[Mesa-dev] [PATCH v2 40/42] i965: Enable ARB_compute_shader extension on supported hardware

[Jordan Justen]

Enable ARB_compute_shader on gen7+, on hardware that supports the
OpenGL 4.3 requirements of a local group size of 1024.

With SIMD16 support, this is limited to Ivy Bridge and Haswell.

Broadwell will work with a local group size up to 896 on SIMD16
meaning programs that use this size or lower should run when setting
MESA_EXTENSION_OVERRIDE=GL_ARB_compute_shader.

Signed-off-by: Jordan Justen <jordan.l.justen at intel.com>
---
 src/mesa/drivers/dri/i965/brw_context.c      | 11 ++++++-----
 src/mesa/drivers/dri/i965/intel_extensions.c |  2 ++
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c
index 2ea0a9e..fc32a2f 100644
--- a/src/mesa/drivers/dri/i965/brw_context.c
+++ b/src/mesa/drivers/dri/i965/brw_context.c
@@ -330,7 +330,9 @@ brw_initialize_context_constants(struct brw_context *brw)
       [MESA_SHADER_TESS_EVAL] = false,
       [MESA_SHADER_GEOMETRY] = brw->gen >= 6,
       [MESA_SHADER_FRAGMENT] = true,
-      [MESA_SHADER_COMPUTE] = _mesa_extension_override_enables.ARB_compute_shader,
+      [MESA_SHADER_COMPUTE] =
+         (ctx->Const.MaxComputeWorkGroupSize[0] >= 1024) ||
+         _mesa_extension_override_enables.ARB_compute_shader,
    };
 
    unsigned num_stages = 0;
@@ -613,7 +615,7 @@ brw_initialize_context_constants(struct brw_context *brw)
 }
 
 static void
-brw_adjust_cs_context_constants(struct brw_context *brw)
+brw_initialize_cs_context_constants(struct brw_context *brw, unsigned max_threads)
 {
    struct gl_context *ctx = &brw->ctx;
 
@@ -627,7 +629,7 @@ brw_adjust_cs_context_constants(struct brw_context *brw)
     */
    const int simd_size = ctx->API == API_OPENGL_CORE ? 16 : 8;
 
-   const uint32_t max_invocations = simd_size * brw->max_cs_threads;
+   const uint32_t max_invocations = simd_size * max_threads;
    ctx->Const.MaxComputeWorkGroupSize[0] = max_invocations;
    ctx->Const.MaxComputeWorkGroupSize[1] = max_invocations;
    ctx->Const.MaxComputeWorkGroupSize[2] = max_invocations;
@@ -817,6 +819,7 @@ brwCreateContext(gl_api api,
    if (INTEL_DEBUG & DEBUG_PERF)
       brw->perf_debug = true;
 
+   brw_initialize_cs_context_constants(brw, devinfo->max_cs_threads);
    brw_initialize_context_constants(brw);
 
    ctx->Const.ResetStrategy = notify_reset
@@ -871,8 +874,6 @@ brwCreateContext(gl_api api,
    brw->urb.max_ds_entries = devinfo->urb.max_ds_entries;
    brw->urb.max_gs_entries = devinfo->urb.max_gs_entries;
 
-   brw_adjust_cs_context_constants(brw);
-
    /* Estimate the size of the mappable aperture into the GTT.  There's an
     * ioctl to get the whole GTT size, but not one to get the mappable subset.
     * It turns out it's basically always 256MB, though some ancient hardware
diff --git a/src/mesa/drivers/dri/i965/intel_extensions.c b/src/mesa/drivers/dri/i965/intel_extensions.c
index 81215db..6326cfc 100644
--- a/src/mesa/drivers/dri/i965/intel_extensions.c
+++ b/src/mesa/drivers/dri/i965/intel_extensions.c
@@ -356,6 +356,8 @@ intelInitExtensions(struct gl_context *ctx)
          ctx->Extensions.ARB_viewport_array = true;
          ctx->Extensions.AMD_vertex_shader_viewport_index = true;
          ctx->Extensions.ARB_shader_subroutine = true;
+         if (ctx->Const.MaxComputeWorkGroupSize[0] >= 1024)
+            ctx->Extensions.ARB_compute_shader = true;
       }
    }
 
-- 
2.6.2