[libgomp, nvptx] Move device property sampling from nvptx_exec to nvptx_open

Move sampling of device properties from nvptx_exec to nvptx_open, and assume
the sampling always succeeds.  This simplifies the default dimension
initialization code in nvptx_open.

2018-07-26  Cesar Philippidis  <cesar@codesourcery.com>
	    Tom de Vries  <tdevries@suse.de>

	* plugin/plugin-nvptx.c (struct ptx_device): Add warp_size,
	max_threads_per_block and max_threads_per_multiprocessor fields.
	(nvptx_open_device): Initialize new fields.
	(nvptx_exec): Use num_sms, and new fields.

Co-Authored-By: Tom de Vries <tdevries@suse.de>
From-SVN: r262996

diff --git a/libgomp/ChangeLog b/libgomp/ChangeLog
index a3ed6ff2a20689dca5f0051226777e6916d88007..6c5ff91983d6745b45cc567aa23e14660cd607d2 100644 (file)
--- a/libgomp/ChangeLog
+++ b/libgomp/ChangeLog
@@ -1,3 +1,11 @@
+2018-07-26  Cesar Philippidis  <cesar@codesourcery.com>
+           Tom de Vries  <tdevries@suse.de>
+
+       * plugin/plugin-nvptx.c (struct ptx_device): Add warp_size,
+       max_threads_per_block and max_threads_per_multiprocessor fields.
+       (nvptx_open_device): Initialize new fields.
+       (nvptx_exec): Use num_sms, and new fields.
+
 2018-07-26  Tom de Vries  <tdevries@suse.de>
 
        * testsuite/libgomp.oacc-fortran/lib-12.f90: Move acc_async_test calls

diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index 89326e5774136f0b47289d9f3adb7ead4ed6aee7..5d9b5151e9534505c9e61d1bfc9c1d0718669d1c 100644 (file)
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -414,6 +414,9 @@ struct ptx_device
   int num_sms;
   int regs_per_block;
   int regs_per_sm;
+  int warp_size;
+  int max_threads_per_block;
+  int max_threads_per_multiprocessor;
 
   struct ptx_image_data *images;  /* Images loaded on device.  */
   pthread_mutex_t image_lock;     /* Lock for above list.  */
@@ -800,6 +803,15 @@ nvptx_open_device (int n)
       GOMP_PLUGIN_error ("Only warp size 32 is supported");
       return NULL;
     }
+  ptx_dev->warp_size = pi;
+
+  CUDA_CALL_ERET (NULL, cuDeviceGetAttribute, &pi,
+                 CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK, dev);
+  ptx_dev->max_threads_per_block = pi;
+
+  CUDA_CALL_ERET (NULL, cuDeviceGetAttribute, &pi,
+                 CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR, dev);
+  ptx_dev->max_threads_per_multiprocessor = pi;
 
   r = CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &async_engines,
                         CU_DEVICE_ATTRIBUTE_ASYNC_ENGINE_COUNT, dev);
@@ -1150,33 +1162,20 @@ nvptx_exec (void (*fn), size_t mapnum, void **hostaddrs, void **devaddrs,
          for (int i = 0; i < GOMP_DIM_MAX; ++i)
            default_dims[i] = GOMP_PLUGIN_acc_default_dim (i);
 
-         int warp_size, block_size, dev_size, cpu_size;
-         CUdevice dev = nvptx_thread()->ptx_dev->dev;
-         /* 32 is the default for known hardware.  */
-         int gang = 0, worker = 32, vector = 32;
-         CUdevice_attribute cu_tpb, cu_ws, cu_mpc, cu_tpm;
-
-         cu_tpb = CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_BLOCK;
-         cu_ws = CU_DEVICE_ATTRIBUTE_WARP_SIZE;
-         cu_mpc = CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT;
-         cu_tpm  = CU_DEVICE_ATTRIBUTE_MAX_THREADS_PER_MULTIPROCESSOR;
-
-         if (CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &block_size, cu_tpb,
-                                dev) == CUDA_SUCCESS
-             && CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &warp_size, cu_ws,
-                                   dev) == CUDA_SUCCESS
-             && CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &dev_size, cu_mpc,
-                                   dev) == CUDA_SUCCESS
-             && CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &cpu_size, cu_tpm,
-                                   dev) == CUDA_SUCCESS)
-           {
-             GOMP_PLUGIN_debug (0, " warp_size=%d, block_size=%d,"
-                                " dev_size=%d, cpu_size=%d\n",
-                                warp_size, block_size, dev_size, cpu_size);
-             gang = (cpu_size / block_size) * dev_size;
-             worker = block_size / warp_size;
-             vector = warp_size;
-           }
+         int gang, worker, vector;
+         {
+           int warp_size = nvthd->ptx_dev->warp_size;
+           int block_size = nvthd->ptx_dev->max_threads_per_block;
+           int cpu_size = nvthd->ptx_dev->max_threads_per_multiprocessor;
+           int dev_size = nvthd->ptx_dev->num_sms;
+           GOMP_PLUGIN_debug (0, " warp_size=%d, block_size=%d,"
+                              " dev_size=%d, cpu_size=%d\n",
+                              warp_size, block_size, dev_size, cpu_size);
+
+           gang = (cpu_size / block_size) * dev_size;
+           worker = block_size / warp_size;
+           vector = warp_size;
+         }
 
          /* There is no upper bound on the gang size.  The best size
             matches the hardware configuration.  Logical gangs are