Mesa (master): st/mesa: expose ARB_compute_variable_group_size

[Samuel Pitoiset]

Module: Mesa
Branch: master
Commit: 590734fa0d2c97035eae33278cce6065c98b880f
URL:    http://cgit.freedesktop.org/mesa/mesa/commit/?id=590734fa0d2c97035eae33278cce6065c98b880f

Author: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Date:   Wed Sep  7 18:00:16 2016 +0200

st/mesa: expose ARB_compute_variable_group_size

This extension is only exposed if the underlying driver supports
ARB_compute_shader and if PIPE_COMPUTE_MAX_VARIABLE_THREADS_PER_BLOCK
is set.

v3: - initialize max_variable_threads_per_block to 0
v2: - expose the ext based on that new cap

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Reviewed-by: Marek Olšák <marek.olsak at amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle at amd.com>

---

 src/mesa/state_tracker/st_extensions.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/src/mesa/state_tracker/st_extensions.c b/src/mesa/state_tracker/st_extensions.c
index 2282dc7..b9befa1 100644
--- a/src/mesa/state_tracker/st_extensions.c
+++ b/src/mesa/state_tracker/st_extensions.c
@@ -1196,6 +1196,28 @@ void st_init_extensions(struct pipe_screen *screen,
          extensions->ARB_compute_shader =
                                       extensions->ARB_shader_image_load_store &&
                                       extensions->ARB_shader_atomic_counters;
+
+         if (extensions->ARB_compute_shader) {
+            uint64_t max_variable_threads_per_block = 0;
+
+            screen->get_compute_param(screen, PIPE_SHADER_IR_TGSI,
+                                      PIPE_COMPUTE_CAP_MAX_VARIABLE_THREADS_PER_BLOCK,
+                                      &max_variable_threads_per_block);
+
+            for (i = 0; i < 3; i++) {
+               /* Clamp the values to avoid having a local work group size
+                * greater than the maximum number of invocations.
+                */
+               consts->MaxComputeVariableGroupSize[i] =
+                  MIN2(consts->MaxComputeWorkGroupSize[i],
+                       max_variable_threads_per_block);
+            }
+            consts->MaxComputeVariableGroupInvocations =
+               max_variable_threads_per_block;
+
+            extensions->ARB_compute_variable_group_size =
+               max_variable_threads_per_block > 0;
+         }
       }
    }