Allow 4 operand FMAs on power7

From-SVN: r176522

gcc/ChangeLog

+2011-07-20  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	* config/rs6000/vsx.md (vsx_fma*): Use 4 argument fma instructions
+	where we can use them from the standard and altivec instruction
+	sets, instead of always using the 3 operand VSX forms that require
+	the destination to overlap one of the inputs.
+	(vsx_fms*): Ditto.
+	(vsx_fnma*): Ditto.
+	(vsx_fnms*): Ditto.
+
+	* config/rs6000/rs6000.md (fmadf4_fpr): Set fp_type fp_maddsub_d
+	for DF types.
+	(fmsdf4_fpr): Ditto.
+	(nfmadf4_fpr): Ditto.
+	(nfmsdf4_fpr): Ditto.
+
 2011-07-20  Sandra Loosemore  <sandra@codesourcery.com>
 
 	* genrecog.c (make_insn_sequence): Correct position numbering

gcc/config/rs6000/rs6000.md

@@ -6288,7 +6288,7 @@
    && VECTOR_UNIT_NONE_P (DFmode)"
   "{fma|fmadd} %0,%1,%2,%3"
   [(set_attr "type" "fp")
-   (set_attr "fp_type" "fp_maddsub_s")])
+   (set_attr "fp_type" "fp_maddsub_d")])
 
 (define_insn "*fmsdf4_fpr"
   [(set (match_operand:DF 0 "gpc_reg_operand" "=f")
@@ -6299,7 +6299,7 @@
    && VECTOR_UNIT_NONE_P (DFmode)"
   "{fms|fmsub} %0,%1,%2,%3"
   [(set_attr "type" "fp")
-   (set_attr "fp_type" "fp_maddsub_s")])
+   (set_attr "fp_type" "fp_maddsub_d")])
 
 (define_insn "*nfmadf4_fpr"
   [(set (match_operand:DF 0 "gpc_reg_operand" "=f")
@@ -6310,7 +6310,7 @@
    && VECTOR_UNIT_NONE_P (DFmode)"
   "{fnma|fnmadd} %0,%1,%2,%3"
   [(set_attr "type" "fp")
-   (set_attr "fp_type" "fp_maddsub_s")])
+   (set_attr "fp_type" "fp_maddsub_d")])
 
 (define_insn "*nfmsdf4_fpr"
   [(set (match_operand:DF 0 "gpc_reg_operand" "=f")
@@ -6321,7 +6321,7 @@
    && VECTOR_UNIT_NONE_P (DFmode)"
   "{fnms|fnmsub} %0,%1,%2,%3"
   [(set_attr "type" "fp")
-   (set_attr "fp_type" "fp_maddsub_s")])
+   (set_attr "fp_type" "fp_maddsub_d")])
 
 (define_expand "sqrtdf2"
   [(set (match_operand:DF 0 "gpc_reg_operand" "")

gcc/config/rs6000/vsx.md

@@ -524,46 +524,112 @@
   [(set_attr "type" "<VStype_simple>")
    (set_attr "fp_type" "<VSfptype_simple>")])
 
-;; Fused vector multiply/add instructions
-
-(define_insn "*vsx_fma<mode>4"
-  [(set (match_operand:VSX_B 0 "vsx_register_operand" "=<VSr>,<VSr>,?wa,?wa")
-	(fma:VSX_B
-	  (match_operand:VSX_B 1 "vsx_register_operand" "%<VSr>,<VSr>,wa,wa")
-	  (match_operand:VSX_B 2 "vsx_register_operand" "<VSr>,0,wa,0")
-	  (match_operand:VSX_B 3 "vsx_register_operand" "0,<VSr>,0,wa")))]
-  "VECTOR_UNIT_VSX_P (<MODE>mode)"
+;; Fused vector multiply/add instructions Support the classical DF versions of
+;; fma, which allows the target to be a separate register from the 3 inputs.
+;; Under VSX, the target must be either the addend or the first multiply.
+;; Where we can, also do the same for the Altivec V4SF fmas.
+
+(define_insn "*vsx_fmadf4"
+  [(set (match_operand:DF 0 "vsx_register_operand" "=ws,ws,?wa,?wa,d")
+	(fma:DF
+	  (match_operand:DF 1 "vsx_register_operand" "%ws,ws,wa,wa,d")
+	  (match_operand:DF 2 "vsx_register_operand" "ws,0,wa,0,d")
+	  (match_operand:DF 3 "vsx_register_operand" "0,ws,0,wa,d")))]
+  "VECTOR_UNIT_VSX_P (DFmode)"
   "@
-   x<VSv>madda<VSs> %x0,%x1,%x2
-   x<VSv>maddm<VSs> %x0,%x1,%x3
-   x<VSv>madda<VSs> %x0,%x1,%x2
-   x<VSv>maddm<VSs> %x0,%x1,%x3"
-  [(set_attr "type" "<VStype_mul>")
-   (set_attr "fp_type" "<VSfptype_mul>")])
+   xsmaddadp %x0,%x1,%x2
+   xsmaddmdp %x0,%x1,%x3
+   xsmaddadp %x0,%x1,%x2
+   xsmaddmdp %x0,%x1,%x3
+   {fma|fmadd} %0,%1,%2,%3"
+  [(set_attr "type" "fp")
+   (set_attr "fp_type" "fp_maddsub_d")])
+
+(define_insn "*vsx_fmav4sf4"
+  [(set (match_operand:V4SF 0 "vsx_register_operand" "=ws,ws,?wa,?wa,v")
+	(fma:V4SF
+	  (match_operand:V4SF 1 "vsx_register_operand" "%ws,ws,wa,wa,v")
+	  (match_operand:V4SF 2 "vsx_register_operand" "ws,0,wa,0,v")
+	  (match_operand:V4SF 3 "vsx_register_operand" "0,ws,0,wa,v")))]
+  "VECTOR_UNIT_VSX_P (V4SFmode)"
+  "@
+   xvmaddasp %x0,%x1,%x2
+   xvmaddmsp %x0,%x1,%x3
+   xvmaddasp %x0,%x1,%x2
+   xvmaddmsp %x0,%x1,%x3
+   vmaddfp %0,%1,%2,%3"
+  [(set_attr "type" "vecfloat")])
+
+(define_insn "*vsx_fmav2df4"
+  [(set (match_operand:V2DF 0 "vsx_register_operand" "=ws,ws,?wa,?wa")
+	(fma:V2DF
+	  (match_operand:V2DF 1 "vsx_register_operand" "%ws,ws,wa,wa")
+	  (match_operand:V2DF 2 "vsx_register_operand" "ws,0,wa,0")
+	  (match_operand:V2DF 3 "vsx_register_operand" "0,ws,0,wa")))]
+  "VECTOR_UNIT_VSX_P (V2DFmode)"
+  "@
+   xvmaddadp %x0,%x1,%x2
+   xvmaddmdp %x0,%x1,%x3
+   xvmaddadp %x0,%x1,%x2
+   xvmaddmdp %x0,%x1,%x3"
+  [(set_attr "type" "vecfloat")])
+
+(define_insn "*vsx_fmsdf4"
+  [(set (match_operand:DF 0 "vsx_register_operand" "=ws,ws,?wa,?wa,d")
+	(fma:DF
+	  (match_operand:DF 1 "vsx_register_operand" "%ws,ws,wa,wa,d")
+	  (match_operand:DF 2 "vsx_register_operand" "ws,0,wa,0,d")
+	  (neg:DF
+	    (match_operand:DF 3 "vsx_register_operand" "0,ws,0,wa,d"))))]
+  "VECTOR_UNIT_VSX_P (DFmode)"
+  "@
+   xsmsubadp %x0,%x1,%x2
+   xsmsubmdp %x0,%x1,%x3
+   xsmsubadp %x0,%x1,%x2
+   xsmsubmdp %x0,%x1,%x3
+   {fms|fmsub} %0,%1,%2,%3"
+  [(set_attr "type" "fp")
+   (set_attr "fp_type" "fp_maddsub_d")])
 
 (define_insn "*vsx_fms<mode>4"
-  [(set (match_operand:VSX_B 0 "vsx_register_operand" "=<VSr>,<VSr>,?wa,?wa")
-	(fma:VSX_B
-	  (match_operand:VSX_B 1 "vsx_register_operand" "%<VSr>,<VSr>,wa,wa")
-	  (match_operand:VSX_B 2 "vsx_register_operand" "<VSr>,0,wa,0")
-	  (neg:VSX_B
-	    (match_operand:VSX_B 3 "vsx_register_operand" "0,<VSr>,0,wa"))))]
+  [(set (match_operand:VSX_F 0 "vsx_register_operand" "=<VSr>,<VSr>,?wa,?wa")
+	(fma:VSX_F
+	  (match_operand:VSX_F 1 "vsx_register_operand" "%<VSr>,<VSr>,wa,wa")
+	  (match_operand:VSX_F 2 "vsx_register_operand" "<VSr>,0,wa,0")
+	  (neg:VSX_F
+	    (match_operand:VSX_F 3 "vsx_register_operand" "0,<VSr>,0,wa"))))]
   "VECTOR_UNIT_VSX_P (<MODE>mode)"
   "@
    x<VSv>msuba<VSs> %x0,%x1,%x2
    x<VSv>msubm<VSs> %x0,%x1,%x3
    x<VSv>msuba<VSs> %x0,%x1,%x2
    x<VSv>msubm<VSs> %x0,%x1,%x3"
-  [(set_attr "type" "<VStype_mul>")
-   (set_attr "fp_type" "<VSfptype_mul>")])
+  [(set_attr "type" "vecfloat")])
+
+(define_insn "*vsx_nfmadf4"
+  [(set (match_operand:DF 0 "vsx_register_operand" "=ws,ws,?wa,?wa,d")
+	(neg:DF
+	 (fma:DF
+	  (match_operand:DF 1 "vsx_register_operand" "ws,ws,wa,wa,d")
+	  (match_operand:DF 2 "vsx_register_operand" "ws,0,wa,0,d")
+	  (match_operand:DF 3 "vsx_register_operand" "0,ws,0,wa,d"))))]
+  "VECTOR_UNIT_VSX_P (DFmode)"
+  "@
+   xsnmaddadp %x0,%x1,%x2
+   xsnmaddmdp %x0,%x1,%x3
+   xsnmaddadp %x0,%x1,%x2
+   xsnmaddmdp %x0,%x1,%x3
+   {fnma|fnmadd} %0,%1,%2,%3"
+  [(set_attr "type" "fp")
+   (set_attr "fp_type" "fp_maddsub_d")])
 
 (define_insn "*vsx_nfma<mode>4"
-  [(set (match_operand:VSX_B 0 "vsx_register_operand" "=<VSr>,<VSr>,?wa,?wa")
-	(neg:VSX_B
-	 (fma:VSX_B
-	  (match_operand:VSX_B 1 "vsx_register_operand" "<VSr>,<VSr>,wa,wa")
-	  (match_operand:VSX_B 2 "vsx_register_operand" "<VSr>,0,wa,0")
-	  (match_operand:VSX_B 3 "vsx_register_operand" "0,<VSr>,0,wa"))))]
+  [(set (match_operand:VSX_F 0 "vsx_register_operand" "=<VSr>,<VSr>,?wa,?wa")
+	(neg:VSX_F
+	 (fma:VSX_F
+	  (match_operand:VSX_F 1 "vsx_register_operand" "<VSr>,<VSr>,wa,wa")
+	  (match_operand:VSX_F 2 "vsx_register_operand" "<VSr>,0,wa,0")
+	  (match_operand:VSX_F 3 "vsx_register_operand" "0,<VSr>,0,wa"))))]
   "VECTOR_UNIT_VSX_P (<MODE>mode)"
   "@
    x<VSv>nmadda<VSs> %x0,%x1,%x2
@@ -573,22 +639,56 @@
   [(set_attr "type" "<VStype_mul>")
    (set_attr "fp_type" "<VSfptype_mul>")])
 
-(define_insn "*vsx_nfms<mode>4"
-  [(set (match_operand:VSX_B 0 "vsx_register_operand" "=<VSr>,<VSr>,?wa,?wa")
-	(neg:VSX_B
-	 (fma:VSX_B
-	   (match_operand:VSX_B 1 "vsx_register_operand" "%<VSr>,<VSr>,wa,wa")
-	   (match_operand:VSX_B 2 "vsx_register_operand" "<VSr>,0,wa,0")
-	   (neg:VSX_B
-	     (match_operand:VSX_B 3 "vsx_register_operand" "0,<VSr>,0,wa")))))]
-  "VECTOR_UNIT_VSX_P (<MODE>mode)"
+(define_insn "*vsx_nfmsdf4"
+  [(set (match_operand:DF 0 "vsx_register_operand" "=ws,ws,?wa,?wa,d")
+	(neg:DF
+	 (fma:DF
+	   (match_operand:DF 1 "vsx_register_operand" "%ws,ws,wa,wa,d")
+	   (match_operand:DF 2 "vsx_register_operand" "ws,0,wa,0,d")
+	   (neg:DF
+	     (match_operand:DF 3 "vsx_register_operand" "0,ws,0,wa,d")))))]
+  "VECTOR_UNIT_VSX_P (DFmode)"
   "@
-   x<VSv>nmsuba<VSs> %x0,%x1,%x2
-   x<VSv>nmsubm<VSs> %x0,%x1,%x3
-   x<VSv>nmsuba<VSs> %x0,%x1,%x2
-   x<VSv>nmsubm<VSs> %x0,%x1,%x3"
-  [(set_attr "type" "<VStype_mul>")
-   (set_attr "fp_type" "<VSfptype_mul>")])
+   xsnmsubadp %x0,%x1,%x2
+   xsnmsubmdp %x0,%x1,%x3
+   xsnmsubadp %x0,%x1,%x2
+   xsnmsubmdp %x0,%x1,%x3
+   {fnms|fnmsub} %0,%1,%2,%3"
+  [(set_attr "type" "fp")
+   (set_attr "fp_type" "fp_maddsub_d")])
+
+(define_insn "*vsx_nfmsv4sf4"
+  [(set (match_operand:V4SF 0 "vsx_register_operand" "=wf,wf,?wa,?wa,v")
+	(neg:V4SF
+	 (fma:V4SF
+	   (match_operand:V4SF 1 "vsx_register_operand" "%wf,wf,wa,wa,v")
+	   (match_operand:V4SF 2 "vsx_register_operand" "wf,0,wa,0,v")
+	   (neg:V4SF
+	     (match_operand:V4SF 3 "vsx_register_operand" "0,wf,0,wa,v")))))]
+  "VECTOR_UNIT_VSX_P (V4SFmode)"
+  "@
+   xvnmsubasp %x0,%x1,%x2
+   xvnmsubmsp %x0,%x1,%x3
+   xvnmsubasp %x0,%x1,%x2
+   xvnmsubmsp %x0,%x1,%x3
+   vnmsubfp %0,%1,%2,%3"
+  [(set_attr "type" "vecfloat")])
+
+(define_insn "*vsx_nfmsv2df4"
+  [(set (match_operand:V2DF 0 "vsx_register_operand" "=wd,wd,?wa,?wa")
+	(neg:V2DF
+	 (fma:V2DF
+	   (match_operand:V2DF 1 "vsx_register_operand" "%wd,wd,wa,wa")
+	   (match_operand:V2DF 2 "vsx_register_operand" "wd,0,wa,0")
+	   (neg:V2DF
+	     (match_operand:V2DF 3 "vsx_register_operand" "0,wd,0,wa")))))]
+  "VECTOR_UNIT_VSX_P (V2DFmode)"
+  "@
+   xvnmsubadp %x0,%x1,%x2
+   xvnmsubmdp %x0,%x1,%x3
+   xvnmsubadp %x0,%x1,%x2
+   xvnmsubmdp %x0,%x1,%x3"
+  [(set_attr "type" "vecfloat")])
 
 ;; Vector conditional expressions (no scalar version for these instructions)
 (define_insn "vsx_eq<mode>"

gcc/testsuite/ChangeLog

+2011-07-20  Michael Meissner  <meissner@linux.vnet.ibm.com>
+
+	* gcc.target/powerpc/ppc-fma-1.c: Adjust to allow non-VSX fmas to
+	be generated.
+	* gcc.target/powerpc/ppc-fma-2.c: Ditto.
+	* gcc.target/powerpc/recip-3.c: Ditto.
+
 2011-07-19  Jason Merrill  <jason@redhat.com>
 
 	PR c++/6709 (DR 743)

gcc/testsuite/gcc.target/powerpc/ppc-fma-1.c

@@ -3,16 +3,16 @@
 /* { dg-require-effective-target powerpc_vsx_ok } */
 /* { dg-options "-O3 -ftree-vectorize -mcpu=power7 -ffast-math" } */
 /* { dg-final { scan-assembler-times "xvmadd" 4 } } */
-/* { dg-final { scan-assembler-times "xsmadd" 2 } } */
+/* { dg-final { scan-assembler-times "xsmadd\|fmadd\ " 2 } } */
 /* { dg-final { scan-assembler-times "fmadds" 2 } } */
 /* { dg-final { scan-assembler-times "xvmsub" 2 } } */
-/* { dg-final { scan-assembler-times "xsmsub" 1 } } */
+/* { dg-final { scan-assembler-times "xsmsub\|fmsub\ " 1 } } */
 /* { dg-final { scan-assembler-times "fmsubs" 1 } } */
 /* { dg-final { scan-assembler-times "xvnmadd" 2 } } */
-/* { dg-final { scan-assembler-times "xsnmadd" 1 } } */
+/* { dg-final { scan-assembler-times "xsnmadd\|fnmadd " 1 } } */
 /* { dg-final { scan-assembler-times "fnmadds" 1 } } */
 /* { dg-final { scan-assembler-times "xvnmsub" 2 } } */
-/* { dg-final { scan-assembler-times "xsnmsub" 1 } } */
+/* { dg-final { scan-assembler-times "xsnmsub\|fnmsub " 1 } } */
 /* { dg-final { scan-assembler-times "fnmsubs" 1 } } */
 
 /* All functions should generate an appropriate (a * b) + c instruction

gcc/testsuite/gcc.target/powerpc/ppc-fma-2.c

@@ -3,16 +3,16 @@
 /* { dg-require-effective-target powerpc_vsx_ok } */
 /* { dg-options "-O3 -ftree-vectorize -mcpu=power7 -ffast-math -ffp-contract=off" } */
 /* { dg-final { scan-assembler-times "xvmadd" 2 } } */
-/* { dg-final { scan-assembler-times "xsmadd" 1 } } */
+/* { dg-final { scan-assembler-times "xsmadd\|fmadd\ " 1 } } */
 /* { dg-final { scan-assembler-times "fmadds" 1 } } */
 /* { dg-final { scan-assembler-times "xvmsub" 2 } } */
-/* { dg-final { scan-assembler-times "xsmsub" 1 } } */
+/* { dg-final { scan-assembler-times "xsmsub\|fmsub\ " 1 } } */
 /* { dg-final { scan-assembler-times "fmsubs" 1 } } */
 /* { dg-final { scan-assembler-times "xvnmadd" 2 } } */
-/* { dg-final { scan-assembler-times "xsnmadd" 1 } } */
+/* { dg-final { scan-assembler-times "xsnmadd\|fnmadd\ " 1 } } */
 /* { dg-final { scan-assembler-times "fnmadds" 1 } } */
 /* { dg-final { scan-assembler-times "xvnmsub" 2 } } */
-/* { dg-final { scan-assembler-times "xsnmsub" 1 } } */
+/* { dg-final { scan-assembler-times "xsnmsub\|fnmsub\ " 1 } } */
 /* { dg-final { scan-assembler-times "fnmsubs" 1 } } */
 
 /* Only the functions calling the bulitin should generate an appropriate (a *

gcc/testsuite/gcc.target/powerpc/recip-3.c

 /* { dg-do compile { target { { powerpc*-*-* } && { ! powerpc*-apple-darwin* } } } } */
 /* { dg-options "-O2 -mrecip -ffast-math -mcpu=power7" } */
 /* { dg-final { scan-assembler-times "xsrsqrtedp" 1 } } */
-/* { dg-final { scan-assembler-times "xsmsub.dp" 1 } } */
+/* { dg-final { scan-assembler-times "xsmsub.dp\|fmsub\ " 1 } } */
 /* { dg-final { scan-assembler-times "xsmuldp" 4 } } */
-/* { dg-final { scan-assembler-times "xsnmsub.dp" 2 } } */
+/* { dg-final { scan-assembler-times "xsnmsub.dp\|fnmsub\ " 2 } } */
 /* { dg-final { scan-assembler-times "frsqrtes" 1 } } */
 /* { dg-final { scan-assembler-times "fmsubs" 1 } } */
 /* { dg-final { scan-assembler-times "fmuls" 4 } } */