[PATCH 2/2 v2] Query the driver directly for compute units and subslice

[jeff.mcgee at intel.com]

From: Jeff McGee <jeff.mcgee at intel.com>

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.

This query requires libdrm 2.4.60. For now we will consider
the use of this query to be optional and exclude it from
compilation when building against older libdrm. Later we may
want to consider requiring the query or at least warning
more strongly when it is not supported.

v2: Make feature use conditional on libdrm version (Zhigang).

Signed-off-by: Jeff McGee <jeff.mcgee at intel.com>
---
 CMakeLists.txt           |  9 +++++++++
 src/CMakeLists.txt       | 10 ++++++++++
 src/intel/intel_driver.c | 25 +++++++++++++++++++++----
 3 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 65f2c70..bb03566 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -131,6 +131,15 @@ IF(DRM_INTEL_FOUND)
   ELSE(DRM_INTEL_VERSION VERSION_GREATER 2.4.57)
     MESSAGE(STATUS "Disable userptr support")
   ENDIF(DRM_INTEL_VERSION VERSION_GREATER 2.4.57)
+  IF(DRM_INTEL_VERSION VERSION_GREATER 2.4.59)
+    MESSAGE(STATUS "Enable EU total query support")
+    SET(DRM_INTEL_EU_TOTAL "enable")
+    MESSAGE(STATUS "Enable subslice total query support")
+    SET(DRM_INTEL_SUBSLICE_TOTAL "enable")
+  ELSE(DRM_INTEL_VERSION VERSION_GREATER 2.4.59)
+    MESSAGE(STATUS "Disable EU total query support")
+    MESSAGE(STATUS "Disable subslice total query support")
+  ENDIF(DRM_INTEL_VERSION VERSION_GREATER 2.4.59)
 ELSE(DRM_INTEL_FOUND)
   MESSAGE(FATAL_ERROR "Looking for DRM Intel (>= 2.4.52) - not found")
 ENDIF(DRM_INTEL_FOUND)
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt
index d4181d8..464765f 100644
--- a/src/CMakeLists.txt
+++ b/src/CMakeLists.txt
@@ -118,6 +118,16 @@ SET(CMAKE_CXX_FLAGS "-DHAS_USERPTR ${CMAKE_CXX_FLAGS}")
 SET(CMAKE_C_FLAGS "-DHAS_USERPTR ${CMAKE_C_FLAGS}")
 endif (DRM_INTEL_USERPTR)
 
+if (DRM_INTEL_EU_TOTAL)
+SET(CMAKE_CXX_FLAGS "-DHAS_EU_TOTAL ${CMAKE_CXX_FLAGS}")
+SET(CMAKE_C_FLAGS "-DHAS_EU_TOTAL ${CMAKE_C_FLAGS}")
+endif (DRM_INTEL_EU_TOTAL)
+
+if (DRM_INTEL_SUBSLICE_TOTAL)
+SET(CMAKE_CXX_FLAGS "-DHAS_SUBSLICE_TOTAL ${CMAKE_CXX_FLAGS}")
+SET(CMAKE_C_FLAGS "-DHAS_SUBSLICE_TOTAL ${CMAKE_C_FLAGS}")
+endif (DRM_INTEL_SUBSLICE_TOTAL)
+
 set(GIT_SHA1 "git_sha1.h")
 add_custom_target(${GIT_SHA1} ALL
   COMMAND chmod +x ${CMAKE_CURRENT_SOURCE_DIR}/git_sha1.sh
diff --git a/src/intel/intel_driver.c b/src/intel/intel_driver.c
index d61988c..755ab6b 100644
--- a/src/intel/intel_driver.c
+++ b/src/intel/intel_driver.c
@@ -757,10 +757,7 @@ 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;
 
   driver = intel_driver_new();
   assert(driver != NULL);
@@ -769,6 +766,10 @@ 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 +782,28 @@ intel_update_device_info(cl_device_id device)
   }
   else
     device->host_unified_memory = CL_FALSE;
+#endif
+
+#ifdef HAS_EU_TOTAL
+  unsigned int eu_total;
+
+  /* Prefer driver-queried max compute units if supported */
+  if (!drm_intel_get_eu_total(driver->fd, &eu_total))
+    device->max_compute_unit = eu_total;
+#endif
+
+#ifdef HAS_SUBSLICE_TOTAL
+  unsigned int subslice_total;
+
+  /* Prefer driver-queried subslice count if supported */
+  if (!drm_intel_get_subslice_total(driver->fd, &subslice_total))
+    device->sub_slice_count = subslice_total;
+#endif
 
   intel_driver_context_destroy(driver);
   intel_driver_close(driver);
   intel_driver_terminate(driver);
   intel_driver_delete(driver);
-#endif
 }
 
 LOCAL void
-- 
2.3.0