From: Andrew Stubbs <ams@codesourcery.com>
Date: Fri, 19 Jul 2019 16:06:50 +0000 (+0100)
Subject: Use GFX9 granulated sgprs count correctly.
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=993d229d9afc275a5f44023d74098bbf03200d97;p=thirdparty%2Fgcc.git

Use GFX9 granulated sgprs count correctly.

2019-09-10  Andrew Stubbs  <ams@codesourcery.com>

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

(cherry picked from openacc-gcc-9-branch commit
68e905b7879641dbae193cec7db71e62b48145c1)
---

diff --git a/gcc/ChangeLog.omp b/gcc/ChangeLog.omp
index c44cffb10413..7a3cc7f5491e 100644
--- a/gcc/ChangeLog.omp
+++ b/gcc/ChangeLog.omp
@@ -1,3 +1,8 @@
+2019-09-10  Andrew Stubbs  <ams@codesourcery.com>
+
+	* config/gcn/gcn.c (gcn_hsa_declare_function_name): Calculate
+	granulated_sgprs according to architecture.
+
 2019-09-09  Andrew Stubbs  <ams@codesourcery.com>
 
 	* config/gcn/gcn-run.c (heap_region): New global variable.
diff --git a/gcc/config/gcn/gcn.c b/gcc/config/gcn/gcn.c
index 66854b6f9c5d..f8434e4a4f11 100644
--- a/gcc/config/gcn/gcn.c
+++ b/gcc/config/gcn/gcn.c
@@ -4884,6 +4884,14 @@ gcn_hsa_declare_function_name (FILE *file, const char *name, tree)
 	sgpr = 102 - 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);
@@ -4922,7 +4930,7 @@ 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);