ two-component vectors with doubled precision in each component.
 
 Like the ``frexp()`` routine in many math libraries, this opcode stores the
 exponent of its source to ``dst0``, and the significand to ``dst1``, such that
-:math:`dst1 \times 2^{dst0} = src` .
+:math:`dst1 \times 2^{dst0} = src` . The results are replicated across
+channels.
 
 .. math::
 
-  dst0.xy = exp(src.xy)
+  dst0.xy = dst.zw = frac(src.xy)
 
-  dst1.xy = frac(src.xy)
+  dst1 = frac(src.xy)
 
-  dst0.zw = exp(src.zw)
-
-  dst1.zw = frac(src.zw)
 
 .. opcode:: DLDEXP - Multiply Number by Integral Power of 2