From: Alexander Monakov <amonakov@ispras.ru>
Date: Mon, 11 Jan 2016 12:55:31 +0000 (+0300)
Subject: nvptx plugin: do not force JIT target SM version
X-Git-Tag: basepoints/gcc-7~1730
X-Git-Url: http://git.ipfire.org/?a=commitdiff_plain;h=0d58938ed798882063737dedfe897a9b484295ad;p=thirdparty%2Fgcc.git

nvptx plugin: do not force JIT target SM version

When link_ptx runs, a CUDA device is already bound to current thread, so the
driver library knows the target architecture.  There isn't any benefit from
forcing a specific target here; on the contrary, hardcoding sm_30 breaks
offloading on later (Maxwell, sm_5x) devices.

	* plugin/plugin-nvptx.c (link_ptx): Do not set CU_JIT_TARGET.

From-SVN: r232227
---

diff --git a/libgomp/ChangeLog b/libgomp/ChangeLog
index dbe181549c30..e2117259a118 100644
--- a/libgomp/ChangeLog
+++ b/libgomp/ChangeLog
@@ -1,3 +1,7 @@
+2016-01-11  Alexander Monakov  <amonakov@ispras.ru>
+
+	* plugin/plugin-nvptx.c (link_ptx): Do not set CU_JIT_TARGET.
+
 2016-01-07  H.J. Lu  <hongjiu.lu@intel.com>
 
 	PR fortran/66680
diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index 061842580676..7ec1810a0468 100644
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -712,8 +712,8 @@ static void
 link_ptx (CUmodule *module, const struct targ_ptx_obj *ptx_objs,
 	  unsigned num_objs)
 {
-  CUjit_option opts[7];
-  void *optvals[7];
+  CUjit_option opts[6];
+  void *optvals[6];
   float elapsed = 0.0;
 #define LOGSIZE 8192
   char elog[LOGSIZE];
@@ -742,10 +742,7 @@ link_ptx (CUmodule *module, const struct targ_ptx_obj *ptx_objs,
   opts[5] = CU_JIT_LOG_VERBOSE;
   optvals[5] = (void *) 1;
 
-  opts[6] = CU_JIT_TARGET;
-  optvals[6] = (void *) CU_TARGET_COMPUTE_30;
-
-  r = cuLinkCreate (7, opts, optvals, &linkstate);
+  r = cuLinkCreate (6, opts, optvals, &linkstate);
   if (r != CUDA_SUCCESS)
     GOMP_PLUGIN_fatal ("cuLinkCreate error: %s", cuda_error (r));