libgomp: Add is_integrated_apu function to plugin/plugin-{gcn,nvptx}.c

The added function is currently '#if 0' but is planned to be used to enable
self mapping automatically. Prerequisite for auto self maps is still mapping
'declare target' variables (if any, in libgomp) or converting all
'declare target' variables to 'declare target link' in the compiler
(as required for 'omp requires self_maps').

include/ChangeLog:

	* hsa_ext_amd.h (enum hsa_amd_agent_info_s): Add
	HSA_AMD_AGENT_INFO_MEMORY_PROPERTIES.
	(enum): Add HSA_AMD_MEMORY_PROPERTY_AGENT_IS_APU.

libgomp/ChangeLog:

	* plugin/plugin-gcn.c (is_integrated_apu): New; currently '#if 0'.
	* plugin/plugin-nvptx.c (is_integrated_apu): Likewise.

diff --git a/include/hsa_ext_amd.h b/include/hsa_ext_amd.h
index c1c16536621a54a9ce400676f39cc1b9f1911f0d..e29e88090eb02a468e347faaa63e27d7c0762086 100644 (file)
--- a/include/hsa_ext_amd.h
+++ b/include/hsa_ext_amd.h
@@ -168,9 +168,17 @@ typedef enum hsa_amd_agent_info_s {
    * selective workarounds for hardware errata.
    * The type of this attribute is uint32_t.
    */
-  HSA_AMD_AGENT_INFO_ASIC_REVISION = 0xA012
+  HSA_AMD_AGENT_INFO_ASIC_REVISION = 0xA012,
+
+  /* Bitmask with memory properties of the agent.  */
+  HSA_AMD_AGENT_INFO_MEMORY_PROPERTIES = 0xA114
 } hsa_amd_agent_info_t;
 
+
+enum {
+  HSA_AMD_MEMORY_PROPERTY_AGENT_IS_APU = (1 << 0)
+};
+
 typedef struct hsa_amd_hdp_flush_s {
   uint32_t* HDP_MEM_FLUSH_CNTL;
   uint32_t* HDP_REG_FLUSH_CNTL;

diff --git a/libgomp/plugin/plugin-gcn.c b/libgomp/plugin/plugin-gcn.c
index 18f01e090023e12da1b61f6dc1f0be4364a5ef60..cd5a19b03551a4769f900ee39cb5c4929de89cef 100644 (file)
--- a/libgomp/plugin/plugin-gcn.c
+++ b/libgomp/plugin/plugin-gcn.c
@@ -3331,6 +3331,61 @@ gcn_exec (struct kernel_info *kernel,
 /* }}}  */
 /* {{{ Generic Plugin API  */
 
+#if 0  /* TODO: Use to enable self-mapping/USM automatically.  */
+/* FIXME: The auto-self-map feature depends on still mapping 'declare target'
+   variables, even if ignoring all other mappings. Cf. PR 115279.  */
+
+/* Return TRUE if the GPU is an APU, i.e. the GPU is integrated with the CPU
+   such that both use the same memory controller such that mapping or memory
+   migration is pointless.  If CHECK_XNACK is TRUE, it additionally requires
+   that the GPU has *no* XNACK support otherwise FALSE is returned.
+
+   In theory, enabling unified-shared memory for APUs should always work,
+   however, with AMD GPUs some APUs (e.g. MI300A) still require XNACK to be
+   enabled as it is required to handle page faults.
+
+   Thus, for unified-shared memory access, either of the following must hold:
+   * HSA_AMD_SYSTEM_INFO_SVM_ACCESSIBLE_BY_DEFAULT is TRUE
+     This implies that all GPUs support USM access, either directly (as APU)
+     or via page migration.  For MI300A, this is only the case if
+     HSA_AMD_SYSTEM_INFO_XNACK_ENABLED is TRUE.
+   * If the GPU an APU *and* it does not support XNACK.  */
+
+static bool
+is_integrated_apu (struct agent_info *agent, bool check_xnack)
+{
+  enum {
+    HSACO_ATTR_UNSUPPORTED,
+    HSACO_ATTR_OFF,
+    HSACO_ATTR_ON,
+    HSACO_ATTR_ANY,
+    HSACO_ATTR_DEFAULT
+  };
+
+  bool is_apu;
+  uint8_t mem_prop[8];
+  hsa_status_t status;
+
+  status = hsa_fns.hsa_agent_get_info_fn (
+            agent->id, (hsa_agent_info_t) HSA_AMD_AGENT_INFO_MEMORY_PROPERTIES,
+            mem_prop);
+  _Static_assert (HSA_AMD_MEMORY_PROPERTY_AGENT_IS_APU < 8,
+                 "HSA_AMD_MEMORY_PROPERTY_AGENT_IS_APU < 8");
+  is_apu = (status == HSA_STATUS_SUCCESS
+           && (mem_prop[0] & (1 << HSA_AMD_MEMORY_PROPERTY_AGENT_IS_APU)));
+
+  if (check_xnack)
+    switch(agent->device_isa)
+      {
+#define GCN_DEVICE(name, NAME, ELF, ISA, XNACK, ...) \
+      case ELF: return is_apu && (XNACK == HSACO_ATTR_UNSUPPORTED);
+#include "../../gcc/config/gcn/gcn-devices.def"
+      default: return false;  /* Just to be save.  */
+      }
+  return is_apu;
+}
+#endif
+
 /* Return the name of the accelerator, which is "gcn".  */
 
 const char *

diff --git a/libgomp/plugin/plugin-nvptx.c b/libgomp/plugin/plugin-nvptx.c
index eb7b5e59d8f7d21c7383b6effbc859fb661f20e0..92c62ee5b8686958c13b6fe06490b7ea345844aa 100644 (file)
--- a/libgomp/plugin/plugin-nvptx.c
+++ b/libgomp/plugin/plugin-nvptx.c
@@ -1246,6 +1246,24 @@ nvptx_get_current_cuda_context (void)
   return nvthd->ptx_dev->ctx;
 }
 
+#if 0  /* TODO: Use to enable self-mapping/USM automatically.  */
+/* FIXME: The auto-self-map feature depends on still mapping 'declare target'
+   variables, even if ignoring all other mappings. Cf. PR 115279.  */
+
+/* Return TRUE if the GPU is integrated with host memory, i.e. GPU and
+   host share the same memory controller.  As of Oct 2025, no such
+   Nvidia GPU seems to exist.  */
+static bool
+is_integrated_apu (struct ptx_device *ptx_dev)
+{
+  int pi;
+  CUresult r;
+  r = CUDA_CALL_NOCHECK (cuDeviceGetAttribute, &pi,
+                        CU_DEVICE_ATTRIBUTE_INTEGRATED, ptx_dev->dev);
+  return (r == CUDA_SUCCESS && pi == 1);
+}
+#endif
+
 /* Plugin entry points.  */
 
 const char *