[gcc/devel/omp/gcc-12] amdgcn, openmp: Auto-detect USM mode and set HSA_XNACK

[gcc/devel/omp/gcc-12] amdgcn, openmp: Auto-detect USM mode and set HSA_XNACK

[Kwok Yeung]

https://gcc.gnu.org/g:687640af27af0d2a5bd92a5de44a9a7d33526052

commit 687640af27af0d2a5bd92a5de44a9a7d33526052
Author: Andrew Stubbs <ams@codesourcery.com>
Date:   Fri Jun 17 13:07:11 2022 +0100

    amdgcn, openmp: Auto-detect USM mode and set HSA_XNACK
    
    The AMD GCN runtime must be set to the correct mode for Unified Shared Memory
    to work, but this is not always clear at compile and link time due to the split
    nature of the offload compilation pipeline.
    
    This patch sets a new attribute on OpenMP offload functions to ensure that the
    information is passed all the way to the backend.  The backend then places a
    marker in the assembler code for mkoffload to find. Finally mkoffload places a
    constructor function into the final program to ensure that the HSA_XNACK
    environment variable passes the correct mode to the GPU.
    
    The HSA_XNACK variable must be set before the HSA runtime is even loaded, so
    it makes more sense to have this set within the constructor than at some point
    later within libgomp or the GCN plugin.
    
    gcc/ChangeLog:
    
            * config/gcn/gcn.c (unified_shared_memory_enabled): New variable.
            (gcn_init_cumulative_args): Handle attribute "omp unified memory".
            (gcn_hsa_declare_function_name): Emit "MKOFFLOAD OPTIONS: USM+".
            * config/gcn/mkoffload.c (TEST_XNACK_OFF): New macro.
            (process_asm): Detect "MKOFFLOAD OPTIONS: USM+".
            Emit configure_xnack constructor, as required.
            * omp-low.c (create_omp_child_function): Add attribute "omp unified
            memory".

Diff:
---
 gcc/ChangeLog.omp           | 11 +++++++++++
 gcc/config/gcn/gcn.cc       | 28 +++++++++++++++++++++++++++-
 gcc/config/gcn/mkoffload.cc | 37 ++++++++++++++++++++++++++++++++++++-
 gcc/omp-low.cc              |  4 ++++
 4 files changed, 78 insertions(+), 2 deletions(-)

diff --git a/gcc/ChangeLog.omp b/gcc/ChangeLog.omp
index 7af24604841..6e059579a81 100644
--- a/gcc/ChangeLog.omp
+++ b/gcc/ChangeLog.omp
@@ -1,3 +1,14 @@
+2022-06-17  Andrew Stubbs  <ams@codesourcery.com>
+
+	* config/gcn/gcn.c (unified_shared_memory_enabled): New variable.
+	(gcn_init_cumulative_args): Handle attribute "omp unified memory".
+	(gcn_hsa_declare_function_name): Emit "MKOFFLOAD OPTIONS: USM+".
+	* config/gcn/mkoffload.c (TEST_XNACK_OFF): New macro.
+	(process_asm): Detect "MKOFFLOAD OPTIONS: USM+".
+	Emit configure_xnack constructor, as required.
+	* omp-low.c (create_omp_child_function): Add attribute "omp unified
+	memory".
+
 2022-06-10  Andrew Stubbs  <ams@codesourcery.com>
 
 	* config/gcn/gcn-hsa.h (XNACKOPT): New macro.
diff --git a/gcc/config/gcn/gcn.cc b/gcc/config/gcn/gcn.cc
index 15aa8c138ee..98e56305436 100644
--- a/gcc/config/gcn/gcn.cc
+++ b/gcc/config/gcn/gcn.cc
@@ -68,6 +68,11 @@ static bool ext_gcn_constants_init = 0;
 
 enum gcn_isa gcn_isa = ISA_GCN3;	/* Default to GCN3.  */
 
+/* Record whether the host compiler added "omp unifed memory" attributes to
+   any functions.  We can then pass this on to mkoffload to ensure xnack is
+   compatible there too.  */
+static bool unified_shared_memory_enabled = false;
+
 /* Reserve this much space for LDS (for propagating variables from
    worker-single mode to worker-partitioned mode), per workgroup.  Global
    analysis could calculate an exact bound, but we don't do that yet.
@@ -2542,6 +2547,25 @@ gcn_init_cumulative_args (CUMULATIVE_ARGS *cum /* Argument info to init */ ,
   if (!caller && cfun->machine->normal_function)
     gcn_detect_incoming_pointer_arg (fndecl);
 
+  if (fndecl && lookup_attribute ("omp unified memory",
+				  DECL_ATTRIBUTES (fndecl)))
+    {
+      unified_shared_memory_enabled = true;
+
+      switch (gcn_arch)
+	{
+	case PROCESSOR_FIJI:
+	case PROCESSOR_VEGA10:
+	case PROCESSOR_VEGA20:
+	  error ("GPU architecture does not support Unified Shared Memory");
+	default:
+	  ;
+	}
+
+      if (flag_xnack == HSACO_ATTR_OFF)
+	error ("Unified Shared Memory is enabled, but XNACK is disabled");
+    }
+
   reinit_regs ();
 }
 
@@ -5455,12 +5479,14 @@ gcn_hsa_declare_function_name (FILE *file, const char *name, tree)
   assemble_name (file, name);
   fputs (":\n", file);
 
-  /* This comment is read by mkoffload.  */
+  /* These comments are read by mkoffload.  */
   if (flag_openacc)
     fprintf (file, "\t;; OPENACC-DIMS: %d, %d, %d : %s\n",
 	     oacc_get_fn_dim_size (cfun->decl, GOMP_DIM_GANG),
 	     oacc_get_fn_dim_size (cfun->decl, GOMP_DIM_WORKER),
 	     oacc_get_fn_dim_size (cfun->decl, GOMP_DIM_VECTOR), name);
+  if (unified_shared_memory_enabled)
+    fprintf (asm_out_file, "\t;; MKOFFLOAD OPTIONS: USM+\n");
 }
 
 /* Implement TARGET_ASM_SELECT_SECTION.
diff --git a/gcc/config/gcn/mkoffload.cc b/gcc/config/gcn/mkoffload.cc
index 16c479b6f5a..c430c4e8cee 100644
--- a/gcc/config/gcn/mkoffload.cc
+++ b/gcc/config/gcn/mkoffload.cc
@@ -80,6 +80,8 @@
 			     == EF_AMDGPU_FEATURE_XNACK_ANY_V4)
 #define TEST_XNACK_ON(VAR) ((VAR & EF_AMDGPU_FEATURE_XNACK_V4) \
 			    == EF_AMDGPU_FEATURE_XNACK_ON_V4)
+#define TEST_XNACK_OFF(VAR) ((VAR & EF_AMDGPU_FEATURE_XNACK_V4) \
+			     == EF_AMDGPU_FEATURE_XNACK_OFF_V4)
 
 #define SET_SRAM_ECC_ON(VAR) VAR = ((VAR & ~EF_AMDGPU_FEATURE_SRAMECC_V4) \
 				    | EF_AMDGPU_FEATURE_SRAMECC_ON_V4)
@@ -474,6 +476,7 @@ static void
 process_asm (FILE *in, FILE *out, FILE *cfile)
 {
   int fn_count = 0, var_count = 0, dims_count = 0, regcount_count = 0;
+  bool unified_shared_memory_enabled = false;
   struct obstack fns_os, dims_os, regcounts_os;
   obstack_init (&fns_os);
   obstack_init (&dims_os);
@@ -498,6 +501,7 @@ process_asm (FILE *in, FILE *out, FILE *cfile)
   fn_count += 2;
 
   char buf[1000];
+  char dummy;
   enum
     { IN_CODE,
       IN_METADATA,
@@ -517,6 +521,9 @@ process_asm (FILE *in, FILE *out, FILE *cfile)
 		dims_count++;
 	      }
 
+	    if (sscanf (buf, " ;; MKOFFLOAD OPTIONS: USM+%c", &dummy) > 0)
+	      unified_shared_memory_enabled = true;
+
 	    break;
 	  }
 	case IN_METADATA:
@@ -565,7 +572,6 @@ process_asm (FILE *in, FILE *out, FILE *cfile)
 	  }
 	}
 
-      char dummy;
       if (sscanf (buf, " .section .gnu.offload_vars%c", &dummy) > 0)
 	{
 	  state = IN_VARS;
@@ -616,6 +622,7 @@ process_asm (FILE *in, FILE *out, FILE *cfile)
 
   fprintf (cfile, "#include <stdlib.h>\n");
   fprintf (cfile, "#include <stdbool.h>\n\n");
+  fprintf (cfile, "#include <stdio.h>\n\n");
 
   fprintf (cfile, "static const int gcn_num_vars = %d;\n\n", var_count);
 
@@ -656,6 +663,34 @@ process_asm (FILE *in, FILE *out, FILE *cfile)
     }
   fprintf (cfile, "\n};\n\n");
 
+  /* Emit a constructor function to set the HSA_XNACK environment variable.
+     This must be done before the ROCr runtime library is loaded.
+     We never override a user value (exit empty string), but we do emit a
+     useful diagnostic in the wrong mode (the ROCr message is not good.  */
+  if (TEST_XNACK_OFF (elf_flags) && unified_shared_memory_enabled)
+    fatal_error (input_location,
+		 "conflicting settings; XNACK is forced off but Unified "
+		 "Shared Memory is on");
+  if (!TEST_XNACK_ANY (elf_flags) || unified_shared_memory_enabled)
+    fprintf (cfile,
+	     "static __attribute__((constructor))\n"
+	     "void configure_xnack (void)\n"
+	     "{\n"
+	     "  const char *val = getenv (\"HSA_XNACK\");\n"
+	     "  if (!val || val[0] == '\\0')\n"
+	     "    setenv (\"HSA_XNACK\", \"%d\", true);\n"
+	     "  else if (%s)\n"
+	     "    {\n"
+	     "      fprintf (stderr, \"error: HSA_XNACK=%%s is incompatible; "
+			    "please unset\\n\", val);\n"
+	     "      exit (1);\n"
+	     "    }\n"
+	     "}\n\n",
+	     unified_shared_memory_enabled || TEST_XNACK_ON (elf_flags),
+	     (unified_shared_memory_enabled || TEST_XNACK_ON (elf_flags)
+	      ? "val[0] != '1' || val[1] != '\\0'"
+	      : "val[0] == '1' && val[1] == '\\0'"));
+
   obstack_free (&fns_os, NULL);
   for (i = 0; i < dims_count; i++)
     free (dims[i].name);
diff --git a/gcc/omp-low.cc b/gcc/omp-low.cc
index dc53373cac7..04b315d47b6 100644
--- a/gcc/omp-low.cc
+++ b/gcc/omp-low.cc
@@ -2413,6 +2413,10 @@ create_omp_child_function (omp_context *ctx, bool task_copy)
 	DECL_ATTRIBUTES (decl)
 	  = tree_cons (get_identifier (target_attr),
 		       NULL_TREE, DECL_ATTRIBUTES (decl));
+      if (flag_offload_memory == OFFLOAD_MEMORY_UNIFIED)
+	DECL_ATTRIBUTES (decl)
+	  = tree_cons (get_identifier ("omp unified memory"),
+		       NULL_TREE, DECL_ATTRIBUTES (decl));
     }
 
   t = build_decl (DECL_SOURCE_LOCATION (decl),