[2/2] Query the driver directly for compute units and subslice

Commit Message

[e-mail] March 2, 2015, 11:42 p.m. UTC

From: Jeff McGee <[e-mail]>

Values of device max compute units and max subslice obtained
directly from the driver should be more accurate than our own
ID-based lookup values. This is particularly important when a
single device ID may encompass more than one configuration. If
the driver cannot provide a valid value for the given device,
we fallback on the ID-based lookup value.

Signed-off-by: Jeff McGee <[e-mail]>
---
 src/intel/intel_driver.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

Patch

diff --git a/src/intel/intel_driver.c b/src/intel/intel_driver.c
index d61988c..d99fea9 100644
--- a/src/intel/intel_driver.c
+++ b/src/intel/intel_driver.c
@@ -757,10 +757,8 @@  static int intel_buffer_set_tiling(cl_buffer bo,
 static void
 intel_update_device_info(cl_device_id device)
 {
-#ifdef HAS_USERPTR
   intel_driver_t *driver;
-  const size_t sz = 4096;
-  void *host_ptr;
+  unsigned int eu_total, subslice_total;
 
   driver = intel_driver_new();
   assert(driver != NULL);
@@ -769,6 +767,10 @@  intel_update_device_info(cl_device_id device)
     return;
   }
 
+#ifdef HAS_USERPTR
+  const size_t sz = 4096;
+  void *host_ptr;
+
   host_ptr = cl_aligned_malloc(sz, 4096);
   if (host_ptr != NULL) {
     cl_buffer bo = intel_buffer_alloc_userptr((cl_buffer_mgr)driver->bufmgr,
@@ -781,12 +783,18 @@  intel_update_device_info(cl_device_id device)
   }
   else
     device->host_unified_memory = CL_FALSE;
+#endif
+
+  /* Prefer driver-queried value if supported */
+  if (!drm_intel_get_eu_total(driver->fd, &eu_total))
+    device->max_compute_unit = eu_total;
+  if (!drm_intel_get_subslice_total(driver->fd, &subslice_total))
+    device->sub_slice_count = subslice_total;
 
   intel_driver_context_destroy(driver);
   intel_driver_close(driver);
   intel_driver_terminate(driver);
   intel_driver_delete(driver);
-#endif
 }
 
 LOCAL void