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

8 files changed, 253 insertions, 4 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3d20349..cb473f5 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+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.
diff --git a/gcc/combine.c b/gcc/combine.c
index a0214d1..4d24807 100644
--- a/gcc/combine.c
+++ b/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))
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 853dab2..16f083b 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/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")])
 
diff --git a/gcc/doc/md.texi b/gcc/doc/md.texi
index c4501ee..bc187c5 100644
--- a/gcc/doc/md.texi
+++ b/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
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 0695cfb..c8181d4 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,9 @@
+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.
diff --git a/gcc/testsuite/gcc.dg/ppc-fmadd-1.c b/gcc/testsuite/gcc.dg/ppc-fmadd-1.c
new file mode 100644
index 0000000..ff959f2
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ppc-fmadd-1.c
@@ -0,0 +1,43 @@
+/* { 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
+}
diff --git a/gcc/testsuite/gcc.dg/ppc-fmadd-2.c b/gcc/testsuite/gcc.dg/ppc-fmadd-2.c
new file mode 100644
index 0000000..02ed811
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ppc-fmadd-2.c
@@ -0,0 +1,27 @@
+/* { 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
+}
diff --git a/gcc/testsuite/gcc.dg/ppc-fmadd-3.c b/gcc/testsuite/gcc.dg/ppc-fmadd-3.c
new file mode 100644
index 0000000..d420522
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ppc-fmadd-3.c
@@ -0,0 +1,36 @@
+/* { 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
+}
+