diff mbox series

[v5,5/6] libgomp, nvptx: Cuda pinned memory

Message ID 20240612114223.2206735-6-ams@baylibre.com
State New
Headers show
Series libgomp: OpenMP pinned memory for omp_alloc | expand

Commit Message

Andrew Stubbs June 12, 2024, 11:42 a.m. UTC
This patch was already approved, in the v3 posting by Tobias Burnus
(with one caveat about initialization location), but wasn't committed at
that time as I didn't want to disentangle it from the textual
dependencies on the other patches in the series.

------

Use Cuda to pin memory, instead of Linux mlock, when available.

There are two advantages: firstly, this gives a significant speed boost for
NVPTX offloading, and secondly, it side-steps the usual OS ulimit/rlimit
setting.

The design adds a device independent plugin API for allocating pinned memory,
and then implements it for NVPTX.  At present, the other supported devices do
not have equivalent capabilities (or requirements).

libgomp/ChangeLog:

	* config/linux/allocator.c: Include assert.h.
	(using_device_for_page_locked): New variable.
	(linux_memspace_alloc): Add init0 parameter. Support device pinning.
	(linux_memspace_calloc): Set init0 to true.
	(linux_memspace_free): Support device pinning.
	(linux_memspace_realloc): Support device pinning.
	(MEMSPACE_ALLOC): Set init0 to false.
	* libgomp-plugin.h
	(GOMP_OFFLOAD_page_locked_host_alloc): New prototype.
	(GOMP_OFFLOAD_page_locked_host_free): Likewise.
	* libgomp.h (gomp_page_locked_host_alloc): Likewise.
	(gomp_page_locked_host_free): Likewise.
	(struct gomp_device_descr): Add page_locked_host_alloc_func and
	page_locked_host_free_func.
	* libgomp.texi: Adjust the docs for the pinned trait.
	* libgomp_g.h (GOMP_enable_pinned_mode): New prototype.
	* plugin/plugin-nvptx.c
	(GOMP_OFFLOAD_page_locked_host_alloc): New function.
	(GOMP_OFFLOAD_page_locked_host_free): Likewise.
	* target.c (device_for_page_locked): New variable.
	(get_device_for_page_locked): New function.
	(gomp_page_locked_host_alloc): Likewise.
	(gomp_page_locked_host_free): Likewise.
	(gomp_load_plugin_for_device): Add page_locked_host_alloc and
	page_locked_host_free.
	* testsuite/libgomp.c/alloc-pinned-1.c: Change expectations for NVPTX
	devices.
	* testsuite/libgomp.c/alloc-pinned-2.c: Likewise.
	* testsuite/libgomp.c/alloc-pinned-3.c: Likewise.
	* testsuite/libgomp.c/alloc-pinned-4.c: Likewise.
	* testsuite/libgomp.c/alloc-pinned-5.c: Likewise.
	* testsuite/libgomp.c/alloc-pinned-6.c: Likewise.

Co-Authored-By: Thomas Schwinge <thomas@codesourcery.com>
---
 libgomp/config/linux/allocator.c             | 141 ++++++++++++++-----
 libgomp/libgomp-plugin.h                     |   2 +
 libgomp/libgomp.h                            |   4 +
 libgomp/libgomp.texi                         |  11 +-
 libgomp/libgomp_g.h                          |   1 +
 libgomp/plugin/plugin-nvptx.c                |  42 ++++++
 libgomp/target.c                             | 136 ++++++++++++++++++
 libgomp/testsuite/libgomp.c/alloc-pinned-1.c |  26 ++++
 libgomp/testsuite/libgomp.c/alloc-pinned-2.c |  26 ++++
 libgomp/testsuite/libgomp.c/alloc-pinned-3.c |  45 +++++-
 libgomp/testsuite/libgomp.c/alloc-pinned-4.c |  44 +++++-
 libgomp/testsuite/libgomp.c/alloc-pinned-5.c |  26 ++++
 libgomp/testsuite/libgomp.c/alloc-pinned-6.c |  34 ++++-
 13 files changed, 488 insertions(+), 50 deletions(-)
diff mbox series

Patch

diff --git a/libgomp/config/linux/allocator.c b/libgomp/config/linux/allocator.c
index 7e09ba44b2f..063c46f972c 100644
--- a/libgomp/config/linux/allocator.c
+++ b/libgomp/config/linux/allocator.c
@@ -36,6 +36,11 @@ 
 
 /* Implement malloc routines that can handle pinned memory on Linux.
    
+   Given that pinned memory is typically used to help host <-> device memory
+   transfers, we attempt to allocate such memory using a device (really:
+   libgomp plugin), but fall back to mmap plus mlock if no suitable device is
+   available.
+
    It's possible to use mlock on any heap memory, but using munlock is
    problematic if there are multiple pinned allocations on the same page.
    Tracking all that manually would be possible, but adds overhead. This may
@@ -49,6 +54,7 @@ 
 #define _GNU_SOURCE
 #include <sys/mman.h>
 #include <string.h>
+#include <assert.h>
 #include "libgomp.h"
 #ifdef HAVE_INTTYPES_H
 # include <inttypes.h>  /* For PRIu64.  */
@@ -68,50 +74,92 @@  GOMP_enable_pinned_mode ()
     always_pinned_mode = true;
 }
 
+static int using_device_for_page_locked
+  = /* uninitialized */ -1;
+
 static void *
-linux_memspace_alloc (omp_memspace_handle_t memspace, size_t size, int pin)
+linux_memspace_alloc (omp_memspace_handle_t memspace, size_t size, int pin,
+		      bool init0)
 {
-  (void)memspace;
+  gomp_debug (0, "%s: memspace=%llu, size=%llu, pin=%d, init0=%d\n",
+	      __FUNCTION__, (unsigned long long) memspace,
+	      (unsigned long long) size, pin, init0);
+
+  void *addr;
 
   /* Explicit pinning may not be required.  */
   pin = pin && !always_pinned_mode;
 
   if (pin)
     {
-      /* Note that mmap always returns zeroed memory and is therefore also a
-	 suitable implementation of calloc.  */
-      void *addr = mmap (NULL, size, PROT_READ | PROT_WRITE,
-			 MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
-      if (addr == MAP_FAILED)
-	return NULL;
-
-      if (mlock (addr, size))
+      int using_device
+	= __atomic_load_n (&using_device_for_page_locked,
+			   MEMMODEL_RELAXED);
+      gomp_debug (0, "  using_device=%d\n",
+		  using_device);
+      if (using_device != 0)
+	{
+	  using_device = gomp_page_locked_host_alloc (&addr, size);
+	  int using_device_old
+	    = __atomic_exchange_n (&using_device_for_page_locked,
+				   using_device, MEMMODEL_RELAXED);
+	  gomp_debug (0, "  using_device=%d, using_device_old=%d\n",
+		      using_device, using_device_old);
+	  assert (using_device_old == -1
+		  /* We shouldn't have concurrently changed our mind.  */
+		  || using_device_old == using_device);
+	}
+      if (using_device == 0)
 	{
+	  gomp_debug (0, "  mmap\n");
+	  addr = mmap (NULL, size, PROT_READ | PROT_WRITE,
+		       MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+	  if (addr == MAP_FAILED)
+	    addr = NULL;
+	  else
+	    {
+	      /* 'mmap' zero-initializes.  */
+	      init0 = false;
+
+	      gomp_debug (0, "  mlock\n");
+	      if (mlock (addr, size))
+		{
 #ifdef HAVE_INTTYPES_H
-	  gomp_debug (0, "libgomp: failed to pin %"PRIu64" bytes of"
-		      " memory (ulimit too low?)\n", (uint64_t) size);
+		  gomp_debug (0, "libgomp: failed to pin %"PRIu64" bytes of"
+			      " memory (ulimit too low?)\n", (uint64_t) size);
 #else
-	  gomp_debug (0, "libgomp: failed to pin %lu bytes of"
-		      " memory (ulimit too low?)\n", (unsigned long) size);
+		  gomp_debug (0, "libgomp: failed to pin %lu bytes of memory"
+			      " (ulimit too low?)\n", (unsigned long) size);
 #endif
-	  munmap (addr, size);
-	  return NULL;
+		  munmap (addr, size);
+		  addr = NULL;
+		}
+	    }
 	}
-
-      return addr;
     }
   else
-    return malloc (size);
+    addr = malloc (size);
+
+  if (addr && init0)
+    {
+      gomp_debug (0, "  init0\n");
+      memset (addr, 0, size);
+    }
+
+  return addr;
 }
 
 static void *
 linux_memspace_calloc (omp_memspace_handle_t memspace, size_t size, int pin)
 {
+  gomp_debug (0, "%s: memspace=%llu, size=%llu, pin=%d\n",
+	      __FUNCTION__, (unsigned long long) memspace, (unsigned long long) size, pin);
+
   /* Explicit pinning may not be required.  */
   pin = pin && !always_pinned_mode;
 
   if (pin)
-    return linux_memspace_alloc (memspace, size, pin);
+    return linux_memspace_alloc (memspace, size, pin, true);
   else
     return calloc (1, size);
 }
@@ -120,13 +168,25 @@  static void
 linux_memspace_free (omp_memspace_handle_t memspace, void *addr, size_t size,
 		     int pin)
 {
-  (void)memspace;
+  gomp_debug (0, "%s: memspace=%llu, addr=%p, size=%llu, pin=%d\n",
+	      __FUNCTION__, (unsigned long long) memspace, addr, (unsigned long long) size, pin);
 
   /* Explicit pinning may not be required.  */
   pin = pin && !always_pinned_mode;
 
   if (pin)
-    munmap (addr, size);
+    {
+      int using_device
+	= __atomic_load_n (&using_device_for_page_locked,
+			   MEMMODEL_RELAXED);
+      gomp_debug (0, "  using_device=%d\n",
+		  using_device);
+      if (using_device == 1)
+	gomp_page_locked_host_free (addr);
+      else
+	/* 'munlock'ing is implicit with following 'munmap'.  */
+	munmap (addr, size);
+    }
   else
     free (addr);
 }
@@ -135,11 +195,25 @@  static void *
 linux_memspace_realloc (omp_memspace_handle_t memspace, void *addr,
 			size_t oldsize, size_t size, int oldpin, int pin)
 {
+  gomp_debug (0, "%s: memspace=%llu, addr=%p, oldsize=%llu, size=%llu, oldpin=%d, pin=%d\n",
+	      __FUNCTION__, (unsigned long long) memspace, addr, (unsigned long long) oldsize, (unsigned long long) size, oldpin, pin);
+
   /* Explicit pinning may not be required.  */
   pin = pin && !always_pinned_mode;
 
   if (oldpin && pin)
     {
+      /* We can only expect to be able to just 'mremap' if not using a device
+	 for page-locked memory.  */
+      int using_device
+	= __atomic_load_n (&using_device_for_page_locked,
+		       MEMMODEL_RELAXED);
+      gomp_debug (0, "  using_device=%d\n",
+		  using_device);
+      if (using_device != 0)
+	goto manual_realloc;
+
+      gomp_debug (0, "  mremap\n");
       void *newaddr = mremap (addr, oldsize, size, MREMAP_MAYMOVE);
       if (newaddr == MAP_FAILED)
 	return NULL;
@@ -147,18 +221,19 @@  linux_memspace_realloc (omp_memspace_handle_t memspace, void *addr,
       return newaddr;
     }
   else if (oldpin || pin)
-    {
-      void *newaddr = linux_memspace_alloc (memspace, size, pin);
-      if (newaddr)
-	{
-	  memcpy (newaddr, addr, oldsize < size ? oldsize : size);
-	  linux_memspace_free (memspace, addr, oldsize, oldpin);
-	}
-
-      return newaddr;
-    }
+    goto manual_realloc;
   else
     return realloc (addr, size);
+
+manual_realloc:;
+  void *newaddr = linux_memspace_alloc (memspace, size, pin, false);
+  if (newaddr)
+    {
+      memcpy (newaddr, addr, oldsize < size ? oldsize : size);
+      linux_memspace_free (memspace, addr, oldsize, oldpin);
+    }
+
+  return newaddr;
 }
 
 static int
@@ -169,7 +244,7 @@  linux_memspace_validate (omp_memspace_handle_t, unsigned, int)
 }
 
 #define MEMSPACE_ALLOC(MEMSPACE, SIZE, PIN) \
-  linux_memspace_alloc (MEMSPACE, SIZE, PIN)
+  linux_memspace_alloc (MEMSPACE, SIZE, PIN, false)
 #define MEMSPACE_CALLOC(MEMSPACE, SIZE, PIN) \
   linux_memspace_calloc (MEMSPACE, SIZE, PIN)
 #define MEMSPACE_REALLOC(MEMSPACE, ADDR, OLDSIZE, SIZE, OLDPIN, PIN) \
diff --git a/libgomp/libgomp-plugin.h b/libgomp/libgomp-plugin.h
index 0c9c28c65cf..0d2e3f0a6ec 100644
--- a/libgomp/libgomp-plugin.h
+++ b/libgomp/libgomp-plugin.h
@@ -139,6 +139,8 @@  extern int GOMP_OFFLOAD_load_image (int, unsigned, const void *,
 extern bool GOMP_OFFLOAD_unload_image (int, unsigned, const void *);
 extern void *GOMP_OFFLOAD_alloc (int, size_t);
 extern bool GOMP_OFFLOAD_free (int, void *);
+extern bool GOMP_OFFLOAD_page_locked_host_alloc (void **, size_t);
+extern bool GOMP_OFFLOAD_page_locked_host_free (void *);
 extern bool GOMP_OFFLOAD_dev2host (int, void *, const void *, size_t);
 extern bool GOMP_OFFLOAD_host2dev (int, void *, const void *, size_t);
 extern bool GOMP_OFFLOAD_dev2dev (int, void *, const void *, size_t);
diff --git a/libgomp/libgomp.h b/libgomp/libgomp.h
index 089393846d1..b8c6fc00de4 100644
--- a/libgomp/libgomp.h
+++ b/libgomp/libgomp.h
@@ -1128,6 +1128,8 @@  extern int gomp_get_num_devices (void);
 extern bool gomp_target_task_fn (void *);
 extern void gomp_target_rev (uint64_t, uint64_t, uint64_t, uint64_t, uint64_t,
 			     int, struct goacc_asyncqueue *);
+extern bool gomp_page_locked_host_alloc (void **, size_t);
+extern void gomp_page_locked_host_free (void *);
 
 /* Splay tree definitions.  */
 typedef struct splay_tree_node_s *splay_tree_node;
@@ -1409,6 +1411,8 @@  struct gomp_device_descr
   __typeof (GOMP_OFFLOAD_unload_image) *unload_image_func;
   __typeof (GOMP_OFFLOAD_alloc) *alloc_func;
   __typeof (GOMP_OFFLOAD_free) *free_func;
+  __typeof (GOMP_OFFLOAD_page_locked_host_alloc) *page_locked_host_alloc_func;
+  __typeof (GOMP_OFFLOAD_page_locked_host_free) *page_locked_host_free_func;
   __typeof (GOMP_OFFLOAD_dev2host) *dev2host_func;
   __typeof (GOMP_OFFLOAD_host2dev) *host2dev_func;
   __typeof (GOMP_OFFLOAD_memcpy2d) *memcpy2d_func;
diff --git a/libgomp/libgomp.texi b/libgomp/libgomp.texi
index b3abb3dbdd9..eed95640001 100644
--- a/libgomp/libgomp.texi
+++ b/libgomp/libgomp.texi
@@ -6285,8 +6285,9 @@  a @code{nearest} allocation.
 
 Additional notes regarding the traits:
 @itemize
-@item The @code{pinned} trait is supported on Linux hosts, but is subject to
-      the OS @code{ulimit}/@code{rlimit} locked memory settings.
+@item The @code{pinned} trait is supported on Linux hosts, but is usually
+      subject to the OS @code{ulimit}/@code{rlimit} locked memory settings (see
+      @ref{Offload-Target Specifics} for exceptions).
 @item The default for the @code{pool_size} trait is no pool and for every
       (re)allocation the associated library routine is called, which might
       internally use a memory pool.
@@ -6474,6 +6475,12 @@  The implementation remark:
       @code{omp_thread_mem_alloc}, all use low-latency memory as first
       preference, and fall back to main graphics memory when the low-latency
       pool is exhausted.
+@item Pinned memory allocated using @code{omp_alloc} with the
+      @code{ompx_gnu_pinned_mem_alloc} allocator or the @code{pinned} trait is
+      obtained via the CUDA API when an NVPTX device is present.  This provides
+      a performance boost for NVPTX offload code and also allows unlimited use
+      of pinned memory regardless of the OS @code{ulimit}/@code{rlimit}
+      settings.
 @end itemize
 
 
diff --git a/libgomp/libgomp_g.h b/libgomp/libgomp_g.h
index c0cc03ae61f..74c0fd17784 100644
--- a/libgomp/libgomp_g.h
+++ b/libgomp/libgomp_g.h
@@ -371,6 +371,7 @@  extern bool GOMP_is_alloc (void *);
 
 extern void *GOMP_alloc (size_t, size_t, uintptr_t);
 extern void GOMP_free (void *, uintptr_t);
+extern void GOMP_enable_pinned_mode (void);
 
 /* error.c */
 
diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index 4cedc5390a3..5caf8fe5026 100644
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -1625,6 +1625,48 @@  GOMP_OFFLOAD_free (int ord, void *ptr)
 	  && nvptx_free (ptr, ptx_devices[ord]));
 }
 
+bool
+GOMP_OFFLOAD_page_locked_host_alloc (void **ptr, size_t size)
+{
+  GOMP_PLUGIN_debug (0, "nvptx %s: ptr=%p, size=%llu\n",
+		     __FUNCTION__, ptr, (unsigned long long) size);
+
+  if (size == 0)
+    {
+      /* Special case to ensure omp_alloc specification compliance.  */
+      *ptr = NULL;
+      GOMP_PLUGIN_debug (0, "  -> *ptr=null\n");
+      return true;
+    }
+
+  CUresult r;
+
+  unsigned int flags = 0;
+  /* Given 'CU_DEVICE_ATTRIBUTE_UNIFIED_ADDRESSING', we don't need
+     'flags |= CU_MEMHOSTALLOC_PORTABLE;' here.  */
+  r = CUDA_CALL_NOCHECK (cuMemHostAlloc, ptr, size, flags);
+  if (r == CUDA_ERROR_OUT_OF_MEMORY)
+    *ptr = NULL;
+  else if (r != CUDA_SUCCESS)
+    {
+      GOMP_PLUGIN_error ("cuMemHostAlloc error: %s", cuda_error (r));
+      return false;
+    }
+  GOMP_PLUGIN_debug (0, "  -> *ptr=%p\n",
+		     *ptr);
+  return true;
+}
+
+bool
+GOMP_OFFLOAD_page_locked_host_free (void *ptr)
+{
+  GOMP_PLUGIN_debug (0, "nvptx %s: ptr=%p\n",
+		     __FUNCTION__, ptr);
+
+  CUDA_CALL (cuMemFreeHost, ptr);
+  return true;
+}
+
 void
 GOMP_OFFLOAD_openacc_exec (void (*fn) (void *),
 			   size_t mapnum  __attribute__((unused)),
diff --git a/libgomp/target.c b/libgomp/target.c
index 48689920d4a..adbd18101f2 100644
--- a/libgomp/target.c
+++ b/libgomp/target.c
@@ -4437,6 +4437,140 @@  omp_target_free (void *device_ptr, int device_num)
   gomp_mutex_unlock (&devicep->lock);
 }
 
+/* Device (really: libgomp plugin) to use for paged-locked memory.  We
+   assume there is either none or exactly one such device for the lifetime of
+   the process.  */
+
+static struct gomp_device_descr *device_for_page_locked
+  = /* uninitialized */ (void *) -1;
+
+static struct gomp_device_descr *
+get_device_for_page_locked (void)
+{
+  gomp_debug (0, "%s\n",
+	      __FUNCTION__);
+
+  struct gomp_device_descr *device;
+#ifdef HAVE_SYNC_BUILTINS
+  device
+    = __atomic_load_n (&device_for_page_locked, MEMMODEL_RELAXED);
+  if (device == (void *) -1)
+    {
+      gomp_debug (0, "  init\n");
+
+      gomp_init_targets_once ();
+
+      device = NULL;
+      for (int i = 0; i < num_devices; ++i)
+	{
+	  gomp_debug (0, "  i=%d, target_id=%d\n",
+		      i, devices[i].target_id);
+
+	  /* We consider only the first device of potentially several of the
+	     same type as this functionality is not specific to an individual
+	     offloading device, but instead relates to the host-side
+	     implementation of the respective offloading implementation.  */
+	  if (devices[i].target_id != 0)
+	    continue;
+
+	  if (!devices[i].page_locked_host_alloc_func)
+	    continue;
+
+	  gomp_debug (0, "  found device: %p (%s)\n",
+		      &devices[i], devices[i].name);
+	  if (device)
+	    gomp_fatal ("Unclear how %s and %s libgomp plugins may"
+			" simultaneously provide functionality"
+			" for page-locked memory",
+			device->name, devices[i].name);
+	  else
+	    device = &devices[i];
+	}
+
+      struct gomp_device_descr *device_old
+	= __atomic_exchange_n (&device_for_page_locked, device,
+			       MEMMODEL_RELAXED);
+      gomp_debug (0, "  old device_for_page_locked: %p\n",
+		  device_old);
+      assert (device_old == (void *) -1
+	      /* We shouldn't have concurrently found a different or no
+		 device.  */
+	      || device_old == device);
+    }
+#else /* !HAVE_SYNC_BUILTINS */
+  gomp_debug (0, "  not implemented for '!HAVE_SYNC_BUILTINS'\n");
+  (void) &device_for_page_locked;
+  device = NULL;
+#endif /* HAVE_SYNC_BUILTINS */
+
+  gomp_debug (0, "  -> device=%p (%s)\n",
+	      device, device ? device->name : "[none]");
+  return device;
+}
+
+/* Allocate page-locked host memory.
+   Returns whether we have a device capable of that.  */
+
+attribute_hidden bool
+gomp_page_locked_host_alloc (void **ptr, size_t size)
+{
+  gomp_debug (0, "%s: ptr=%p, size=%llu\n",
+	      __FUNCTION__, ptr, (unsigned long long) size);
+
+  struct gomp_device_descr *device = get_device_for_page_locked ();
+  gomp_debug (0, "  device=%p (%s)\n",
+	      device, device ? device->name : "[none]");
+  if (device)
+    {
+      gomp_mutex_lock (&device->lock);
+      if (device->state == GOMP_DEVICE_UNINITIALIZED)
+	gomp_init_device (device);
+      else if (device->state == GOMP_DEVICE_FINALIZED)
+	{
+	  gomp_mutex_unlock (&device->lock);
+	  gomp_fatal ("Device %s used for for page-locked memory is finalized",
+		      device->name);
+	}
+      gomp_mutex_unlock (&device->lock);
+
+      if (!device->page_locked_host_alloc_func (ptr, size))
+	gomp_fatal ("Failed to allocate page-locked host memory"
+		    " via %s libgomp plugin",
+		    device->name);
+    }
+  return device != NULL;
+}
+
+/* Free page-locked host memory.
+   This must only be called if 'gomp_page_locked_host_alloc' returned
+   'true'.  */
+
+attribute_hidden void
+gomp_page_locked_host_free (void *ptr)
+{
+  gomp_debug (0, "%s: ptr=%p\n",
+	      __FUNCTION__, ptr);
+
+  struct gomp_device_descr *device = get_device_for_page_locked ();
+  gomp_debug (0, "  device=%p (%s)\n",
+	      device, device ? device->name : "[none]");
+  assert (device);
+
+  gomp_mutex_lock (&device->lock);
+  assert (device->state != GOMP_DEVICE_UNINITIALIZED);
+  if (device->state == GOMP_DEVICE_FINALIZED)
+    {
+      gomp_mutex_unlock (&device->lock);
+      return;
+    }
+  gomp_mutex_unlock (&device->lock);
+
+  if (!device->page_locked_host_free_func (ptr))
+    gomp_fatal ("Failed to free page-locked host memory"
+		" via %s libgomp plugin",
+		device->name);
+}
+
 int
 omp_target_is_present (const void *ptr, int device_num)
 {
@@ -5159,6 +5293,8 @@  gomp_load_plugin_for_device (struct gomp_device_descr *device,
   DLSYM (unload_image);
   DLSYM (alloc);
   DLSYM (free);
+  DLSYM_OPT (page_locked_host_alloc, page_locked_host_alloc);
+  DLSYM_OPT (page_locked_host_free, page_locked_host_free);
   DLSYM (dev2host);
   DLSYM (host2dev);
   DLSYM_OPT (memcpy2d, memcpy2d);
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-1.c b/libgomp/testsuite/libgomp.c/alloc-pinned-1.c
index 672f2453a78..693f9032c8d 100644
--- a/libgomp/testsuite/libgomp.c/alloc-pinned-1.c
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-1.c
@@ -2,6 +2,8 @@ 
 
 /* { dg-skip-if "Pinning not implemented on this host" { ! *-*-linux-gnu* } } */
 
+/* { dg-additional-options -DOFFLOAD_DEVICE_NVPTX { target offload_device_nvptx } } */
+
 /* Test that pinned memory works.  */
 
 #include <stdio.h>
@@ -63,10 +65,16 @@  verify0 (char *p, size_t s)
 int
 main ()
 {
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* Go big or go home.
+     The OS ulimit does not affect memory locked via CUDA for NVPTX devices. */
+  const int SIZE = 40 * 1024 * 1024;
+#else
   /* Allocate at least a page each time, allowing space for overhead,
      but stay within the ulimit.  */
   const int SIZE = PAGE_SIZE - 128;
   CHECK_SIZE (SIZE * 5);  // This is intended to help diagnose failures
+#endif
 
   const omp_alloctrait_t traits[] = {
       { omp_atk_pinned, 1 }
@@ -88,21 +96,39 @@  main ()
     abort ();
 
   int amount = get_pinned_mem ();
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (amount != 0)
+    abort ();
+#else
   if (amount == 0)
     abort ();
+#endif
 
   p = omp_realloc (p, SIZE * 2, allocator, allocator);
 
   int amount2 = get_pinned_mem ();
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (amount2 != 0)
+    abort ();
+#else
   if (amount2 <= amount)
     abort ();
+#endif
 
   /* SIZE*2 ensures that it doesn't slot into the space possibly
      vacated by realloc.  */
   p = omp_calloc (1, SIZE * 2, allocator);
 
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (get_pinned_mem () != 0)
+    abort ();
+#else
   if (get_pinned_mem () <= amount2)
     abort ();
+#endif
 
   verify0 (p, SIZE * 2);
 
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-2.c b/libgomp/testsuite/libgomp.c/alloc-pinned-2.c
index b6d1d83fb6f..e7ac64e911f 100644
--- a/libgomp/testsuite/libgomp.c/alloc-pinned-2.c
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-2.c
@@ -2,6 +2,8 @@ 
 
 /* { dg-skip-if "Pinning not implemented on this host" { ! *-*-linux-gnu* } } */
 
+/* { dg-additional-options -DOFFLOAD_DEVICE_NVPTX { target offload_device_nvptx } } */
+
 /* Test that pinned memory works (pool_size code path).  */
 
 #include <stdio.h>
@@ -63,10 +65,16 @@  verify0 (char *p, size_t s)
 int
 main ()
 {
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* Go big or go home.
+     The OS ulimit does not affect memory locked via CUDA for NVPTX devices. */
+  const int SIZE = 40 * 1024 * 1024;
+#else
   /* Allocate at least a page each time, allowing space for overhead,
      but stay within the ulimit.  */
   const int SIZE = PAGE_SIZE - 128;
   CHECK_SIZE (SIZE * 5);  // This is intended to help diagnose failures
+#endif
 
   const omp_alloctrait_t traits[] = {
       { omp_atk_pinned, 1 },
@@ -89,16 +97,28 @@  main ()
     abort ();
 
   int amount = get_pinned_mem ();
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (amount != 0)
+    abort ();
+#else
   if (amount == 0)
     abort ();
+#endif
 
   p = omp_realloc (p, SIZE * 2, allocator, allocator);
   if (!p)
     abort ();
 
   int amount2 = get_pinned_mem ();
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (amount2 != 0)
+    abort ();
+#else
   if (amount2 <= amount)
     abort ();
+#endif
 
   /* SIZE*2 ensures that it doesn't slot into the space possibly
      vacated by realloc.  */
@@ -106,8 +126,14 @@  main ()
   if (!p)
     abort ();
 
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (get_pinned_mem () != 0)
+    abort ();
+#else
   if (get_pinned_mem () <= amount2)
     abort ();
+#endif
 
   verify0 (p, SIZE * 2);
 
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-3.c b/libgomp/testsuite/libgomp.c/alloc-pinned-3.c
index 53e4720cc9c..b17daf7e222 100644
--- a/libgomp/testsuite/libgomp.c/alloc-pinned-3.c
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-3.c
@@ -1,5 +1,7 @@ 
 /* { dg-do run } */
 
+/* { dg-additional-options -DOFFLOAD_DEVICE_NVPTX { target offload_device_nvptx } } */
+
 /* Test that pinned memory fails correctly.  */
 
 #include <stdio.h>
@@ -75,8 +77,15 @@  verify0 (char *p, size_t s)
 int
 main ()
 {
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* Go big or go home.
+     The OS ulimit does not affect memory locked via CUDA for NVPTX devices. */
+  const int SIZE = 40 * 1024 * 1024;
+#else
   /* This needs to be large enough to cover multiple pages.  */
   const int SIZE = PAGE_SIZE * 4;
+#endif
+  const int PIN_LIMIT = PAGE_SIZE * 2;
 
   /* Pinned memory, no fallback.  */
   const omp_alloctrait_t traits1[] = {
@@ -101,23 +110,34 @@  main ()
 #endif
 
   /* Ensure that the limit is smaller than the allocation.  */
-  set_pin_limit (SIZE / 2);
+  set_pin_limit (PIN_LIMIT);
 
   // Sanity check
   if (get_pinned_mem () != 0)
     abort ();
 
-  // Should fail
   void *p1 = omp_alloc (SIZE, allocator1);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'.
+  if (!p1)
+    abort ();
+#else
+  // Should fail
   if (p1)
     abort ();
+#endif
 
-  // Should fail
   void *p2 = omp_calloc (1, SIZE, allocator1);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'.
+  if (!p2)
+    abort ();
+#else
+  // Should fail
   if (p2)
     abort ();
+#endif
 
-  // Should fall back
   void *p3 = omp_alloc (SIZE, allocator2);
   if (!p3)
     abort ();
@@ -128,16 +148,29 @@  main ()
     abort ();
   verify0 (p4, SIZE);
 
-  // Should fail to realloc
   void *notpinned = omp_alloc (SIZE, omp_default_mem_alloc);
   void *p5 = omp_realloc (notpinned, SIZE, allocator1, omp_default_mem_alloc);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'; does reallocate.
+  if (!notpinned || !p5 || p5 == notpinned)
+    abort ();
+#else
+  // Should fail to realloc
   if (!notpinned || p5)
     abort ();
+#endif
 
-  // Should fall back to no realloc needed
+#ifdef OFFLOAD_DEVICE_NVPTX
+  void *p6 = omp_realloc (p5, SIZE, allocator2, allocator1);
+  // Does reallocate.
+  if (p5 == p6)
+    abort ();
+#else
   void *p6 = omp_realloc (notpinned, SIZE, allocator2, omp_default_mem_alloc);
+  // Should fall back to no realloc needed
   if (p6 != notpinned)
     abort ();
+#endif
 
   // No memory should have been pinned
   int amount = get_pinned_mem ();
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-4.c b/libgomp/testsuite/libgomp.c/alloc-pinned-4.c
index 9d850c23e4b..aadd9249ba9 100644
--- a/libgomp/testsuite/libgomp.c/alloc-pinned-4.c
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-4.c
@@ -1,5 +1,7 @@ 
 /* { dg-do run } */
 
+/* { dg-additional-options -DOFFLOAD_DEVICE_NVPTX { target offload_device_nvptx } } */
+
 /* Test that pinned memory fails correctly, pool_size code path.  */
 
 #include <stdio.h>
@@ -75,8 +77,15 @@  verify0 (char *p, size_t s)
 int
 main ()
 {
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* Go big or go home.
+     The OS ulimit does not affect memory locked via CUDA for NVPTX devices. */
+  const int SIZE = 40 * 1024 * 1024;
+#else
   /* This needs to be large enough to cover multiple pages.  */
   const int SIZE = PAGE_SIZE * 4;
+#endif
+  const int PIN_LIMIT = PAGE_SIZE * 2;
 
   /* Pinned memory, no fallback.  */
   const omp_alloctrait_t traits1[] = {
@@ -103,21 +112,33 @@  main ()
 #endif
 
   /* Ensure that the limit is smaller than the allocation.  */
-  set_pin_limit (SIZE / 2);
+  set_pin_limit (PIN_LIMIT);
 
   // Sanity check
   if (get_pinned_mem () != 0)
     abort ();
 
-  // Should fail
   void *p = omp_alloc (SIZE, allocator1);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'.
+  if (!p)
+    abort ();
+#else
+  // Should fail
   if (p)
     abort ();
+#endif
 
-  // Should fail
   p = omp_calloc (1, SIZE, allocator1);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'.
+  if (!p)
+    abort ();
+#else
+  // Should fail
   if (p)
     abort ();
+#endif
 
   // Should fall back
   p = omp_alloc (SIZE, allocator2);
@@ -130,16 +151,29 @@  main ()
     abort ();
   verify0 (p, SIZE);
 
-  // Should fail to realloc
   void *notpinned = omp_alloc (SIZE, omp_default_mem_alloc);
   p = omp_realloc (notpinned, SIZE, allocator1, omp_default_mem_alloc);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'; does reallocate.
+  if (!notpinned || !p || p == notpinned)
+    abort ();
+#else
+  // Should fail to realloc
   if (!notpinned || p)
     abort ();
+#endif
 
-  // Should fall back to no realloc needed
+#ifdef OFFLOAD_DEVICE_NVPTX
+  void *p_ = omp_realloc (p, SIZE, allocator2, allocator1);
+  // Does reallocate.
+  if (p_ == p)
+    abort ();
+#else
   p = omp_realloc (notpinned, SIZE, allocator2, omp_default_mem_alloc);
+  // Should fall back to no realloc needed
   if (p != notpinned)
     abort ();
+#endif
 
   // No memory should have been pinned
   int amount = get_pinned_mem ();
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-5.c b/libgomp/testsuite/libgomp.c/alloc-pinned-5.c
index 0ba2feb8d96..cc7776409ff 100644
--- a/libgomp/testsuite/libgomp.c/alloc-pinned-5.c
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-5.c
@@ -2,6 +2,8 @@ 
 
 /* { dg-skip-if "Pinning not implemented on this host" { ! *-*-linux-gnu* } } */
 
+/* { dg-additional-options -DOFFLOAD_DEVICE_NVPTX { target offload_device_nvptx } } */
+
 /* Test that ompx_gnu_pinned_mem_alloc works.  */
 
 #include <stdio.h>
@@ -63,10 +65,16 @@  verify0 (char *p, size_t s)
 int
 main ()
 {
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* Go big or go home.
+     The OS ulimit does not affect memory locked via CUDA for NVPTX devices. */
+  const int SIZE = 40 * 1024 * 1024;
+#else
   /* Allocate at least a page each time, allowing space for overhead,
      but stay within the ulimit.  */
   const int SIZE = PAGE_SIZE - 128;
   CHECK_SIZE (SIZE * 5);
+#endif
 
   // Sanity check
   if (get_pinned_mem () != 0)
@@ -77,22 +85,40 @@  main ()
     abort ();
 
   int amount = get_pinned_mem ();
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (amount != 0)
+    abort ();
+#else
   if (amount == 0)
     abort ();
+#endif
 
   p = omp_realloc (p, SIZE * 2, ompx_gnu_pinned_mem_alloc,
 		   ompx_gnu_pinned_mem_alloc);
 
   int amount2 = get_pinned_mem ();
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (amount2 != 0)
+    abort ();
+#else
   if (amount2 <= amount)
     abort ();
+#endif
 
   /* SIZE*2 ensures that it doesn't slot into the space possibly
      vacated by realloc.  */
   p = omp_calloc (1, SIZE * 2, ompx_gnu_pinned_mem_alloc);
 
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* This doesn't show up as process 'VmLck'ed memory.  */
+  if (get_pinned_mem () != 0)
+    abort ();
+#else
   if (get_pinned_mem () <= amount2)
     abort ();
+#endif
 
   verify0 (p, SIZE * 2);
 
diff --git a/libgomp/testsuite/libgomp.c/alloc-pinned-6.c b/libgomp/testsuite/libgomp.c/alloc-pinned-6.c
index 7ed68740ae6..44aca12bad1 100644
--- a/libgomp/testsuite/libgomp.c/alloc-pinned-6.c
+++ b/libgomp/testsuite/libgomp.c/alloc-pinned-6.c
@@ -1,4 +1,5 @@ 
 /* { dg-do run } */
+/* { dg-additional-options -DOFFLOAD_DEVICE_NVPTX { target offload_device_nvptx } } */
 
 /* Test that ompx_gnu_pinned_mem_alloc fails correctly.  */
 
@@ -66,32 +67,57 @@  set_pin_limit ()
 int
 main ()
 {
+#ifdef OFFLOAD_DEVICE_NVPTX
+  /* Go big or go home.
+     The OS ulimit does not affect memory locked via CUDA for NVPTX devices. */
+  const int SIZE = 40 * 1024 * 1024;
+#else
   /* Allocate at least a page each time, but stay within the ulimit.  */
   const int SIZE = PAGE_SIZE * 4;
+#endif
+  const int PIN_LIMIT = PAGE_SIZE*2;
 
   /* Ensure that the limit is smaller than the allocation.  */
-  set_pin_limit (SIZE / 2);
+  set_pin_limit (PIN_LIMIT);
 
   // Sanity check
   if (get_pinned_mem () != 0)
     abort ();
 
-  // Should fail
   void *p = omp_alloc (SIZE, ompx_gnu_pinned_mem_alloc);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'.
+  if (!p)
+    abort ();
+#else
+  // Should fail
   if (p)
     abort ();
+#endif
 
-  // Should fail
   p = omp_calloc (1, SIZE, ompx_gnu_pinned_mem_alloc);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'.
+  if (!p)
+    abort ();
+#else
+  // Should fail
   if (p)
     abort ();
+#endif
 
-  // Should fail to realloc
   void *notpinned = omp_alloc (SIZE, omp_default_mem_alloc);
   p = omp_realloc (notpinned, SIZE, ompx_gnu_pinned_mem_alloc,
 		   omp_default_mem_alloc);
+#ifdef OFFLOAD_DEVICE_NVPTX
+  // Doesn't care about 'set_pin_limit'; does reallocate.
+  if (!notpinned || !p || p == notpinned)
+    abort ();
+#else
+  // Should fail to realloc
   if (!notpinned || p)
     abort ();
+#endif
 
   // No memory should have been pinned
   int amount = get_pinned_mem ();