diff mbox series

[v2,2/3] openmp, nvptx: low-lat memory access traits

Message ID 161001070f7573c98d2b72223933dbba49405fea.1690994309.git.ams@codesourcery.com
State Unresolved
Headers
Series libgomp: OpenMP low-latency omp_alloc |

Checks

Context Check Description
snail/gcc-patch-check warning Git am fail log

Commit Message

Andrew Stubbs Aug. 2, 2023, 5 p.m. UTC 
  The NVPTX low latency memory is not accessible outside the team that allocates
it, and therefore should be unavailable for allocators with the access trait
"all".  This change means that the omp_low_lat_mem_alloc predefined
allocator now implicitly implies the "pteam" trait.

libgomp/ChangeLog:

	* allocator.c (MEMSPACE_VALIDATE): New macro.
	(omp_aligned_alloc): Use MEMSPACE_VALIDATE.
	(omp_aligned_calloc): Likewise.
	(omp_realloc): Likewise.
	* config/nvptx/allocator.c (nvptx_memspace_validate): New function.
	(MEMSPACE_VALIDATE): New macro.
	* testsuite/libgomp.c/omp_alloc-4.c (main): Add access trait.
	* testsuite/libgomp.c/omp_alloc-6.c (main): Add access trait.
	* testsuite/libgomp.c/omp_alloc-traits.c: New test.
---
 libgomp/allocator.c                           | 16 +++++
 libgomp/config/nvptx/allocator.c              | 11 +++
 libgomp/testsuite/libgomp.c/omp_alloc-4.c     |  7 +-
 libgomp/testsuite/libgomp.c/omp_alloc-6.c     |  7 +-
 .../testsuite/libgomp.c/omp_alloc-traits.c    | 68 +++++++++++++++++++
 5 files changed, 103 insertions(+), 6 deletions(-)
 create mode 100644 libgomp/testsuite/libgomp.c/omp_alloc-traits.c
diff mbox series

Patch

diff --git a/libgomp/allocator.c b/libgomp/allocator.c
index fbf7b1ab061..35b8ec71480 100644
--- a/libgomp/allocator.c
+++ b/libgomp/allocator.c
@@ -56,6 +56,10 @@ 
 #define MEMSPACE_FREE(MEMSPACE, ADDR, SIZE) \
   free (((void)(MEMSPACE), (void)(SIZE), (ADDR)))
 #endif
+#ifndef MEMSPACE_VALIDATE
+#define MEMSPACE_VALIDATE(MEMSPACE, ACCESS) \
+  (((void)(MEMSPACE), (void)(ACCESS), 1))
+#endif
 
 /* Map the predefined allocators to the correct memory space.
    The index to this table is the omp_allocator_handle_t enum value.
@@ -507,6 +511,10 @@  retry:
   if (__builtin_add_overflow (size, new_size, &new_size))
     goto fail;
 
+  if (allocator_data
+      && !MEMSPACE_VALIDATE (allocator_data->memspace, allocator_data->access))
+    goto fail;
+
   if (__builtin_expect (allocator_data
 			&& allocator_data->pool_size < ~(uintptr_t) 0, 0))
     {
@@ -817,6 +825,10 @@  retry:
   if (__builtin_add_overflow (size_temp, new_size, &new_size))
     goto fail;
 
+  if (allocator_data
+      && !MEMSPACE_VALIDATE (allocator_data->memspace, allocator_data->access))
+    goto fail;
+
   if (__builtin_expect (allocator_data
 			&& allocator_data->pool_size < ~(uintptr_t) 0, 0))
     {
@@ -1063,6 +1075,10 @@  retry:
     goto fail;
   old_size = data->size;
 
+  if (allocator_data
+      && !MEMSPACE_VALIDATE (allocator_data->memspace, allocator_data->access))
+    goto fail;
+
   if (__builtin_expect (allocator_data
 			&& allocator_data->pool_size < ~(uintptr_t) 0, 0))
     {
diff --git a/libgomp/config/nvptx/allocator.c b/libgomp/config/nvptx/allocator.c
index 6014fba177f..f19ac28d32a 100644
--- a/libgomp/config/nvptx/allocator.c
+++ b/libgomp/config/nvptx/allocator.c
@@ -108,6 +108,15 @@  nvptx_memspace_realloc (omp_memspace_handle_t memspace, void *addr,
     return realloc (addr, size);
 }
 
+static inline int
+nvptx_memspace_validate (omp_memspace_handle_t memspace, unsigned access)
+{
+  /* Disallow use of low-latency memory when it must be accessible by
+     all threads.  */
+  return (memspace != omp_low_lat_mem_space
+	  || access != omp_atv_all);
+}
+
 #define MEMSPACE_ALLOC(MEMSPACE, SIZE) \
   nvptx_memspace_alloc (MEMSPACE, SIZE)
 #define MEMSPACE_CALLOC(MEMSPACE, SIZE) \
@@ -116,5 +125,7 @@  nvptx_memspace_realloc (omp_memspace_handle_t memspace, void *addr,
   nvptx_memspace_realloc (MEMSPACE, ADDR, OLDSIZE, SIZE)
 #define MEMSPACE_FREE(MEMSPACE, ADDR, SIZE) \
   nvptx_memspace_free (MEMSPACE, ADDR, SIZE)
+#define MEMSPACE_VALIDATE(MEMSPACE, ACCESS) \
+  nvptx_memspace_validate (MEMSPACE, ACCESS)
 
 #include "../../allocator.c"
diff --git a/libgomp/testsuite/libgomp.c/omp_alloc-4.c b/libgomp/testsuite/libgomp.c/omp_alloc-4.c
index 66e13c09234..9d169858151 100644
--- a/libgomp/testsuite/libgomp.c/omp_alloc-4.c
+++ b/libgomp/testsuite/libgomp.c/omp_alloc-4.c
@@ -23,10 +23,11 @@  main ()
   #pragma omp target
   {
     /* Ensure that the memory we get *is* low-latency with a null-fallback.  */
-    omp_alloctrait_t traits[1]
-      = { { omp_atk_fallback, omp_atv_null_fb } };
+    omp_alloctrait_t traits[2]
+      = { { omp_atk_fallback, omp_atv_null_fb },
+          { omp_atk_access, omp_atv_pteam } };
     omp_allocator_handle_t lowlat = omp_init_allocator (omp_low_lat_mem_space,
-							1, traits);
+							2, traits);
 
     int size = 4;
 
diff --git a/libgomp/testsuite/libgomp.c/omp_alloc-6.c b/libgomp/testsuite/libgomp.c/omp_alloc-6.c
index 66bf69b0455..b5f0a296998 100644
--- a/libgomp/testsuite/libgomp.c/omp_alloc-6.c
+++ b/libgomp/testsuite/libgomp.c/omp_alloc-6.c
@@ -23,10 +23,11 @@  main ()
   #pragma omp target
   {
     /* Ensure that the memory we get *is* low-latency with a null-fallback.  */
-    omp_alloctrait_t traits[1]
-      = { { omp_atk_fallback, omp_atv_null_fb } };
+    omp_alloctrait_t traits[2]
+      = { { omp_atk_fallback, omp_atv_null_fb },
+          { omp_atk_access, omp_atv_pteam } };
     omp_allocator_handle_t lowlat = omp_init_allocator (omp_low_lat_mem_space,
-							1, traits);
+							2, traits);
 
     int size = 16;
 
diff --git a/libgomp/testsuite/libgomp.c/omp_alloc-traits.c b/libgomp/testsuite/libgomp.c/omp_alloc-traits.c
new file mode 100644
index 00000000000..6294ba19c16
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/omp_alloc-traits.c
@@ -0,0 +1,68 @@ 
+/* { dg-do run } */
+
+/* { dg-require-effective-target offload_device } */
+/* { dg-xfail-if "not implemented" { ! offload_target_nvptx } } */
+
+/* Test that GPU low-latency allocation is limited to team access.  */
+
+#include <stddef.h>
+#include <omp.h>
+
+#pragma omp requires dynamic_allocators
+
+int
+main ()
+{
+  #pragma omp target
+  {
+    /* Ensure that the memory we get *is* low-latency with a null-fallback.  */
+    omp_alloctrait_t traits[2]
+      = { { omp_atk_fallback, omp_atv_null_fb },
+	  { omp_atk_access, omp_atv_pteam } };
+    omp_allocator_handle_t lowlat = omp_init_allocator (omp_low_lat_mem_space,
+							2, traits);
+
+    omp_alloctrait_t traits_all[2]
+      = { { omp_atk_fallback, omp_atv_null_fb },
+	  { omp_atk_access, omp_atv_all } };
+    omp_allocator_handle_t lowlat_all
+      = omp_init_allocator (omp_low_lat_mem_space, 2, traits_all);
+
+    omp_alloctrait_t traits_default[1]
+      = { { omp_atk_fallback, omp_atv_null_fb } };
+    omp_allocator_handle_t lowlat_default
+      = omp_init_allocator (omp_low_lat_mem_space, 1, traits_default);
+
+    void *a = omp_alloc (1, lowlat);	    // good
+    void *b = omp_alloc (1, lowlat_all);     // bad
+    void *c = omp_alloc (1, lowlat_default); // bad
+
+    if (!a || b || c)
+      __builtin_abort ();
+
+    omp_free (a, lowlat);
+
+
+    a = omp_calloc (1, 1, lowlat);	  // good
+    b = omp_calloc (1, 1, lowlat_all);     // bad
+    c = omp_calloc (1, 1, lowlat_default); // bad
+
+    if (!a || b || c)
+      __builtin_abort ();
+
+    omp_free (a, lowlat);
+
+
+    a = omp_realloc (NULL, 1, lowlat, lowlat);		      // good
+    b = omp_realloc (NULL, 1, lowlat_all, lowlat_all);	      // bad
+    c = omp_realloc (NULL, 1, lowlat_default, lowlat_default); // bad
+
+    if (!a || b || c)
+      __builtin_abort ();
+
+    omp_free (a, lowlat);
+  }
+
+  return 0;
+}
+