Index: gcc/ChangeLog

2002-12-02  Geoffrey Keating  <geoffk@apple.com>

	* combine.c (combine_simplify_rtx): Add new canonicalizations.
	* doc/md.texi (Insn Canonicalizations): Document new
	canonicalizations for multiply/add combinations.
	* config/rs6000/rs6000.md: Add and modify floating add/multiply
	patterns to ensure they're used whenever they can be.

Index: gcc/testsuite/ChangeLog
2002-12-02  Geoffrey Keating  <geoffk@apple.com>

	* gcc.dg/ppc-fmadd-1.c: New file.
	* gcc.dg/ppc-fmadd-2.c: New file.
	* gcc.dg/ppc-fmadd-3.c: New file.

From-SVN: r59841

gcc/ChangeLog

+2002-12-04  Geoffrey Keating  <geoffk@apple.com>
+
+	* combine.c (combine_simplify_rtx): Add new canonicalizations.
+	* doc/md.texi (Insn Canonicalizations): Document new
+	canonicalizations for multiply/add combinations.
+	* config/rs6000/rs6000.md: Add and modify floating add/multiply
+	patterns to ensure they're used whenever they can be.
+
 2002-12-04  Kazu Hirata  <kazu@cs.umass.edu>
 
 	* config/h8300/h8300.c: Update the comments related to shifts.

gcc/combine.c

@@ -4029,6 +4029,24 @@ combine_simplify_rtx (x, op0_mode, last, in_dest)
 	return gen_binary (MINUS, mode, XEXP (XEXP (x, 0), 1),
 			   XEXP (XEXP (x, 0), 0));
 
+      /* (neg (plus A B)) is canonicalized to (minus (neg A) B).  */
+      if (GET_CODE (XEXP (x, 0)) == PLUS
+	  && !HONOR_SIGNED_ZEROS (mode)
+	  && !HONOR_SIGN_DEPENDENT_ROUNDING (mode))
+	{
+	  temp = simplify_gen_unary (NEG, mode, XEXP (XEXP (x, 0), 0), mode);
+	  temp = combine_simplify_rtx (temp, mode, last, in_dest);
+	  return gen_binary (MINUS, mode, temp, XEXP (XEXP (x, 0), 1));
+	}
+
+      /* (neg (mult A B)) becomes (mult (neg A) B).  
+         This works even for floating-point values.  */
+      if (GET_CODE (XEXP (x, 0)) == MULT)
+	{
+	  temp = simplify_gen_unary (NEG, mode, XEXP (XEXP (x, 0), 0), mode);
+	  return gen_binary (MULT, mode, temp, XEXP (XEXP (x, 0), 1));
+	}
+
       /* (neg (xor A 1)) is (plus A -1) if A is known to be either 0 or 1.  */
       if (GET_CODE (XEXP (x, 0)) == XOR && XEXP (XEXP (x, 0), 1) == const1_rtx
 	  && nonzero_bits (XEXP (XEXP (x, 0), 0), mode) == 1)
@@ -4217,6 +4235,19 @@ combine_simplify_rtx (x, op0_mode, last, in_dest)
 #endif
 
     case PLUS:
+      /* Canonicalize (plus (mult (neg B) C) A) to (minus A (mult B C)).
+       */
+      if (GET_CODE (XEXP (x, 0)) == MULT 
+	  && GET_CODE (XEXP (XEXP (x, 0), 0)) == NEG)
+	{
+	  rtx in1, in2;
+	 
+	  in1 = XEXP (XEXP (XEXP (x, 0), 0), 0);
+	  in2 = XEXP (XEXP (x, 0), 1);
+	  return gen_binary (MINUS, mode, XEXP (x, 1),
+			     gen_binary (MULT, mode, in1, in2));
+	}
+
       /* If we have (plus (plus (A const) B)), associate it so that CONST is
 	 outermost.  That's because that's the way indexed addresses are
 	 supposed to appear.  This code used to check many more cases, but
@@ -4323,6 +4354,32 @@ combine_simplify_rtx (x, op0_mode, last, in_dest)
 	return simplify_and_const_int (NULL_RTX, mode, XEXP (x, 0),
 				       -INTVAL (XEXP (XEXP (x, 1), 1)) - 1);
 
+      /* Canonicalize (minus A (mult (neg B) C)) to (plus (mult B C) A).
+       */
+      if (GET_CODE (XEXP (x, 1)) == MULT 
+	  && GET_CODE (XEXP (XEXP (x, 1), 0)) == NEG)
+	{
+	  rtx in1, in2;
+	 
+	  in1 = XEXP (XEXP (XEXP (x, 1), 0), 0);
+	  in2 = XEXP (XEXP (x, 1), 1);
+	  return gen_binary (PLUS, mode, gen_binary (MULT, mode, in1, in2),
+			     XEXP (x, 0));
+	}
+
+       /* Canonicalize (minus (neg A) (mult B C)) to 
+	  (minus (mult (neg B) C) A). */
+      if (GET_CODE (XEXP (x, 1)) == MULT 
+	  && GET_CODE (XEXP (x, 0)) == NEG)
+	{
+	  rtx in1, in2;
+	 
+	  in1 = simplify_gen_unary (NEG, mode, XEXP (XEXP (x, 1), 0), mode);
+	  in2 = XEXP (XEXP (x, 1), 1);
+	  return gen_binary (MINUS, mode, gen_binary (MULT, mode, in1, in2),
+			     XEXP (XEXP (x, 0), 0));
+	}
+
       /* Canonicalize (minus A (plus B C)) to (minus (minus A B) C) for
 	 integers.  */
       if (GET_CODE (XEXP (x, 1)) == PLUS && INTEGRAL_MODE_P (mode))

gcc/config/rs6000/rs6000.md

@@ -5280,7 +5280,18 @@
 	(neg:SF (plus:SF (mult:SF (match_operand:SF 1 "gpc_reg_operand" "%f")
 				  (match_operand:SF 2 "gpc_reg_operand" "f"))
 			 (match_operand:SF 3 "gpc_reg_operand" "f"))))]
-  "TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD"
+  "TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && HONOR_SIGNED_ZEROS (SFmode)"
+  "fnmadds %0,%1,%2,%3"
+  [(set_attr "type" "fp")])
+
+(define_insn ""
+  [(set (match_operand:SF 0 "gpc_reg_operand" "=f")
+	(minus:SF (mult:SF (neg:SF (match_operand:SF 1 "gpc_reg_operand" "f"))
+			   (match_operand:SF 2 "gpc_reg_operand" "f"))
+			 (match_operand:SF 3 "gpc_reg_operand" "f")))]
+  "TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && ! HONOR_SIGNED_ZEROS (SFmode)"
   "fnmadds %0,%1,%2,%3"
   [(set_attr "type" "fp")])
 
@@ -5295,10 +5306,31 @@
 
 (define_insn ""
   [(set (match_operand:SF 0 "gpc_reg_operand" "=f")
+	(minus:SF (mult:SF (neg:SF (match_operand:SF 1 "gpc_reg_operand" "f"))
+			   (match_operand:SF 2 "gpc_reg_operand" "f"))
+			 (match_operand:SF 3 "gpc_reg_operand" "f")))]
+  "! TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && ! HONOR_SIGNED_ZEROS (SFmode)"
+  "{fnma|fnmadd} %0,%1,%2,%3"
+  [(set_attr "type" "dmul")])
+
+(define_insn ""
+  [(set (match_operand:SF 0 "gpc_reg_operand" "=f")
 	(neg:SF (minus:SF (mult:SF (match_operand:SF 1 "gpc_reg_operand" "%f")
 				   (match_operand:SF 2 "gpc_reg_operand" "f"))
 			  (match_operand:SF 3 "gpc_reg_operand" "f"))))]
-  "TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD"
+  "TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && HONOR_SIGNED_ZEROS (SFmode)"
+  "fnmsubs %0,%1,%2,%3"
+  [(set_attr "type" "fp")])
+
+(define_insn ""
+  [(set (match_operand:SF 0 "gpc_reg_operand" "=f")
+	(minus:SF (match_operand:SF 3 "gpc_reg_operand" "f")
+		  (mult:SF (match_operand:SF 1 "gpc_reg_operand" "%f")
+			   (match_operand:SF 2 "gpc_reg_operand" "f"))))]
+  "TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && ! HONOR_SIGNED_ZEROS (SFmode)"
   "fnmsubs %0,%1,%2,%3"
   [(set_attr "type" "fp")])
 
@@ -5311,6 +5343,16 @@
   "{fnms|fnmsub} %0,%1,%2,%3"
   [(set_attr "type" "dmul")])
 
+(define_insn ""
+  [(set (match_operand:SF 0 "gpc_reg_operand" "=f")
+	(minus:SF (match_operand:SF 3 "gpc_reg_operand" "f")
+		  (mult:SF (match_operand:SF 1 "gpc_reg_operand" "%f")
+			   (match_operand:SF 2 "gpc_reg_operand" "f"))))]
+  "! TARGET_POWERPC && TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && ! HONOR_SIGNED_ZEROS (SFmode)"
+  "{fnms|fnmsub} %0,%1,%2,%3"
+  [(set_attr "type" "fp")])
+
 (define_expand "sqrtsf2"
   [(set (match_operand:SF 0 "gpc_reg_operand" "")
 	(sqrt:SF (match_operand:SF 1 "gpc_reg_operand" "")))]
@@ -5524,7 +5566,18 @@
 	(neg:DF (plus:DF (mult:DF (match_operand:DF 1 "gpc_reg_operand" "%f")
 				  (match_operand:DF 2 "gpc_reg_operand" "f"))
 			 (match_operand:DF 3 "gpc_reg_operand" "f"))))]
-  "TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD"
+  "TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && HONOR_SIGNED_ZEROS (DFmode)"
+  "{fnma|fnmadd} %0,%1,%2,%3"
+  [(set_attr "type" "dmul")])
+
+(define_insn ""
+  [(set (match_operand:DF 0 "gpc_reg_operand" "=f")
+	(minus:DF (mult:DF (neg:DF (match_operand:DF 1 "gpc_reg_operand" "f"))
+			   (match_operand:DF 2 "gpc_reg_operand" "f"))
+		  (match_operand:DF 3 "gpc_reg_operand" "f")))]
+  "TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && ! HONOR_SIGNED_ZEROS (DFmode)"
   "{fnma|fnmadd} %0,%1,%2,%3"
   [(set_attr "type" "dmul")])
 
@@ -5533,7 +5586,18 @@
 	(neg:DF (minus:DF (mult:DF (match_operand:DF 1 "gpc_reg_operand" "%f")
 				   (match_operand:DF 2 "gpc_reg_operand" "f"))
 			  (match_operand:DF 3 "gpc_reg_operand" "f"))))]
-  "TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD"
+  "TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD
+   && HONOR_SIGNED_ZEROS (DFmode)"
+  "{fnms|fnmsub} %0,%1,%2,%3"
+  [(set_attr "type" "dmul")])
+
+(define_insn ""
+  [(set (match_operand:DF 0 "gpc_reg_operand" "=f")
+	(minus:DF (match_operand:DF 3 "gpc_reg_operand" "f")
+	          (mult:DF (match_operand:DF 1 "gpc_reg_operand" "%f")
+			   (match_operand:DF 2 "gpc_reg_operand" "f"))))]
+  "TARGET_HARD_FLOAT && TARGET_FPRS && TARGET_FUSED_MADD 
+   && ! HONOR_SIGNED_ZEROS (DFmode)"
   "{fnms|fnmsub} %0,%1,%2,%3"
   [(set_attr "type" "dmul")])
 

gcc/doc/md.texi

@@ -3670,6 +3670,14 @@ For these operators, if only one operand is a @code{neg}, @code{not},
 @code{mult}, @code{plus}, or @code{minus} expression, it will be the
 first operand.
 
+@item
+In combinations of @code{neg}, @code{mult}, @code{plus}, and
+@code{minus}, the @code{neg} operations (if any) will be moved inside
+the operations as far as possible.  For instance, 
+@code{(neg (mult A B))} is canonicalized as @code{(mult (neg A) B)}, but
+@code{(plus (mult (neg A) B) C)} is canonicalized as
+@code{(minus A (mult B C))}.
+
 @cindex @code{compare}, canonicalization of
 @item
 For the @code{compare} operator, a constant is always the second operand

gcc/testsuite/ChangeLog

+2002-12-04  Geoffrey Keating  <geoffk@apple.com>
+
+	* gcc.dg/ppc-fmadd-1.c: New file.
+	* gcc.dg/ppc-fmadd-2.c: New file.
+	* gcc.dg/ppc-fmadd-3.c: New file.
+
 2002-12-04  Eric Botcazou  <ebotcazou@libertysurf.fr>
 
 	* gcc.c-torture/compile/20021204-1.c: New test.

gcc/testsuite/gcc.dg/ppc-fmadd-1.c

+/* { dg-do compile { target powerpc*-*-* } } */
+/* { dg-options "-ffast-math -O2" } */
+/* { dg-final { scan-assembler-not "f(add|sub|mul|neg)" } } */
+
+void foo(double *a, double *b, double *c, double *d)
+{
+  a[0] =  b[0] + c[0] * d[0];		// fmadd
+  a[1] =  b[1] - c[1] * d[1];		// fnmsub with fast-math
+  a[2] = -b[2] + c[2] * d[2];   	// fmsub
+  a[3] = -b[3] - c[3] * d[3];		// fnmadd with fast-math
+  a[4] = -( b[4] + c[4] * d[4]);	// fnmadd
+  a[5] = -( b[5] - c[5] * d[5]);	// fmsub with fast-math
+  a[6] = -(-b[6] + c[6] * d[6]);	// fnmsub
+  a[7] = -(-b[7] - c[7] * d[7]);	// fmadd with fast-math
+  a[10] =  b[10] - c[10] * -d[10];	// fmadd
+  a[11] =  b[11] + c[11] * -d[11];	// fnmsub with fast-math
+  a[12] = -b[12] - c[12] * -d[12];   	// fmsub
+  a[13] = -b[13] + c[13] * -d[13];	// fnmadd with fast-math
+  a[14] = -( b[14] - c[14] * -d[14]);	// fnmadd
+  a[15] = -( b[15] + c[15] * -d[15]);	// fmsub with fast-math
+  a[16] = -(-b[16] - c[16] * -d[16]);	// fnmsub
+  a[17] = -(-b[17] + c[17] * -d[17]);	// fmadd with fast-math
+}
+
+void foos(float *a, float *b, float *c, float *d)
+{
+  a[0] =  b[0] + c[0] * d[0];		// fmadd
+  a[1] =  b[1] - c[1] * d[1];		// fnmsub with fast-math
+  a[2] = -b[2] + c[2] * d[2];   	// fmsub
+  a[3] = -b[3] - c[3] * d[3];		// fnmadd with fast-math
+  a[4] = -( b[4] + c[4] * d[4]);	// fnmadd
+  a[5] = -( b[5] - c[5] * d[5]);	// fmsub with fast-math
+  a[6] = -(-b[6] + c[6] * d[6]);	// fnmsub
+  a[7] = -(-b[7] - c[7] * d[7]);	// fmadd with fast-math
+  a[10] =  b[10] - c[10] * -d[10];	// fmadd
+  a[11] =  b[11] + c[11] * -d[11];	// fnmsub with fast-math
+  a[12] = -b[12] - c[12] * -d[12];   	// fmsub
+  a[13] = -b[13] + c[13] * -d[13];	// fnmadd with fast-math
+  a[14] = -( b[14] - c[14] * -d[14]);	// fnmadd
+  a[15] = -( b[15] + c[15] * -d[15]);	// fmsub with fast-math
+  a[16] = -(-b[16] - c[16] * -d[16]);	// fnmsub
+  a[17] = -(-b[17] + c[17] * -d[17]);	// fmadd with fast-math
+}

gcc/testsuite/gcc.dg/ppc-fmadd-2.c

+/* { dg-do compile { target powerpc*-*-* } } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler-not "f(add|sub|mul|neg)" } } */
+
+void foo(double *a, double *b, double *c, double *d)
+{
+  a[0] =  b[0] + c[0] * d[0];		// fmadd
+  a[2] = -b[2] + c[2] * d[2];   	// fmsub
+  a[4] = -( b[4] + c[4] * d[4]);	// fnmadd
+  a[6] = -(-b[6] + c[6] * d[6]);	// fnmsub
+  a[10] =  b[10] - c[10] * -d[10];	// fmadd
+  a[12] = -b[12] - c[12] * -d[12];   	// fmsub
+  a[14] = -( b[14] - c[14] * -d[14]);	// fnmadd
+  a[16] = -(-b[16] - c[16] * -d[16]);	// fnmsub
+}
+
+void foos(float *a, float *b, float *c, float *d)
+{
+  a[0] =  b[0] + c[0] * d[0];		// fmadd
+  a[2] = -b[2] + c[2] * d[2];   	// fmsub
+  a[4] = -( b[4] + c[4] * d[4]);	// fnmadd
+  a[6] = -(-b[6] + c[6] * d[6]);	// fnmsub
+  a[10] =  b[10] - c[10] * -d[10];	// fmadd
+  a[12] = -b[12] - c[12] * -d[12];   	// fmsub
+  a[14] = -( b[14] - c[14] * -d[14]);	// fnmadd
+  a[16] = -(-b[16] - c[16] * -d[16]);	// fnmsub
+}

gcc/testsuite/gcc.dg/ppc-fmadd-3.c

+/* { dg-do compile { target powerpc*-*-* } } */
+/* { dg-options "-O2" } */
+/* { dg-final { scan-assembler-not "f(add|sub|mul)" } } */
+
+void foo(double *a, double *b, double *c, double *d)
+{
+#if 0
+  a[1] =  b[1] - c[1] * d[1];		// fneg, fmadd without fast-math
+#endif
+  a[3] = -b[3] - c[3] * d[3];		// fneg, fmsub without fast-math
+#if 0
+  a[5] = -( b[5] - c[5] * d[5]);	// fneg, fnmadd without fast-math
+#endif
+  a[7] = -(-b[7] - c[7] * d[7]);	// fneg, fnmsub without fast-math
+  a[11] =  b[11] + c[11] * -d[11];	// fneg, fmadd without fast-math
+  a[13] = -b[13] + c[13] * -d[13];	// fneg, fmsub without fast-math
+  a[15] = -( b[15] + c[15] * -d[15]);	// fneg, fnmadd without fast-math
+  a[17] = -(-b[17] + c[17] * -d[17]);	// fneg, fnmsub without fast-math
+}
+
+void foos(float *a, float *b, float *c, float *d)
+{
+#if 0
+  a[1] =  b[1] - c[1] * d[1];		// fneg, fmadd without fast-math
+#endif
+  a[3] = -b[3] - c[3] * d[3];		// fneg, fmsub without fast-math
+#if 0
+  a[5] = -( b[5] - c[5] * d[5]);	// fneg, fnmadd without fast-math
+#endif
+  a[7] = -(-b[7] - c[7] * d[7]);	// fneg, fnmsub without fast-math
+  a[11] =  b[11] + c[11] * -d[11];	// fneg, fmadd without fast-math
+  a[13] = -b[13] + c[13] * -d[13];	// fneg, fmsub without fast-math
+  a[15] = -( b[15] + c[15] * -d[15]);	// fneg, fnmadd without fast-math
+  a[17] = -(-b[17] + c[17] * -d[17]);	// fneg, fnmsub without fast-math
+}
+