AVX-512. 57/n. Extend blend/cmp/brodcast insn patterns.

gcc/
	* config/i386/sse.md
	(define_insn "avx512f_blendm<mode>"): Delete.
	(define_insn "<avx512>_blendm<VI48_AVX512VL:mode>"): New.
	(define_insn "<avx512>_blendm<VI12_AVX512VL:mode>"): Ditto..
	(define_mode_attr cmp_imm_predicate): Add V8SF, V4DF, V8SI, V4DI, V4SF,
	V2DF, V4SI, V2DI, V32HI, V64QI, V16HI, V32QI, V8HI, V16QI modes.
	(define_insn
	"avx512f_cmp<mode>3<mask_scalar_merge_name><round_saeonly_name>"):
	Remove.
	(define_insn
	"<avx512>_cmp<VI48_AVX512VL:mode>3<mask_scalar_merge_name><round_saeonly_name>"):
	New.
	(define_insn
	"<avx512>_cmp<VI12_AVX512VL:mode>3<mask_scalar_merge_name><round_saeonly_name>"):
	Ditto.
	(define_insn "<mask_codefor>avx512f_vec_dup<mode><mask_name>"): Delete.
	(define_insn "<avx512>_vec_dup<V48_AVX512VL:mode><mask_name>"): New.
	(define_insn "<avx512>_vec_dup<V12_AVX512VL:mode><mask_name>"): Ditto.
	(define_insn "<mask_codefor>avx512f_vec_dup_gpr<mode><mask_name>"):
	Delete.
	(define_insn
	"<mask_codefor><avx512>_vec_dup_gpr<VI48_AVX512VL:mode><mask_name>"):
	New.
	(define_insn
	"<mask_codefor><avx512>_vec_dup_gpr<VI12_AVX512VL:mode><mask_name>"):
	Ditto.
	(define_insn·"<mask_codefor>avx512f_vec_dup_mem<mode><mask_name>"):
	Delete.
	(define_insn
	"<mask_codefor><avx512>_vec_dup_mem<VI48_AVX512VL:mode><mask_name>"):
	New.
	(define_insn
	"<mask_codefor><avx512>_vec_dup_mem<VI12_AVX512VL:mode><mask_name>"):
	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>

From-SVN: r216175

2 files changed, 135 insertions, 24 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index c7aa8f6..0a4673c 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,47 @@
+2014-10-14  Alexander Ivchenko  <alexander.ivchenko@intel.com>
+	    Maxim Kuznetsov  <maxim.kuznetsov@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
+	(define_insn "avx512f_blendm<mode>"): Delete.
+	(define_insn "<avx512>_blendm<VI48_AVX512VL:mode>"): New.
+	(define_insn "<avx512>_blendm<VI12_AVX512VL:mode>"): Ditto..
+	(define_mode_attr cmp_imm_predicate): Add V8SF, V4DF, V8SI, V4DI, V4SF,
+	V2DF, V4SI, V2DI, V32HI, V64QI, V16HI, V32QI, V8HI, V16QI modes.
+	(define_insn
+	"avx512f_cmp<mode>3<mask_scalar_merge_name><round_saeonly_name>"):
+	Remove.
+	(define_insn
+	"<avx512>_cmp<VI48_AVX512VL:mode>3<mask_scalar_merge_name><round_saeonly_name>"):
+	New.
+	(define_insn
+	"<avx512>_cmp<VI12_AVX512VL:mode>3<mask_scalar_merge_name><round_saeonly_name>"):
+	Ditto.
+	(define_insn "<mask_codefor>avx512f_vec_dup<mode><mask_name>"): Delete.
+	(define_insn "<avx512>_vec_dup<V48_AVX512VL:mode><mask_name>"): New.
+	(define_insn "<avx512>_vec_dup<V12_AVX512VL:mode><mask_name>"): Ditto.
+	(define_insn "<mask_codefor>avx512f_vec_dup_gpr<mode><mask_name>"):
+	Delete.
+	(define_insn
+	"<mask_codefor><avx512>_vec_dup_gpr<VI48_AVX512VL:mode><mask_name>"):
+	New.
+	(define_insn
+	"<mask_codefor><avx512>_vec_dup_gpr<VI12_AVX512VL:mode><mask_name>"):
+	Ditto.
+	(define_insn·"<mask_codefor>avx512f_vec_dup_mem<mode><mask_name>"):
+	Delete.
+	(define_insn
+	"<mask_codefor><avx512>_vec_dup_mem<VI48_AVX512VL:mode><mask_name>"):
+	New.
+	(define_insn
+	"<mask_codefor><avx512>_vec_dup_mem<VI12_AVX512VL:mode><mask_name>"):
+	Ditto.
+
 2014-10-14  Richard Biener  <rguenther@suse.de>
 
 	PR tree-optimization/63512
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index e7646d77..d544ed0 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -959,14 +959,26 @@
    (set_attr "memory" "none,load")
    (set_attr "mode" "<sseinsnmode>")])
 
-(define_insn "avx512f_blendm<mode>"
-  [(set (match_operand:VI48F_512 0 "register_operand" "=v")
-	(vec_merge:VI48F_512
-	  (match_operand:VI48F_512 2 "nonimmediate_operand" "vm")
-	  (match_operand:VI48F_512 1 "register_operand" "v")
+(define_insn "<avx512>_blendm<mode>"
+  [(set (match_operand:V48_AVX512VL 0 "register_operand" "=v")
+	(vec_merge:V48_AVX512VL
+	  (match_operand:V48_AVX512VL 2 "nonimmediate_operand" "vm")
+	  (match_operand:V48_AVX512VL 1 "register_operand" "v")
 	  (match_operand:<avx512fmaskmode> 3 "register_operand" "Yk")))]
   "TARGET_AVX512F"
-  "v<sseintprefix>blendm<ssemodesuffix>\t{%2, %1, %0%{%3%}|%0%{%3%}, %1, %2}"
+  "vblendm<ssemodesuffix>\t{%2, %1, %0%{%3%}|%0%{%3%}, %1, %2}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "<avx512>_blendm<mode>"
+  [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+	(vec_merge:VI12_AVX512VL
+	  (match_operand:VI12_AVX512VL 2 "nonimmediate_operand" "vm")
+	  (match_operand:VI12_AVX512VL 1 "register_operand" "v")
+	  (match_operand:<avx512fmaskmode> 3 "register_operand" "Yk")))]
+  "TARGET_AVX512BW"
+  "vpblendm<ssemodesuffix>\t{%2, %1, %0%{%3%}|%0%{%3%}, %1, %2}"
   [(set_attr "type" "ssemov")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
@@ -2472,14 +2484,21 @@
    (set_attr "mode" "<ssescalarmode>")])
 
 (define_mode_attr cmp_imm_predicate
-  [(V16SF "const_0_to_31_operand") (V8DF "const_0_to_31_operand")
-  (V16SI "const_0_to_7_operand") (V8DI "const_0_to_7_operand")])
-
-(define_insn "avx512f_cmp<mode>3<mask_scalar_merge_name><round_saeonly_name>"
+  [(V16SF "const_0_to_31_operand")  (V8DF "const_0_to_31_operand")
+   (V16SI "const_0_to_7_operand")   (V8DI "const_0_to_7_operand")
+   (V8SF "const_0_to_31_operand")   (V4DF "const_0_to_31_operand")
+   (V8SI "const_0_to_7_operand")    (V4DI "const_0_to_7_operand")
+   (V4SF "const_0_to_31_operand")   (V2DF "const_0_to_31_operand")
+   (V4SI "const_0_to_7_operand")    (V2DI "const_0_to_7_operand")
+   (V32HI "const_0_to_7_operand")   (V64QI "const_0_to_7_operand")
+   (V16HI "const_0_to_7_operand")   (V32QI "const_0_to_7_operand")
+   (V8HI "const_0_to_7_operand")    (V16QI "const_0_to_7_operand")])
+
+(define_insn "<avx512>_cmp<mode>3<mask_scalar_merge_name><round_saeonly_name>"
   [(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=Yk")
 	(unspec:<avx512fmaskmode>
-	  [(match_operand:VI48F_512 1 "register_operand" "v")
-	   (match_operand:VI48F_512 2 "<round_saeonly_nimm_predicate>" "<round_saeonly_constraint>")
+	  [(match_operand:V48_AVX512VL 1 "register_operand" "v")
+	   (match_operand:V48_AVX512VL 2 "nonimmediate_operand" "<round_saeonly_constraint>")
 	   (match_operand:SI 3 "<cmp_imm_predicate>" "n")]
 	  UNSPEC_PCMP))]
   "TARGET_AVX512F && <round_saeonly_mode512bit_condition>"
@@ -2489,6 +2508,20 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
+(define_insn "<avx512>_cmp<mode>3<mask_scalar_merge_name>"
+  [(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=Yk")
+	(unspec:<avx512fmaskmode>
+	  [(match_operand:VI12_AVX512VL 1 "register_operand" "v")
+	   (match_operand:VI12_AVX512VL 2 "nonimmediate_operand" "vm")
+	   (match_operand:SI 3 "<cmp_imm_predicate>" "n")]
+	  UNSPEC_PCMP))]
+  "TARGET_AVX512BW"
+  "vpcmp<ssemodesuffix>\t{%3, %2, %1, %0<mask_scalar_merge_operand4>|%0<mask_scalar_merge_operand4>, %1, %2, %3}"
+  [(set_attr "type" "ssecmp")
+   (set_attr "length_immediate" "1")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
 (define_insn "avx512f_ucmp<mode>3<mask_scalar_merge_name>"
   [(set (match_operand:<avx512fmaskmode> 0 "register_operand" "=Yk")
 	(unspec:<avx512fmaskmode>
@@ -16016,13 +16049,13 @@
    #"
   [(set_attr "type" "ssemov")
    (set_attr "prefix_extra" "1")
-   (set_attr "prefix" "vex")
+   (set_attr "prefix" "maybe_evex")
    (set_attr "isa" "*,avx2,noavx2")
    (set_attr "mode" "V8SF")])
 
-(define_insn "<mask_codefor>avx512f_vec_dup<mode><mask_name>"
-  [(set (match_operand:VI48F_512 0 "register_operand" "=v")
-	(vec_duplicate:VI48F_512
+(define_insn "<avx512>_vec_dup<mode><mask_name>"
+  [(set (match_operand:V48_AVX512VL 0 "register_operand" "=v")
+	(vec_duplicate:V48_AVX512VL
 	  (vec_select:<ssescalarmode>
 	    (match_operand:<ssexmmmode> 1 "nonimmediate_operand" "vm")
 	    (parallel [(const_int 0)]))))]
@@ -16032,6 +16065,18 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
+(define_insn "<avx512>_vec_dup<mode><mask_name>"
+  [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+	(vec_duplicate:VI12_AVX512VL
+	  (vec_select:<ssescalarmode>
+	    (match_operand:<ssexmmmode> 1 "nonimmediate_operand" "vm")
+	    (parallel [(const_int 0)]))))]
+  "TARGET_AVX512BW"
+  "vpbroadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
 (define_insn "<mask_codefor>avx512f_broadcast<mode><mask_name>"
   [(set (match_operand:V16FI 0 "register_operand" "=v,v")
 	(vec_duplicate:V16FI
@@ -16056,19 +16101,31 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
-(define_insn "<mask_codefor>avx512f_vec_dup_gpr<mode><mask_name>"
-  [(set (match_operand:VI48_512 0 "register_operand" "=v")
-	(vec_duplicate:VI48_512
+(define_insn "<mask_codefor><avx512>_vec_dup_gpr<mode><mask_name>"
+  [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+	(vec_duplicate:VI12_AVX512VL
 	  (match_operand:<ssescalarmode> 1 "register_operand" "r")))]
-  "TARGET_AVX512F && (<MODE>mode != V8DImode || TARGET_64BIT)"
-  "vpbroadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+  "TARGET_AVX512BW"
+  "vpbroadcast<bcstscalarsuff>\t{%k1, %0<mask_operand2>|%0<mask_operand2>, %k1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "<mask_codefor><avx512>_vec_dup_gpr<mode><mask_name>"
+  [(set (match_operand:VI48_AVX512VL 0 "register_operand" "=v")
+	(vec_duplicate:VI48_AVX512VL
+	  (match_operand:<ssescalarmode> 1 "register_operand" "r")))]
+  "TARGET_AVX512F && (<ssescalarmode>mode != DImode || TARGET_64BIT)"
+{
+  return "vpbroadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}";
+}
   [(set_attr "type" "ssemov")
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
-(define_insn "<mask_codefor>avx512f_vec_dup_mem<mode><mask_name>"
-  [(set (match_operand:VI48F_512 0 "register_operand" "=v")
-	(vec_duplicate:VI48F_512
+(define_insn "<mask_codefor><avx512>_vec_dup_mem<mode><mask_name>"
+  [(set (match_operand:V48_AVX512VL 0 "register_operand" "=v")
+	(vec_duplicate:V48_AVX512VL
 	  (match_operand:<ssescalarmode> 1 "nonimmediate_operand" "vm")))]
   "TARGET_AVX512F"
   "v<sseintprefix>broadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
@@ -16076,6 +16133,16 @@
    (set_attr "prefix" "evex")
    (set_attr "mode" "<sseinsnmode>")])
 
+(define_insn "<mask_codefor><avx512>_vec_dup_mem<mode><mask_name>"
+  [(set (match_operand:VI12_AVX512VL 0 "register_operand" "=v")
+	(vec_duplicate:VI12_AVX512VL
+	  (match_operand:<ssescalarmode> 1 "nonimmediate_operand" "vm")))]
+  "TARGET_AVX512BW"
+  "vpbroadcast<bcstscalarsuff>\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
+  [(set_attr "type" "ssemov")
+   (set_attr "prefix" "evex")
+   (set_attr "mode" "<sseinsnmode>")])
+
 (define_insn "avx2_vbroadcasti128_<mode>"
   [(set (match_operand:VI_256 0 "register_operand" "=x")
 	(vec_concat:VI_256