Use GFX9 granulated sgprs count correctly.

2019-11-22  Andrew Stubbs  <ams@codesourcery.com>

	gcc/
	* config/gcn/gcn.c (gcn_hsa_declare_function_name): Calculate
	granulated_sgprs according to architecture.

From-SVN: r278617

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 62ddef2..2512838 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2019-11-22  Andrew Stubbs  <ams@codesourcery.com>
+
+       * config/gcn/gcn.c (gcn_hsa_declare_function_name): Calculate
+       granulated_sgprs according to architecture.
+
 2019-11-22  Jan Hubicka  <jh@suse.cz>
 
        * ggc-page.c (ggc_collect): Call memory_block_pool::trim.

diff --git a/gcc/config/gcn/gcn.c b/gcc/config/gcn/gcn.c
index 26c1067..3a8c10e 100644 (file)
--- a/gcc/config/gcn/gcn.c
+++ b/gcc/config/gcn/gcn.c
@@ -4922,6 +4922,14 @@ gcn_hsa_declare_function_name (FILE *file, const char *name, tree)
        sgpr = MAX_NORMAL_SGPR_COUNT - extra_regs;
     }
 
+  /* GFX8 allocates SGPRs in blocks of 8.
+     GFX9 uses blocks of 16.  */
+  int granulated_sgprs;
+  if (TARGET_GCN3)
+    granulated_sgprs = (sgpr + extra_regs + 7) / 8 - 1;
+  else if (TARGET_GCN5)
+    granulated_sgprs = 2 * ((sgpr + extra_regs + 15) / 16 - 1);
+
   fputs ("\t.align\t256\n", file);
   fputs ("\t.type\t", file);
   assemble_name (file, name);
@@ -4960,7 +4968,7 @@ gcn_hsa_declare_function_name (FILE *file, const char *name, tree)
           "\t\tcompute_pgm_rsrc2_excp_en = 0\n",
           (vgpr - 1) / 4,
           /* Must match wavefront_sgpr_count */
-          (sgpr + extra_regs + 7) / 8 - 1,
+          granulated_sgprs,
           /* The total number of SGPR user data registers requested.  This
              number must match the number of user data registers enabled.  */
           cfun->machine->args.nsgprs);