i965/cs: Set invocation counts based on max_cs_threads

For ES, we set the max counts based on SIMD8, which is currently
accurate.

For desktop GL, we set the max counts based on SIMD16, which can fail
in some cases where a SIMD16 program is not currently supported.
Therefore, this value is not currently accurate, but will work fine in
many cases, and lets us run more test cases. Eventually we want to
always be able to generate a SIMD16 program.

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>

diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c
index 029091e..1f0da35 100644 (file)
--- a/src/mesa/drivers/dri/i965/brw_context.c
+++ b/src/mesa/drivers/dri/i965/brw_context.c
@@ -612,6 +612,28 @@ brw_initialize_context_constants(struct brw_context *brw)
       ctx->Const.MaxVertexStreams = MIN2(4, MAX_VERTEX_STREAMS);
 }
 
+static void
+brw_adjust_cs_context_constants(struct brw_context *brw)
+{
+   struct gl_context *ctx = &brw->ctx;
+
+   /* For ES, we set these constants based on SIMD8.
+    *
+    * TODO: Once we can always generate SIMD16, we should update this.
+    *
+    * For GL, we assume we can generate a SIMD16 program, but this currently
+    * is not always true. This allows us to run more test cases, and will be
+    * required based on desktop GL compute shader requirements.
+    */
+   const simd_size = ctx->API == API_OPENGL_CORE ? 16 : 8;
+
+   const uint32_t max_invocations = simd_size * brw->max_cs_threads;
+   ctx->Const.MaxComputeWorkGroupSize[0] = max_invocations;
+   ctx->Const.MaxComputeWorkGroupSize[1] = max_invocations;
+   ctx->Const.MaxComputeWorkGroupSize[2] = max_invocations;
+   ctx->Const.MaxComputeWorkGroupInvocations = max_invocations;
+}
+
 /**
  * Process driconf (drirc) options, setting appropriate context flags.
  *
@@ -843,6 +865,8 @@ 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