diff mbox series

[rs6000] Disable generation of scalar modulo instructions

Message ID 49f9e9ee-3137-e483-e337-ae030579bd6a@linux.ibm.com
State Not Applicable
Headers
Series [rs6000] Disable generation of scalar modulo instructions |

Checks

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

Commit Message

Pat Haugen April 7, 2023, 4:07 p.m. UTC 
  Disable generation of scalar modulo instructions.

It was recently discovered that the scalar modulo instructions can suffer
noticeable performance issues for certain input values. This patch disables
their generation since the equivalent div/mul/sub sequence does not suffer
the same problem.

Bootstrapped and regression tested on powerpc64le (Power10).
Ok for master and backports after burn in?

-Pat


2023-04-07  Pat Haugen  <pthaugen@linux.ibm.com>

gcc/
	* config/rs6000/rs6000.h (RS6000_DISABLE_SCALAR_MODULO): New.
	* config/rs6000/rs6000.md (mod<mode>3, *mod<mode>3): Use it.
	(define_expand umod<mode>3): New.
	(define_insn umod<mode>3): Rename to *umod<mode>3 and disable.

gcc/testsuite/
	* gcc.target/powerpc/clone1.c: Add xfails.
	* gcc.target/powerpc/clone3.c: Likewise.
	* gcc.target/powerpc/mod-1.c: Likewise.
	* gcc.target/powerpc/mod-2.c: Likewise.
diff mbox series

Patch

diff --git a/gcc/config/rs6000/rs6000.h b/gcc/config/rs6000/rs6000.h
index 3503614efbd..e4d9f357622 100644
--- a/gcc/config/rs6000/rs6000.h
+++ b/gcc/config/rs6000/rs6000.h
@@ -2492,3 +2492,9 @@  while (0)
         rs6000_asm_output_opcode (STREAM);				\
      }									\
    while (0)
+
+/* Disable generation of scalar modulo instructions for word/dword due to
+   performance issues with certain input values. This can be removed in the
+   future when the issues have been resolved.  */
+#define RS6000_DISABLE_SCALAR_MODULO 1
+
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 44f7dd509cb..a267b7ee2d0 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -3421,6 +3421,17 @@  (define_expand "mod<mode>3"
  	FAIL;

        operands[2] = force_reg (<MODE>mode, operands[2]);
+
+      if (RS6000_DISABLE_SCALAR_MODULO)
+	{
+	  temp1 = gen_reg_rtx (<MODE>mode);
+	  temp2 = gen_reg_rtx (<MODE>mode);
+
+	  emit_insn (gen_div<mode>3 (temp1, operands[1], operands[2]));
+	  emit_insn (gen_mul<mode>3 (temp2, temp1, operands[2]));
+	  emit_insn (gen_sub<mode>3 (operands[0], operands[1], temp2));
+	  DONE;
+	}
      }
    else
      {
@@ -3440,17 +3451,42 @@  (define_insn "*mod<mode>3"
    [(set (match_operand:GPR 0 "gpc_reg_operand" "=&r,r")
          (mod:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
  		 (match_operand:GPR 2 "gpc_reg_operand" "r,r")))]
-  "TARGET_MODULO"
+  "TARGET_MODULO && !RS6000_DISABLE_SCALAR_MODULO"
    "mods<wd> %0,%1,%2"
    [(set_attr "type" "div")
     (set_attr "size" "<bits>")])

+;; This define_expand can be removed when RS6000_DISABLE_SCALAR_MODULO is
+;; removed.
+(define_expand "umod<mode>3"
+  [(set (match_operand:GPR 0 "gpc_reg_operand")
+	(umod:GPR (match_operand:GPR 1 "gpc_reg_operand")
+		  (match_operand:GPR 2 "gpc_reg_operand")))]
+  ""
+{
+  rtx temp1;
+  rtx temp2;
+
+  if (!TARGET_MODULO)
+	FAIL;
+
+  if (RS6000_DISABLE_SCALAR_MODULO)
+    {
+      temp1 = gen_reg_rtx (<MODE>mode);
+      temp2 = gen_reg_rtx (<MODE>mode);
+
+      emit_insn (gen_udiv<mode>3 (temp1, operands[1], operands[2]));
+      emit_insn (gen_mul<mode>3 (temp2, temp1, operands[2]));
+      emit_insn (gen_sub<mode>3 (operands[0], operands[1], temp2));
+      DONE;
+    }
+})

-(define_insn "umod<mode>3"
+(define_insn "*umod<mode>3"
    [(set (match_operand:GPR 0 "gpc_reg_operand" "=&r,r")
          (umod:GPR (match_operand:GPR 1 "gpc_reg_operand" "r,r")
  		  (match_operand:GPR 2 "gpc_reg_operand" "r,r")))]
-  "TARGET_MODULO"
+  "TARGET_MODULO && !RS6000_DISABLE_SCALAR_MODULO"
    "modu<wd> %0,%1,%2"
    [(set_attr "type" "div")
     (set_attr "size" "<bits>")])
diff --git a/gcc/testsuite/gcc.target/powerpc/clone1.c 
b/gcc/testsuite/gcc.target/powerpc/clone1.c
index c69fd2aa1b8..74323ca0e8c 100644
--- a/gcc/testsuite/gcc.target/powerpc/clone1.c
+++ b/gcc/testsuite/gcc.target/powerpc/clone1.c
@@ -21,6 +21,7 @@  long mod_func_or (long a, long b, long c)
    return mod_func (a, b) | c;
  }

-/* { dg-final { scan-assembler-times {\mdivd\M}  1 } } */
-/* { dg-final { scan-assembler-times {\mmulld\M} 1 } } */
-/* { dg-final { scan-assembler-times {\mmodsd\M} 1 } } */
+/* { Fail due to RS6000_DISABLE_SCALAR_MODULO. */
+/* { dg-final { scan-assembler-times {\mdivd\M}  1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\mmulld\M} 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\mmodsd\M} 1 { xfail *-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/clone3.c 
b/gcc/testsuite/gcc.target/powerpc/clone3.c
index 911b88b781d..d3eb4dd2378 100644
--- a/gcc/testsuite/gcc.target/powerpc/clone3.c
+++ b/gcc/testsuite/gcc.target/powerpc/clone3.c
@@ -27,7 +27,8 @@  long mod_func_or (long a, long b, long c)
    return mod_func (a, b) | c;
  }

-/* { dg-final { scan-assembler-times {\mdivd\M}  1 } } */
-/* { dg-final { scan-assembler-times {\mmulld\M} 1 } } */
-/* { dg-final { scan-assembler-times {\mmodsd\M} 2 } } */
+/* { Fail due to RS6000_DISABLE_SCALAR_MODULO. */
+/* { dg-final { scan-assembler-times {\mdivd\M}  1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\mmulld\M} 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times {\mmodsd\M} 2 { xfail *-*-* } } } */
  /* { dg-final { scan-assembler-times {\mpld\M}   1 } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/mod-1.c 
b/gcc/testsuite/gcc.target/powerpc/mod-1.c
index 861ba670af4..74af98f5bc3 100644
--- a/gcc/testsuite/gcc.target/powerpc/mod-1.c
+++ b/gcc/testsuite/gcc.target/powerpc/mod-1.c
@@ -7,13 +7,14 @@  long lsmod (long a, long b) { return a%b; }
  unsigned int iumod (unsigned int a, unsigned int b) { return a%b; }
  unsigned long lumod (unsigned long a, unsigned long b) { return a%b; }

-/* { dg-final { scan-assembler-times "modsw " 1 } } */
-/* { dg-final { scan-assembler-times "modsd " 1 } } */
-/* { dg-final { scan-assembler-times "moduw " 1 } } */
-/* { dg-final { scan-assembler-times "modud " 1 } } */
-/* { dg-final { scan-assembler-not   "mullw "   } } */
-/* { dg-final { scan-assembler-not   "mulld "   } } */
-/* { dg-final { scan-assembler-not   "divw "    } } */
-/* { dg-final { scan-assembler-not   "divd "    } } */
-/* { dg-final { scan-assembler-not   "divwu "   } } */
-/* { dg-final { scan-assembler-not   "divdu "   } } */
+/* { Fail due to RS6000_DISABLE_SCALAR_MODULO. */
+/* { dg-final { scan-assembler-times "modsw " 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times "modsd " 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times "moduw " 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times "modud " 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "mullw "   { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "mulld "   { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "divw "    { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "divd "    { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "divwu "   { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "divdu "   { xfail *-*-* } } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/mod-2.c 
b/gcc/testsuite/gcc.target/powerpc/mod-2.c
index 441ec5878f1..896e2e35260 100644
--- a/gcc/testsuite/gcc.target/powerpc/mod-2.c
+++ b/gcc/testsuite/gcc.target/powerpc/mod-2.c
@@ -5,8 +5,9 @@ 
  int ismod (int a, int b) { return a%b; }
  unsigned int iumod (unsigned int a, unsigned int b) { return a%b; }

-/* { dg-final { scan-assembler-times "modsw " 1 } } */
-/* { dg-final { scan-assembler-times "moduw " 1 } } */
-/* { dg-final { scan-assembler-not   "mullw "   } } */
-/* { dg-final { scan-assembler-not   "divw "    } } */
-/* { dg-final { scan-assembler-not   "divwu "   } } */
+/* { Fail due to RS6000_DISABLE_SCALAR_MODULO. */
+/* { dg-final { scan-assembler-times "modsw " 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-times "moduw " 1 { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "mullw "   { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "divw "    { xfail *-*-* } } } */
+/* { dg-final { scan-assembler-not   "divwu "   { xfail *-*-* } } } */