radeonsi: Compute correct LDS size for fragment shaders.

No sure where the 36 came from, but we clearly need at least
48 bytes per attribute per primitive.

Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>

diff --git a/src/gallium/drivers/radeonsi/si_shader.c b/src/gallium/drivers/radeonsi/si_shader.c
index 49c498da61efc15fbac02e1912ae1d3a53b6695e..211db9f6f2fea2778e6c266f4385ad12ba480d61 100644 (file)
--- a/src/gallium/drivers/radeonsi/si_shader.c
+++ b/src/gallium/drivers/radeonsi/si_shader.c
@@ -5640,15 +5640,18 @@ static void si_shader_dump_stats(struct si_screen *sscreen,
 
        /* Compute LDS usage for PS. */
        if (processor == PIPE_SHADER_FRAGMENT) {
-               /* The minimum usage per wave is (num_inputs * 36). The maximum
-                * usage is (num_inputs * 36 * 16).
+               /* The minimum usage per wave is (num_inputs * 48). The maximum
+                * usage is (num_inputs * 48 * 16).
                 * We can get anything in between and it varies between waves.
                 *
+                * The 48 bytes per input for a single primitive is equal to
+                * 4 bytes/component * 4 components/input * 3 points.
+                *
                 * Other stages don't know the size at compile time or don't
                 * allocate LDS per wave, but instead they do it per thread group.
                 */
                lds_per_wave = conf->lds_size * lds_increment +
-                              align(num_inputs * 36, lds_increment);
+                              align(num_inputs * 48, lds_increment);
        }
 
        /* Compute the per-SIMD wave counts. */