aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorAlexander Ivchenko <alexander.ivchenko@intel.com>2013-10-11 14:00:11 +0000
committerKirill Yukhin <kyukhin@gcc.gnu.org>2013-10-11 14:00:11 +0000
commit558d9f795b5c7f560bef4539e19c4f2e9e99533b (patch)
tree4d16e072920798617e00eae25a2088045f2e9a3b
parente8d0820644097f0fc200364f799ff1c2766bd1ac (diff)
downloadgcc-558d9f795b5c7f560bef4539e19c4f2e9e99533b.zip
gcc-558d9f795b5c7f560bef4539e19c4f2e9e99533b.tar.gz
gcc-558d9f795b5c7f560bef4539e19c4f2e9e99533b.tar.bz2
i386.c (ix86_rtx_costs): Enable fma for TARGET_AVX512F.
* config/i386/i386.c (ix86_rtx_costs): Enable fma for TARGET_AVX512F. * config/i386/sse.md (FMAMODEM): Changed modes and conditions. (FMAMODE): Ditto. (fma<mode>4): Removed condition. (fms<mode>4): Ditto. (fnma<mode>4): Ditto. (fnms<mode>4): Ditto. (fma4i_fmadd_<mode>): Ditto. (*fma_fmadd_<mode>): Ditto. (*fma_fmsub_<mode>): Ditto. (*fma_fnmadd_<mode>): Ditto. (*fma_fnmsub_<mode>): Ditto. (fmaddsub_<mode>): Allow for TARGET_AVX512F. (*fma_fmaddsub_<mode>): Ditto. (*fma_fmsubadd_<mode>): Ditto. (*fmai_fmadd_<mode>): Ditto. (*fmai_fmsub_<mode>): Ditto. (*fmai_fnmadd_<mode>): Ditto. (*fmai_fnmsub_<mode>): Ditto. Co-Authored-By: Andrey Turetskiy <andrey.turetskiy@intel.com> Co-Authored-By: Anna Tikhonova <anna.tikhonova@intel.com> Co-Authored-By: Ilya Tocar <ilya.tocar@intel.com> Co-Authored-By: Ilya Verbin <ilya.verbin@intel.com> Co-Authored-By: Kirill Yukhin <kirill.yukhin@intel.com> Co-Authored-By: Maxim Kuznetsov <maxim.kuznetsov@intel.com> Co-Authored-By: Michael Zolotukhin <michael.v.zolotukhin@intel.com> Co-Authored-By: Sergey Lega <sergey.s.lega@intel.com> From-SVN: r203439
Diffstat
-rw-r--r--gcc/ChangeLog30
-rw-r--r--gcc/config/i386/i386.c2
-rw-r--r--gcc/config/i386/sse.md64
3 files changed, 73 insertions, 23 deletions
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 7a694c0..0fb3d0b 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -8,6 +8,36 @@
Kirill Yukhin <kirill.yukhin@intel.com>
Michael Zolotukhin <michael.v.zolotukhin@intel.com>
+ * config/i386/i386.c (ix86_rtx_costs): Enable fma for TARGET_AVX512F.
+ * config/i386/sse.md (FMAMODEM): Changed modes and conditions.
+ (FMAMODE): Ditto.
+ (fma<mode>4): Removed condition.
+ (fms<mode>4): Ditto.
+ (fnma<mode>4): Ditto.
+ (fnms<mode>4): Ditto.
+ (fma4i_fmadd_<mode>): Ditto.
+ (*fma_fmadd_<mode>): Ditto.
+ (*fma_fmsub_<mode>): Ditto.
+ (*fma_fnmadd_<mode>): Ditto.
+ (*fma_fnmsub_<mode>): Ditto.
+ (fmaddsub_<mode>): Allow for TARGET_AVX512F.
+ (*fma_fmaddsub_<mode>): Ditto.
+ (*fma_fmsubadd_<mode>): Ditto.
+ (*fmai_fmadd_<mode>): Ditto.
+ (*fmai_fmsub_<mode>): Ditto.
+ (*fmai_fnmadd_<mode>): Ditto.
+ (*fmai_fnmsub_<mode>): Ditto.
+
+2013-10-11 Alexander Ivchenko <alexander.ivchenko@intel.com>
+ Maxim Kuznetsov <maxim.kuznetsov@intel.com>
+ Sergey Lega <sergey.s.lega@intel.com>
+ Anna Tikhonova <anna.tikhonova@intel.com>
+ Ilya Tocar <ilya.tocar@intel.com>
+ Andrey Turetskiy <andrey.turetskiy@intel.com>
+ Ilya Verbin <ilya.verbin@intel.com>
+ Kirill Yukhin <kirill.yukhin@intel.com>
+ Michael Zolotukhin <michael.v.zolotukhin@intel.com>
+
* config/i386/sse.md (VI248_AVX2_8_AVX512F): New.
(VI124_256): Changed to ...
(VI124_256_48_512): This.
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 168a2ac..37c1bec 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -34811,7 +34811,7 @@ 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..0b81521 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -2254,9 +2254,22 @@
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;; 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.
+;; TODO: In theory AVX512F does not automatically imply FMA, and without FMA
+;; one must force the EVEX encoding of the fma insns. Ideally we'd improve
+;; GAS to allow proper prefix selection. However, for the moment all hardware
+;; that supports AVX512F also supports FMA so we can ignore this for now.
+(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 +2277,7 @@
(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 +2285,7 @@
(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 +2293,7 @@
(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 +2301,17 @@
(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 +2319,7 @@
(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 +2327,7 @@
(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 +2338,14 @@
(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 +2356,14 @@
(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 +2382,7 @@
(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 +2411,7 @@
(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 +2420,7 @@
(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 +2439,7 @@
(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 +2473,7 @@
(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 +2490,7 @@
(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 +2507,7 @@
(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 +2525,7 @@
(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}"
generated by cgit v1.1 at 2025-08-17 01:51:16 +0000