This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH i386 3/8] [AVX512] [11/n] Add AVX-512 patterns: FMA.


Hello,

> This patch is still far too large.
>
> I think you should split it up based on every single mode iterator that
> you need to add or change.

Here's 11th subpatch. It introduces AVX-512 FMA instructions.

Is it Ok?

Testing:
  1. Bootstrap pass.
  2. make check shows no regressions.
  3. Spec 2000 & 2006 build show no regressions both with and without -mavx512f option.
  4. Spec 2000 & 2006 run shows no stability regressions without -mavx512f option.

--
Thanks, K

PS. If it is Ok - I am going to strip out ChangeLog lines from big patch.

---
 gcc/config/i386/i386.c |  2 +-
 gcc/config/i386/sse.md | 60 ++++++++++++++++++++++++++++++++------------------
 2 files changed, 39 insertions(+), 23 deletions(-)

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index f10113f..5908383 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -34785,7 +34785,7 @@ ix86_rtx_costs (rtx x, int code_i, int outer_code_i, int opno, int *total,
 	rtx sub;
 
         gcc_assert (FLOAT_MODE_P (mode));
-        gcc_assert (TARGET_FMA || TARGET_FMA4);
+        gcc_assert (TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F);
 
         /* ??? SSE scalar/vector cost should be used here.  */
         /* ??? Bald assumption that fma has the same cost as fmul.  */
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index a380690..6adcdd3 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2254,9 +2254,18 @@
 ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
 
 ;; The standard names for scalar FMA are only available with SSE math enabled.
-(define_mode_iterator FMAMODEM [(SF "TARGET_SSE_MATH")
-				(DF "TARGET_SSE_MATH")
-				V4SF V2DF V8SF V4DF])
+;; CPUID bit AVX512F enables evex encoded scalar and 512-bit fma.  It doesn't
+;; care about FMA bit, so we enable fma for TARGET_AVX512F even when TARGET_FMA
+;; and TARGET_FMA4 are both false.
+(define_mode_iterator FMAMODEM
+  [(SF "TARGET_SSE_MATH && (TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F)")
+   (DF "TARGET_SSE_MATH && (TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F)")
+   (V4SF "TARGET_FMA || TARGET_FMA4")
+   (V2DF "TARGET_FMA || TARGET_FMA4")
+   (V8SF "TARGET_FMA || TARGET_FMA4")
+   (V4DF "TARGET_FMA || TARGET_FMA4")
+   (V16SF "TARGET_AVX512F")
+   (V8DF "TARGET_AVX512F")])
 
 (define_expand "fma<mode>4"
   [(set (match_operand:FMAMODEM 0 "register_operand")
@@ -2264,7 +2273,7 @@
 	  (match_operand:FMAMODEM 1 "nonimmediate_operand")
 	  (match_operand:FMAMODEM 2 "nonimmediate_operand")
 	  (match_operand:FMAMODEM 3 "nonimmediate_operand")))]
-  "TARGET_FMA || TARGET_FMA4")
+  "")
 
 (define_expand "fms<mode>4"
   [(set (match_operand:FMAMODEM 0 "register_operand")
@@ -2272,7 +2281,7 @@
 	  (match_operand:FMAMODEM 1 "nonimmediate_operand")
 	  (match_operand:FMAMODEM 2 "nonimmediate_operand")
 	  (neg:FMAMODEM (match_operand:FMAMODEM 3 "nonimmediate_operand"))))]
-  "TARGET_FMA || TARGET_FMA4")
+  "")
 
 (define_expand "fnma<mode>4"
   [(set (match_operand:FMAMODEM 0 "register_operand")
@@ -2280,7 +2289,7 @@
 	  (neg:FMAMODEM (match_operand:FMAMODEM 1 "nonimmediate_operand"))
 	  (match_operand:FMAMODEM 2 "nonimmediate_operand")
 	  (match_operand:FMAMODEM 3 "nonimmediate_operand")))]
-  "TARGET_FMA || TARGET_FMA4")
+  "")
 
 (define_expand "fnms<mode>4"
   [(set (match_operand:FMAMODEM 0 "register_operand")
@@ -2288,10 +2297,17 @@
 	  (neg:FMAMODEM (match_operand:FMAMODEM 1 "nonimmediate_operand"))
 	  (match_operand:FMAMODEM 2 "nonimmediate_operand")
 	  (neg:FMAMODEM (match_operand:FMAMODEM 3 "nonimmediate_operand"))))]
-  "TARGET_FMA || TARGET_FMA4")
+  "")
 
 ;; The builtins for intrinsics are not constrained by SSE math enabled.
-(define_mode_iterator FMAMODE [SF DF V4SF V2DF V8SF V4DF])
+(define_mode_iterator FMAMODE [(SF "TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F")
+			       (DF "TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F")
+			       (V4SF "TARGET_FMA || TARGET_FMA4")
+			       (V2DF "TARGET_FMA || TARGET_FMA4")
+			       (V8SF "TARGET_FMA || TARGET_FMA4")
+			       (V4DF "TARGET_FMA || TARGET_FMA4")
+			       (V16SF "TARGET_AVX512F")
+			       (V8DF "TARGET_AVX512F")])
 
 (define_expand "fma4i_fmadd_<mode>"
   [(set (match_operand:FMAMODE 0 "register_operand")
@@ -2299,7 +2315,7 @@
 	  (match_operand:FMAMODE 1 "nonimmediate_operand")
 	  (match_operand:FMAMODE 2 "nonimmediate_operand")
 	  (match_operand:FMAMODE 3 "nonimmediate_operand")))]
-  "TARGET_FMA || TARGET_FMA4")
+  "")
 
 (define_insn "*fma_fmadd_<mode>"
   [(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
@@ -2307,7 +2323,7 @@
 	  (match_operand:FMAMODE 1 "nonimmediate_operand" "%0, 0, v, x,x")
 	  (match_operand:FMAMODE 2 "nonimmediate_operand" "vm, v,vm, x,m")
 	  (match_operand:FMAMODE 3 "nonimmediate_operand" " v,vm, 0,xm,x")))]
-  "TARGET_FMA || TARGET_FMA4"
+  ""
   "@
    vfmadd132<ssemodesuffix>\t{%2, %3, %0|%0, %3, %2}
    vfmadd213<ssemodesuffix>\t{%3, %2, %0|%0, %2, %3}
@@ -2318,14 +2334,14 @@
    (set_attr "type" "ssemuladd")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "*fma_fmsub_<mode>"
+(define_insn "fma_fmsub_<mode>"
   [(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
 	(fma:FMAMODE
 	  (match_operand:FMAMODE   1 "nonimmediate_operand" "%0, 0, v, x,x")
 	  (match_operand:FMAMODE   2 "nonimmediate_operand" "vm, v,vm, x,m")
 	  (neg:FMAMODE
 	    (match_operand:FMAMODE 3 "nonimmediate_operand" " v,vm, 0,xm,x"))))]
-  "TARGET_FMA || TARGET_FMA4"
+  ""
   "@
    vfmsub132<ssemodesuffix>\t{%2, %3, %0|%0, %3, %2}
    vfmsub213<ssemodesuffix>\t{%3, %2, %0|%0, %2, %3}
@@ -2336,14 +2352,14 @@
    (set_attr "type" "ssemuladd")
    (set_attr "mode" "<MODE>")])
 
-(define_insn "*fma_fnmadd_<mode>"
+(define_insn "fma_fnmadd_<mode>"
   [(set (match_operand:FMAMODE 0 "register_operand" "=v,v,v,x,x")
 	(fma:FMAMODE
 	  (neg:FMAMODE
 	    (match_operand:FMAMODE 1 "nonimmediate_operand" "%0, 0, v, x,x"))
 	  (match_operand:FMAMODE   2 "nonimmediate_operand" "vm, v,vm, x,m")
 	  (match_operand:FMAMODE   3 "nonimmediate_operand" " v,vm, 0,xm,x")))]
-  "TARGET_FMA || TARGET_FMA4"
+  ""
   "@
    vfnmadd132<ssemodesuffix>\t{%2, %3, %0|%0, %3, %2}
    vfnmadd213<ssemodesuffix>\t{%3, %2, %0|%0, %2, %3}
@@ -2362,7 +2378,7 @@
 	  (match_operand:FMAMODE   2 "nonimmediate_operand" "vm, v,vm, x,m")
 	  (neg:FMAMODE
 	    (match_operand:FMAMODE 3 "nonimmediate_operand" " v,vm, 0,xm,x"))))]
-  "TARGET_FMA || TARGET_FMA4"
+  ""
   "@
    vfnmsub132<ssemodesuffix>\t{%2, %3, %0|%0, %3, %2}
    vfnmsub213<ssemodesuffix>\t{%3, %2, %0|%0, %2, %3}
@@ -2391,7 +2407,7 @@
 	   (match_operand:VF 2 "nonimmediate_operand")
 	   (match_operand:VF 3 "nonimmediate_operand")]
 	  UNSPEC_FMADDSUB))]
-  "TARGET_FMA || TARGET_FMA4")
+  "TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F")
 
 (define_insn "*fma_fmaddsub_<mode>"
   [(set (match_operand:VF 0 "register_operand" "=v,v,v,x,x")
@@ -2400,7 +2416,7 @@
 	   (match_operand:VF 2 "nonimmediate_operand" "vm, v,vm, x,m")
 	   (match_operand:VF 3 "nonimmediate_operand" " v,vm, 0,xm,x")]
 	  UNSPEC_FMADDSUB))]
-  "TARGET_FMA || TARGET_FMA4"
+  "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F)"
   "@
    vfmaddsub132<ssemodesuffix>\t{%2, %3, %0|%0, %3, %2}
    vfmaddsub213<ssemodesuffix>\t{%3, %2, %0|%0, %2, %3}
@@ -2419,7 +2435,7 @@
 	   (neg:VF
 	     (match_operand:VF 3 "nonimmediate_operand" " v,vm, 0,xm,x"))]
 	  UNSPEC_FMADDSUB))]
-  "TARGET_FMA || TARGET_FMA4"
+  "(TARGET_FMA || TARGET_FMA4 || TARGET_AVX512F)"
   "@
    vfmsubadd132<ssemodesuffix>\t{%2, %3, %0|%0, %3, %2}
    vfmsubadd213<ssemodesuffix>\t{%3, %2, %0|%0, %2, %3}
@@ -2453,7 +2469,7 @@
 	    (match_operand:VF_128 3 "nonimmediate_operand" " v,vm"))
 	  (match_dup 1)
 	  (const_int 1)))]
-  "TARGET_FMA"
+  "TARGET_FMA || TARGET_AVX512F"
   "@
    vfmadd132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
    vfmadd213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
@@ -2470,7 +2486,7 @@
 	      (match_operand:VF_128 3 "nonimmediate_operand" " v,vm")))
 	  (match_dup 1)
 	  (const_int 1)))]
-  "TARGET_FMA"
+  "TARGET_FMA || TARGET_AVX512F"
   "@
    vfmsub132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
    vfmsub213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
@@ -2487,7 +2503,7 @@
 	    (match_operand:VF_128   3 "nonimmediate_operand" " v,vm"))
 	  (match_dup 1)
 	  (const_int 1)))]
-  "TARGET_FMA"
+  "TARGET_FMA || TARGET_AVX512F"
   "@
    vfnmadd132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
    vfnmadd213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
@@ -2505,7 +2521,7 @@
 	      (match_operand:VF_128 3 "nonimmediate_operand" " v,vm")))
 	  (match_dup 1)
 	  (const_int 1)))]
-  "TARGET_FMA"
+  "TARGET_FMA || TARGET_AVX512F"
   "@
    vfnmsub132<ssescalarmodesuffix>\t{%2, %3, %0|%0, %<iptr>3, %<iptr>2}
    vfnmsub213<ssescalarmodesuffix>\t{%3, %2, %0|%0, %<iptr>2, %<iptr>3}"
-- 
1.7.11.7


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]