[PATCH i386 3/8] [AVX512] [19/n] Add AVX-512 patterns: Extracts and converts.
Kirill Yukhin
kirill.yukhin@gmail.com
Tue Oct 22 14:22:00 GMT 2013
Hello,
On 20 Oct 11:55, Uros Bizjak wrote:
> Please also add back expanders with operand fixups and insn
> constraints, as is the case with other commutative operators. They are
> needed to hoist operand loads out of the loops (reload and later
> passes won't hoist memory loads out of the loops when fixing up
> operands).
Whoops. I didn't know how git diff works for set of patches.
Updated patch in the bottom.
> The patch is OK with this change, but please wait for rths final approval.
Richard, are you ok?
Bootstrap pass.
--
Thanks, K
---
gcc/config/i386/i386.md | 5 +
gcc/config/i386/predicates.md | 40 ++
gcc/config/i386/sse.md | 932 +++++++++++++++++++++++++++++++++++++++++-
3 files changed, 971 insertions(+), 6 deletions(-)
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 10ca6cb..e7e9f2d 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -831,6 +831,11 @@
(define_code_attr s [(sign_extend "s") (zero_extend "u")])
(define_code_attr u_bool [(sign_extend "false") (zero_extend "true")])
+;; Used in signed and unsigned truncations.
+(define_code_iterator any_truncate [ss_truncate truncate us_truncate])
+;; Instruction suffix for truncations.
+(define_code_attr trunsuffix [(ss_truncate "s") (truncate "") (us_truncate "us")])
+
;; Used in signed and unsigned fix.
(define_code_iterator any_fix [fix unsigned_fix])
(define_code_attr fixsuffix [(fix "") (unsigned_fix "u")])
diff --git a/gcc/config/i386/predicates.md b/gcc/config/i386/predicates.md
index 06b2914..999d8ab 100644
--- a/gcc/config/i386/predicates.md
+++ b/gcc/config/i386/predicates.md
@@ -752,6 +752,11 @@
(and (match_code "const_int")
(match_test "IN_RANGE (INTVAL (op), 6, 7)")))
+;; Match 8 to 9.
+(define_predicate "const_8_to_9_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 8, 9)")))
+
;; Match 8 to 11.
(define_predicate "const_8_to_11_operand"
(and (match_code "const_int")
@@ -762,16 +767,51 @@
(and (match_code "const_int")
(match_test "IN_RANGE (INTVAL (op), 8, 15)")))
+;; Match 10 to 11.
+(define_predicate "const_10_to_11_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 10, 11)")))
+
+;; Match 12 to 13.
+(define_predicate "const_12_to_13_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 12, 13)")))
+
;; Match 12 to 15.
(define_predicate "const_12_to_15_operand"
(and (match_code "const_int")
(match_test "IN_RANGE (INTVAL (op), 12, 15)")))
+;; Match 14 to 15.
+(define_predicate "const_14_to_15_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 14, 15)")))
+
+;; Match 16 to 19.
+(define_predicate "const_16_to_19_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 16, 19)")))
+
;; Match 16 to 31.
(define_predicate "const_16_to_31_operand"
(and (match_code "const_int")
(match_test "IN_RANGE (INTVAL (op), 16, 31)")))
+;; Match 20 to 23.
+(define_predicate "const_20_to_23_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 20, 23)")))
+
+;; Match 24 to 27.
+(define_predicate "const_24_to_27_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 24, 27)")))
+
+;; Match 28 to 31.
+(define_predicate "const_28_to_31_operand"
+ (and (match_code "const_int")
+ (match_test "IN_RANGE (INTVAL (op), 28, 31)")))
+
;; True if this is a constant appropriate for an increment or decrement.
(define_predicate "incdec_operand"
(match_code "const_int")
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 623e919..c429855 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -87,6 +87,7 @@
;; For AVX512F support
UNSPEC_VPERMI2
UNSPEC_VPERMT2
+ UNSPEC_UNSIGNED_FIX_NOTRUNC
UNSPEC_UNSIGNED_PCMP
UNSPEC_TESTM
UNSPEC_TESTNM
@@ -2994,6 +2995,34 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "DI")])
+(define_insn "cvtusi2<ssescalarmodesuffix>32"
+ [(set (match_operand:VF_128 0 "register_operand" "=v")
+ (vec_merge:VF_128
+ (vec_duplicate:VF_128
+ (unsigned_float:<ssescalarmode>
+ (match_operand:SI 2 "nonimmediate_operand" "rm")))
+ (match_operand:VF_128 1 "register_operand" "v")
+ (const_int 1)))]
+ "TARGET_AVX512F"
+ "vcvtusi2<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<ssescalarmode>")])
+
+(define_insn "cvtusi2<ssescalarmodesuffix>64"
+ [(set (match_operand:VF_128 0 "register_operand" "=v")
+ (vec_merge:VF_128
+ (vec_duplicate:VF_128
+ (unsigned_float:<ssescalarmode>
+ (match_operand:DI 2 "nonimmediate_operand" "rm")))
+ (match_operand:VF_128 1 "register_operand" "v")
+ (const_int 1)))]
+ "TARGET_AVX512F && TARGET_64BIT"
+ "vcvtusi2<ssescalarmodesuffix>\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<ssescalarmode>")])
+
(define_insn "float<sseintvecmodelower><mode>2"
[(set (match_operand:VF1 0 "register_operand" "=v")
(float:VF1
@@ -3004,6 +3033,16 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<sseinsnmode>")])
+(define_insn "ufloatv16siv16sf2"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (unsigned_float:V16SF
+ (match_operand:V16SI 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vcvtudq2ps\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
(define_expand "floatuns<sseintvecmodelower><mode>2"
[(match_operand:VF1 0 "register_operand")
(match_operand:<sseintvecmode> 1 "register_operand")]
@@ -3034,6 +3073,28 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<sseinsnmode>")])
+(define_insn "avx512f_fix_notruncv16sfv16si"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (unspec:V16SI
+ [(match_operand:V16SF 1 "nonimmediate_operand" "vm")]
+ UNSPEC_FIX_NOTRUNC))]
+ "TARGET_AVX512F"
+ "vcvtps2dq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
+(define_insn "avx512f_ufix_notruncv16sfv16si"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (unspec:V16SI
+ [(match_operand:V16SF 1 "nonimmediate_operand" "vm")]
+ UNSPEC_UNSIGNED_FIX_NOTRUNC))]
+ "TARGET_AVX512F"
+ "vcvtps2udq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "<fixsuffix>fix_truncv16sfv16si2"
[(set (match_operand:V16SI 0 "register_operand" "=v")
(any_fix:V16SI
@@ -3169,6 +3230,106 @@
(set_attr "prefix" "orig,orig,maybe_evex")
(set_attr "mode" "DF")])
+(define_insn "avx512f_vcvtss2usi"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (unspec:SI
+ [(vec_select:SF
+ (match_operand:V4SF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))]
+ UNSPEC_UNSIGNED_FIX_NOTRUNC))]
+ "TARGET_AVX512F"
+ "vcvtss2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "SI")])
+
+(define_insn "avx512f_vcvtss2usiq"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (unspec:DI
+ [(vec_select:SF
+ (match_operand:V4SF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))]
+ UNSPEC_UNSIGNED_FIX_NOTRUNC))]
+ "TARGET_AVX512F && TARGET_64BIT"
+ "vcvtss2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "DI")])
+
+(define_insn "avx512f_vcvttss2usi"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (unsigned_fix:SI
+ (vec_select:SF
+ (match_operand:V4SF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))))]
+ "TARGET_AVX512F"
+ "vcvttss2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "SI")])
+
+(define_insn "avx512f_vcvttss2usiq"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (unsigned_fix:DI
+ (vec_select:SF
+ (match_operand:V4SF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))))]
+ "TARGET_AVX512F && TARGET_64BIT"
+ "vcvttss2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "DI")])
+
+(define_insn "avx512f_vcvtsd2usi"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (unspec:SI
+ [(vec_select:DF
+ (match_operand:V2DF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))]
+ UNSPEC_UNSIGNED_FIX_NOTRUNC))]
+ "TARGET_AVX512F"
+ "vcvtsd2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "SI")])
+
+(define_insn "avx512f_vcvtsd2usiq"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (unspec:DI
+ [(vec_select:DF
+ (match_operand:V2DF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))]
+ UNSPEC_UNSIGNED_FIX_NOTRUNC))]
+ "TARGET_AVX512F && TARGET_64BIT"
+ "vcvtsd2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "DI")])
+
+(define_insn "avx512f_vcvttsd2usi"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (unsigned_fix:SI
+ (vec_select:DF
+ (match_operand:V2DF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))))]
+ "TARGET_AVX512F"
+ "vcvttsd2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "SI")])
+
+(define_insn "avx512f_vcvttsd2usiq"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (unsigned_fix:DI
+ (vec_select:DF
+ (match_operand:V2DF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0)]))))]
+ "TARGET_AVX512F && TARGET_64BIT"
+ "vcvttsd2usi\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sseicvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "DI")])
+
(define_insn "sse2_cvtsd2si"
[(set (match_operand:SI 0 "register_operand" "=r,r")
(unspec:SI
@@ -3278,6 +3439,30 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "<MODE>")])
+(define_insn "ufloatv8siv8df"
+ [(set (match_operand:V8DF 0 "register_operand" "=v")
+ (unsigned_float:V8DF (match_operand:V8SI 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vcvtudq2pd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8DF")])
+
+(define_insn "avx512f_cvtdq2pd512_2"
+ [(set (match_operand:V8DF 0 "register_operand" "=v")
+ (float:V8DF
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_AVX"
+ "vcvtdq2pd\t{%t1, %0|%0, %t1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8DF")])
+
(define_insn "avx_cvtdq2pd256_2"
[(set (match_operand:V4DF 0 "register_operand" "=x")
(float:V4DF
@@ -3303,6 +3488,16 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "V2DF")])
+(define_insn "avx512f_cvtpd2dq512"
+ [(set (match_operand:V8SI 0 "register_operand" "=v")
+ (unspec:V8SI [(match_operand:V8DF 1 "nonimmediate_operand" "vm")]
+ UNSPEC_FIX_NOTRUNC))]
+ "TARGET_AVX512F"
+ "vcvtpd2dq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "OI")])
+
(define_insn "avx_cvtpd2dq256"
[(set (match_operand:V4SI 0 "register_operand" "=x")
(unspec:V4SI [(match_operand:V4DF 1 "nonimmediate_operand" "xm")]
@@ -3366,6 +3561,17 @@
(set_attr "athlon_decode" "vector")
(set_attr "bdver1_decode" "double")])
+(define_insn "avx512f_ufix_notruncv8dfv8si"
+ [(set (match_operand:V8SI 0 "register_operand" "=v")
+ (unspec:V8SI
+ [(match_operand:V8DF 1 "nonimmediate_operand" "vm")]
+ UNSPEC_UNSIGNED_FIX_NOTRUNC))]
+ "TARGET_AVX512F"
+ "vcvtpd2udq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "OI")])
+
(define_insn "<fixsuffix>fix_truncv8dfv8si2"
[(set (match_operand:V8SI 0 "register_operand" "=v")
(any_fix:V8SI (match_operand:V8DF 1 "nonimmediate_operand" "vm")))]
@@ -3476,6 +3682,16 @@
(set_attr "prefix" "orig,orig,vex")
(set_attr "mode" "DF")])
+(define_insn "avx512f_cvtpd2ps512"
+ [(set (match_operand:V8SF 0 "register_operand" "=v")
+ (float_truncate:V8SF
+ (match_operand:V8DF 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vcvtpd2ps\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8SF")])
+
(define_insn "avx_cvtpd2ps256"
[(set (match_operand:V4SF 0 "register_operand" "=x")
(float_truncate:V4SF
@@ -3544,6 +3760,21 @@
(set_attr "prefix" "vex")
(set_attr "mode" "V4DF")])
+(define_insn "vec_unpacks_lo_v16sf"
+ [(set (match_operand:V8DF 0 "register_operand" "=v")
+ (float_extend:V8DF
+ (vec_select:V8SF
+ (match_operand:V16SF 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_AVX512F"
+ "vcvtps2pd\t{%t1, %0|%0, %t1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8DF")])
+
(define_insn "sse2_cvtps2pd"
[(set (match_operand:V2DF 0 "register_operand" "=x")
(float_extend:V2DF
@@ -3588,6 +3819,20 @@
"TARGET_AVX"
"operands[2] = gen_reg_rtx (V4SFmode);")
+(define_expand "vec_unpacks_hi_v16sf"
+ [(set (match_dup 2)
+ (vec_select:V8SF
+ (match_operand:V16SF 1 "nonimmediate_operand")
+ (parallel [(const_int 8) (const_int 9)
+ (const_int 10) (const_int 11)
+ (const_int 12) (const_int 13)
+ (const_int 14) (const_int 15)])))
+ (set (match_operand:V8DF 0 "register_operand")
+ (float_extend:V8DF
+ (match_dup 2)))]
+"TARGET_AVX512F"
+"operands[2] = gen_reg_rtx (V8SFmode);")
+
(define_expand "vec_unpacks_lo_v4sf"
[(set (match_operand:V2DF 0 "register_operand")
(float_extend:V2DF
@@ -3704,6 +3949,31 @@
(const_int 2) (const_int 3)]))))]
"TARGET_AVX")
+(define_expand "vec_unpacks_float_hi_v16si"
+ [(set (match_dup 2)
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand")
+ (parallel [(const_int 8) (const_int 9)
+ (const_int 10) (const_int 11)
+ (const_int 12) (const_int 13)
+ (const_int 14) (const_int 15)])))
+ (set (match_operand:V8DF 0 "register_operand")
+ (float:V8DF
+ (match_dup 2)))]
+ "TARGET_AVX512F"
+ "operands[2] = gen_reg_rtx (V8SImode);")
+
+(define_expand "vec_unpacks_float_lo_v16si"
+ [(set (match_operand:V8DF 0 "register_operand")
+ (float:V8DF
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand")
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_AVX512F")
+
(define_expand "vec_unpacku_float_hi_v4si"
[(set (match_dup 5)
(vec_select:V4SI
@@ -4108,6 +4378,26 @@
(set_attr "prefix" "orig,vex,orig,vex,maybe_vex")
(set_attr "mode" "V4SF,V4SF,V2SF,V2SF,V2SF")])
+(define_insn "avx512f_unpckhps512"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (vec_select:V16SF
+ (vec_concat:V32SF
+ (match_operand:V16SF 1 "register_operand" "v")
+ (match_operand:V16SF 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 2) (const_int 18)
+ (const_int 3) (const_int 19)
+ (const_int 6) (const_int 22)
+ (const_int 7) (const_int 23)
+ (const_int 10) (const_int 26)
+ (const_int 11) (const_int 27)
+ (const_int 14) (const_int 30)
+ (const_int 15) (const_int 31)])))]
+ "TARGET_AVX512F"
+ "vunpckhps\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
;; Recall that the 256-bit unpck insns only shuffle within their lanes.
(define_insn "avx_unpckhps256"
[(set (match_operand:V8SF 0 "register_operand" "=x")
@@ -4176,6 +4466,26 @@
(set_attr "prefix" "orig,vex")
(set_attr "mode" "V4SF")])
+(define_insn "avx512f_unpcklps512"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (vec_select:V16SF
+ (vec_concat:V32SF
+ (match_operand:V16SF 1 "register_operand" "v")
+ (match_operand:V16SF 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 0) (const_int 16)
+ (const_int 1) (const_int 17)
+ (const_int 4) (const_int 20)
+ (const_int 5) (const_int 21)
+ (const_int 8) (const_int 24)
+ (const_int 9) (const_int 25)
+ (const_int 12) (const_int 28)
+ (const_int 13) (const_int 29)])))]
+ "TARGET_AVX512F"
+ "vunpcklps\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
;; Recall that the 256-bit unpck insns only shuffle within their lanes.
(define_insn "avx_unpcklps256"
[(set (match_operand:V8SF 0 "register_operand" "=x")
@@ -4279,6 +4589,26 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "V4SF")])
+(define_insn "avx512f_movshdup512"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (vec_select:V16SF
+ (vec_concat:V32SF
+ (match_operand:V16SF 1 "nonimmediate_operand" "vm")
+ (match_dup 1))
+ (parallel [(const_int 1) (const_int 1)
+ (const_int 3) (const_int 3)
+ (const_int 5) (const_int 5)
+ (const_int 7) (const_int 7)
+ (const_int 9) (const_int 9)
+ (const_int 11) (const_int 11)
+ (const_int 13) (const_int 13)
+ (const_int 15) (const_int 15)])))]
+ "TARGET_AVX512F"
+ "vmovshdup\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sse")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
(define_insn "avx_movsldup256"
[(set (match_operand:V8SF 0 "register_operand" "=x")
(vec_select:V8SF
@@ -4312,6 +4642,26 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "V4SF")])
+(define_insn "avx512f_movsldup512"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (vec_select:V16SF
+ (vec_concat:V32SF
+ (match_operand:V16SF 1 "nonimmediate_operand" "vm")
+ (match_dup 1))
+ (parallel [(const_int 0) (const_int 0)
+ (const_int 2) (const_int 2)
+ (const_int 4) (const_int 4)
+ (const_int 6) (const_int 6)
+ (const_int 8) (const_int 8)
+ (const_int 10) (const_int 10)
+ (const_int 12) (const_int 12)
+ (const_int 14) (const_int 14)])))]
+ "TARGET_AVX512F"
+ "vmovsldup\t{%1, %0|%0, %1}"
+ [(set_attr "type" "sse")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
(define_expand "avx_shufps256"
[(match_operand:V8SF 0 "register_operand")
(match_operand:V8SF 1 "register_operand")
@@ -5046,6 +5396,50 @@
(set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
+(define_insn_and_split "vec_extract_lo_v32hi"
+ [(set (match_operand:V16HI 0 "nonimmediate_operand" "=v,m")
+ (vec_select:V16HI
+ (match_operand:V32HI 1 "nonimmediate_operand" "vm,v")
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)
+ (const_int 8) (const_int 9)
+ (const_int 10) (const_int 11)
+ (const_int 12) (const_int 13)
+ (const_int 14) (const_int 15)])))]
+ "TARGET_AVX512F && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0) (match_dup 1))]
+{
+ if (REG_P (operands[1]))
+ operands[1] = gen_rtx_REG (V16HImode, REGNO (operands[1]));
+ else
+ operands[1] = adjust_address (operands[1], V16HImode, 0);
+})
+
+(define_insn "vec_extract_hi_v32hi"
+ [(set (match_operand:V16HI 0 "nonimmediate_operand" "=v,m")
+ (vec_select:V16HI
+ (match_operand:V32HI 1 "nonimmediate_operand" "v,v")
+ (parallel [(const_int 16) (const_int 17)
+ (const_int 18) (const_int 19)
+ (const_int 20) (const_int 21)
+ (const_int 22) (const_int 23)
+ (const_int 24) (const_int 25)
+ (const_int 26) (const_int 27)
+ (const_int 28) (const_int 29)
+ (const_int 30) (const_int 31)])))]
+ "TARGET_AVX512F"
+ "vextracti64x4\t{$0x1, %1, %0|%0, %1, 0x1}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix_extra" "1")
+ (set_attr "length_immediate" "1")
+ (set_attr "memory" "none,store")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn_and_split "vec_extract_lo_v16hi"
[(set (match_operand:V8HI 0 "nonimmediate_operand" "=x,m")
(vec_select:V8HI
@@ -5082,6 +5476,66 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
+(define_insn_and_split "vec_extract_lo_v64qi"
+ [(set (match_operand:V32QI 0 "nonimmediate_operand" "=v,m")
+ (vec_select:V32QI
+ (match_operand:V64QI 1 "nonimmediate_operand" "vm,v")
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)
+ (const_int 8) (const_int 9)
+ (const_int 10) (const_int 11)
+ (const_int 12) (const_int 13)
+ (const_int 14) (const_int 15)
+ (const_int 16) (const_int 17)
+ (const_int 18) (const_int 19)
+ (const_int 20) (const_int 21)
+ (const_int 22) (const_int 23)
+ (const_int 24) (const_int 25)
+ (const_int 26) (const_int 27)
+ (const_int 28) (const_int 29)
+ (const_int 30) (const_int 31)])))]
+ "TARGET_AVX512F && !(MEM_P (operands[0]) && MEM_P (operands[1]))"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0) (match_dup 1))]
+{
+ if (REG_P (operands[1]))
+ operands[1] = gen_rtx_REG (V32QImode, REGNO (operands[1]));
+ else
+ operands[1] = adjust_address (operands[1], V32QImode, 0);
+})
+
+(define_insn "vec_extract_hi_v64qi"
+ [(set (match_operand:V32QI 0 "nonimmediate_operand" "=v,m")
+ (vec_select:V32QI
+ (match_operand:V64QI 1 "nonimmediate_operand" "v,v")
+ (parallel [(const_int 32) (const_int 33)
+ (const_int 34) (const_int 35)
+ (const_int 36) (const_int 37)
+ (const_int 38) (const_int 39)
+ (const_int 40) (const_int 41)
+ (const_int 42) (const_int 43)
+ (const_int 44) (const_int 45)
+ (const_int 46) (const_int 47)
+ (const_int 48) (const_int 49)
+ (const_int 50) (const_int 51)
+ (const_int 52) (const_int 53)
+ (const_int 54) (const_int 55)
+ (const_int 56) (const_int 57)
+ (const_int 58) (const_int 59)
+ (const_int 60) (const_int 61)
+ (const_int 62) (const_int 63)])))]
+ "TARGET_AVX512F"
+ "vextracti64x4\t{$0x1, %1, %0|%0, %1, 0x1}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix_extra" "1")
+ (set_attr "length_immediate" "1")
+ (set_attr "memory" "none,store")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn_and_split "vec_extract_lo_v32qi"
[(set (match_operand:V16QI 0 "nonimmediate_operand" "=x,m")
(vec_select:V16QI
@@ -5130,10 +5584,10 @@
(define_mode_iterator VEC_EXTRACT_MODE
[(V32QI "TARGET_AVX") V16QI
(V16HI "TARGET_AVX") V8HI
- (V8SI "TARGET_AVX") V4SI
- (V4DI "TARGET_AVX") V2DI
- (V8SF "TARGET_AVX") V4SF
- (V4DF "TARGET_AVX") V2DF])
+ (V16SI "TARGET_AVX512F") (V8SI "TARGET_AVX") V4SI
+ (V8DI "TARGET_AVX512F") (V4DI "TARGET_AVX") V2DI
+ (V16SF "TARGET_AVX512F") (V8SF "TARGET_AVX") V4SF
+ (V8DF "TARGET_AVX512F") (V4DF "TARGET_AVX") V2DF])
(define_expand "vec_extract<mode>"
[(match_operand:<ssescalarmode> 0 "register_operand")
@@ -5152,6 +5606,22 @@
;;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+(define_insn "avx512f_unpckhpd512"
+ [(set (match_operand:V8DF 0 "register_operand" "=v")
+ (vec_select:V8DF
+ (vec_concat:V16DF
+ (match_operand:V8DF 1 "nonimmediate_operand" "v")
+ (match_operand:V8DF 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 1) (const_int 9)
+ (const_int 3) (const_int 11)
+ (const_int 5) (const_int 13)
+ (const_int 7) (const_int 15)])))]
+ "TARGET_AVX512F"
+ "vunpckhpd\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8DF")])
+
;; Recall that the 256-bit unpck insns only shuffle within their lanes.
(define_insn "avx_unpckhpd256"
[(set (match_operand:V4DF 0 "register_operand" "=x")
@@ -5232,6 +5702,48 @@
(set_attr "prefix" "orig,vex,maybe_vex,orig,vex,maybe_vex")
(set_attr "mode" "V2DF,V2DF,DF,V1DF,V1DF,V1DF")])
+(define_expand "avx512f_movddup512"
+ [(set (match_operand:V8DF 0 "register_operand")
+ (vec_select:V8DF
+ (vec_concat:V16DF
+ (match_operand:V8DF 1 "nonimmediate_operand")
+ (match_dup 1))
+ (parallel [(const_int 0) (const_int 8)
+ (const_int 2) (const_int 10)
+ (const_int 4) (const_int 12)
+ (const_int 6) (const_int 14)])))]
+ "TARGET_AVX512F")
+
+(define_expand "avx512f_unpcklpd512"
+ [(set (match_operand:V8DF 0 "register_operand")
+ (vec_select:V8DF
+ (vec_concat:V16DF
+ (match_operand:V8DF 1 "register_operand")
+ (match_operand:V8DF 2 "nonimmediate_operand"))
+ (parallel [(const_int 0) (const_int 8)
+ (const_int 2) (const_int 10)
+ (const_int 4) (const_int 12)
+ (const_int 6) (const_int 14)])))]
+ "TARGET_AVX512F")
+
+(define_insn "*avx512f_unpcklpd512"
+ [(set (match_operand:V8DF 0 "register_operand" "=v,v")
+ (vec_select:V8DF
+ (vec_concat:V16DF
+ (match_operand:V8DF 1 "nonimmediate_operand" "vm, v")
+ (match_operand:V8DF 2 "nonimmediate_operand" "1 ,vm"))
+ (parallel [(const_int 0) (const_int 8)
+ (const_int 2) (const_int 10)
+ (const_int 4) (const_int 12)
+ (const_int 6) (const_int 14)])))]
+ "TARGET_AVX512F"
+ "@
+ vmovddup\t{%1, %0|%0, %1}
+ vunpcklpd\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8DF")])
+
;; Recall that the 256-bit unpck insns only shuffle within their lanes.
(define_expand "avx_movddup256"
[(set (match_operand:V4DF 0 "register_operand")
@@ -5491,6 +6003,91 @@
(set_attr "prefix" "evex")
(set_attr "mode" "<MODE>")])
+;; One bit in mask selects 2 elements.
+(define_insn "avx512f_shufps512_1"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (vec_select:V16SF
+ (vec_concat:V32SF
+ (match_operand:V16SF 1 "register_operand" "v")
+ (match_operand:V16SF 2 "nonimmediate_operand" "vm"))
+ (parallel [(match_operand 3 "const_0_to_3_operand")
+ (match_operand 4 "const_0_to_3_operand")
+ (match_operand 5 "const_16_to_19_operand")
+ (match_operand 6 "const_16_to_19_operand")
+ (match_operand 7 "const_4_to_7_operand")
+ (match_operand 8 "const_4_to_7_operand")
+ (match_operand 9 "const_20_to_23_operand")
+ (match_operand 10 "const_20_to_23_operand")
+ (match_operand 11 "const_8_to_11_operand")
+ (match_operand 12 "const_8_to_11_operand")
+ (match_operand 13 "const_24_to_27_operand")
+ (match_operand 14 "const_24_to_27_operand")
+ (match_operand 15 "const_12_to_15_operand")
+ (match_operand 16 "const_12_to_15_operand")
+ (match_operand 17 "const_28_to_31_operand")
+ (match_operand 18 "const_28_to_31_operand")])))]
+ "TARGET_AVX512F
+ && (INTVAL (operands[3]) == (INTVAL (operands[7]) - 4)
+ && INTVAL (operands[4]) == (INTVAL (operands[8]) - 4)
+ && INTVAL (operands[5]) == (INTVAL (operands[9]) - 4)
+ && INTVAL (operands[6]) == (INTVAL (operands[10]) - 4)
+ && INTVAL (operands[3]) == (INTVAL (operands[11]) - 8)
+ && INTVAL (operands[4]) == (INTVAL (operands[12]) - 8)
+ && INTVAL (operands[5]) == (INTVAL (operands[13]) - 8)
+ && INTVAL (operands[6]) == (INTVAL (operands[14]) - 8)
+ && INTVAL (operands[3]) == (INTVAL (operands[15]) - 12)
+ && INTVAL (operands[4]) == (INTVAL (operands[16]) - 12)
+ && INTVAL (operands[5]) == (INTVAL (operands[17]) - 12)
+ && INTVAL (operands[6]) == (INTVAL (operands[18]) - 12))"
+{
+ int mask;
+ mask = INTVAL (operands[3]);
+ mask |= INTVAL (operands[4]) << 2;
+ mask |= (INTVAL (operands[5]) - 16) << 4;
+ mask |= (INTVAL (operands[6]) - 16) << 6;
+ operands[3] = GEN_INT (mask);
+
+ return "vshufps\t{%3, %2, %1, %0|%0, %1, %2, %3}";
+}
+ [(set_attr "type" "sselog")
+ (set_attr "length_immediate" "1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
+(define_insn "avx512f_shufpd512_1"
+ [(set (match_operand:V8DF 0 "register_operand" "=v")
+ (vec_select:V8DF
+ (vec_concat:V16DF
+ (match_operand:V8DF 1 "register_operand" "v")
+ (match_operand:V8DF 2 "nonimmediate_operand" "vm"))
+ (parallel [(match_operand 3 "const_0_to_1_operand")
+ (match_operand 4 "const_8_to_9_operand")
+ (match_operand 5 "const_2_to_3_operand")
+ (match_operand 6 "const_10_to_11_operand")
+ (match_operand 7 "const_4_to_5_operand")
+ (match_operand 8 "const_12_to_13_operand")
+ (match_operand 9 "const_6_to_7_operand")
+ (match_operand 10 "const_14_to_15_operand")])))]
+ "TARGET_AVX512F"
+{
+ int mask;
+ mask = INTVAL (operands[3]);
+ mask |= (INTVAL (operands[4]) - 8) << 1;
+ mask |= (INTVAL (operands[5]) - 2) << 2;
+ mask |= (INTVAL (operands[6]) - 10) << 3;
+ mask |= (INTVAL (operands[7]) - 4) << 4;
+ mask |= (INTVAL (operands[8]) - 12) << 5;
+ mask |= (INTVAL (operands[9]) - 6) << 6;
+ mask |= (INTVAL (operands[10]) - 14) << 7;
+ operands[3] = GEN_INT (mask);
+
+ return "vshufpd\t{%3, %2, %1, %0|%0, %1, %2, %3}";
+}
+ [(set_attr "type" "sselog")
+ (set_attr "length_immediate" "1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V8DF")])
+
(define_expand "avx_shufpd256"
[(match_operand:V4DF 0 "register_operand")
(match_operand:V4DF 1 "register_operand")
@@ -5564,6 +6161,22 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
+(define_insn "avx512f_interleave_highv8di"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (vec_select:V8DI
+ (vec_concat:V16DI
+ (match_operand:V8DI 1 "register_operand" "v")
+ (match_operand:V8DI 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 1) (const_int 9)
+ (const_int 3) (const_int 11)
+ (const_int 5) (const_int 13)
+ (const_int 7) (const_int 15)])))]
+ "TARGET_AVX512F"
+ "vpunpckhqdq\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "vec_interleave_highv2di"
[(set (match_operand:V2DI 0 "register_operand" "=x,x")
(vec_select:V2DI
@@ -5598,6 +6211,22 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
+(define_insn "avx512f_interleave_lowv8di"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (vec_select:V8DI
+ (vec_concat:V16DI
+ (match_operand:V8DI 1 "register_operand" "v")
+ (match_operand:V8DI 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 0) (const_int 8)
+ (const_int 2) (const_int 10)
+ (const_int 4) (const_int 12)
+ (const_int 6) (const_int 14)])))]
+ "TARGET_AVX512F"
+ "vpunpcklqdq\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "vec_interleave_lowv2di"
[(set (match_operand:V2DI 0 "register_operand" "=x,x")
(vec_select:V2DI
@@ -5941,6 +6570,64 @@
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
;;
+;; Parallel integer down-conversion operations
+;;
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+
+(define_mode_iterator PMOV_DST_MODE [V16QI V16HI V8SI V8HI])
+(define_mode_attr pmov_src_mode
+ [(V16QI "V16SI") (V16HI "V16SI") (V8SI "V8DI") (V8HI "V8DI")])
+(define_mode_attr pmov_src_lower
+ [(V16QI "v16si") (V16HI "v16si") (V8SI "v8di") (V8HI "v8di")])
+(define_mode_attr pmov_suff
+ [(V16QI "db") (V16HI "dw") (V8SI "qd") (V8HI "qw")])
+
+(define_insn "*avx512f_<code><pmov_src_lower><mode>2"
+ [(set (match_operand:PMOV_DST_MODE 0 "nonimmediate_operand" "=v,m")
+ (any_truncate:PMOV_DST_MODE
+ (match_operand:<pmov_src_mode> 1 "register_operand" "v,v")))]
+ "TARGET_AVX512F"
+ "vpmov<trunsuffix><pmov_suff>\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "memory" "none,store")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "<sseinsnmode>")])
+
+(define_insn "*avx512f_<code>v8div16qi2"
+ [(set (match_operand:V16QI 0 "register_operand" "=v")
+ (vec_concat:V16QI
+ (any_truncate:V8QI
+ (match_operand:V8DI 1 "register_operand" "v"))
+ (const_vector:V8QI [(const_int 0) (const_int 0)
+ (const_int 0) (const_int 0)
+ (const_int 0) (const_int 0)
+ (const_int 0) (const_int 0)])))]
+ "TARGET_AVX512F"
+ "vpmov<trunsuffix>qb\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "TI")])
+
+(define_insn "*avx512f_<code>v8div16qi2_store"
+ [(set (match_operand:V16QI 0 "memory_operand" "=m")
+ (vec_concat:V16QI
+ (any_truncate:V8QI
+ (match_operand:V8DI 1 "register_operand" "v"))
+ (vec_select:V8QI
+ (match_dup 0)
+ (parallel [(const_int 8) (const_int 9)
+ (const_int 10) (const_int 11)
+ (const_int 12) (const_int 13)
+ (const_int 14) (const_int 15)]))))]
+ "TARGET_AVX512F"
+ "vpmov<trunsuffix>qb\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "memory" "store")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "TI")])
+
+;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
+;;
;; Parallel integral arithmetic
;;
;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;
@@ -6063,6 +6750,51 @@
(set_attr "prefix" "orig,vex")
(set_attr "mode" "<sseinsnmode>")])
+(define_expand "vec_widen_umult_even_v16si"
+ [(set (match_operand:V8DI 0 "register_operand")
+ (mult:V8DI
+ (zero_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))
+ (zero_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 2 "nonimmediate_operand")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))))]
+ "TARGET_AVX512F"
+ "ix86_fixup_binary_operands_no_copy (MULT, V16SImode, operands);")
+
+(define_insn "*vec_widen_umult_even_v16si"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (mult:V8DI
+ (zero_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand" "%v")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))
+ (zero_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 2 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))))]
+ "TARGET_AVX512F && ix86_binary_operator_ok (MULT, V16SImode, operands)"
+ "vpmuludq\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "avx512f")
+ (set_attr "type" "sseimul")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_expand "vec_widen_umult_even_v8si"
[(set (match_operand:V4DI 0 "register_operand")
(mult:V4DI
@@ -6133,6 +6865,51 @@
(set_attr "prefix" "orig,vex")
(set_attr "mode" "TI")])
+(define_expand "vec_widen_smult_even_v16si"
+ [(set (match_operand:V8DI 0 "register_operand")
+ (mult:V8DI
+ (sign_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))
+ (sign_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 2 "nonimmediate_operand")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))))]
+ "TARGET_AVX512F"
+ "ix86_fixup_binary_operands_no_copy (MULT, V16SImode, operands);")
+
+(define_insn "*vec_widen_smult_even_v16si"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (mult:V8DI
+ (sign_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 1 "nonimmediate_operand" "%v")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))
+ (sign_extend:V8DI
+ (vec_select:V8SI
+ (match_operand:V16SI 2 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0) (const_int 2)
+ (const_int 4) (const_int 6)
+ (const_int 8) (const_int 10)
+ (const_int 12) (const_int 14)])))))]
+ "TARGET_AVX512F && ix86_binary_operator_ok (MULT, V16SImode, operands)"
+ "vpmuldq\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "avx512f")
+ (set_attr "type" "sseimul")
+ (set_attr "prefix_extra" "1")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_expand "vec_widen_smult_even_v8si"
[(set (match_operand:V4DI 0 "register_operand")
(mult:V4DI
@@ -7105,7 +7882,9 @@
[V16QI V8HI V4SI V2DI V4SF V2DF
(V32QI "TARGET_AVX2") (V16HI "TARGET_AVX2")
(V8SI "TARGET_AVX2") (V4DI "TARGET_AVX2")
- (V8SF "TARGET_AVX2") (V4DF "TARGET_AVX2")])
+ (V8SF "TARGET_AVX2") (V4DF "TARGET_AVX2")
+ (V16SF "TARGET_AVX512F") (V8DF "TARGET_AVX512F")
+ (V16SI "TARGET_AVX512F") (V8DI "TARGET_AVX512F")])
(define_expand "vec_perm<mode>"
[(match_operand:VEC_PERM_AVX2 0 "register_operand")
@@ -7124,7 +7903,9 @@
(V16QI "TARGET_SSE2") (V8HI "TARGET_SSE2")
(V8SF "TARGET_AVX") (V4DF "TARGET_AVX")
(V8SI "TARGET_AVX") (V4DI "TARGET_AVX")
- (V32QI "TARGET_AVX2") (V16HI "TARGET_AVX2")])
+ (V32QI "TARGET_AVX2") (V16HI "TARGET_AVX2")
+ (V16SI "TARGET_AVX512F") (V8DI "TARGET_AVX512F")
+ (V16SF "TARGET_AVX512F") (V8DF "TARGET_AVX512F")])
(define_expand "vec_perm_const<mode>"
[(match_operand:VEC_PERM_CONST 0 "register_operand")
@@ -7629,6 +8410,27 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
+(define_insn "avx512f_interleave_highv16si"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (vec_select:V16SI
+ (vec_concat:V32SI
+ (match_operand:V16SI 1 "register_operand" "v")
+ (match_operand:V16SI 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 2) (const_int 18)
+ (const_int 3) (const_int 19)
+ (const_int 6) (const_int 22)
+ (const_int 7) (const_int 23)
+ (const_int 10) (const_int 26)
+ (const_int 11) (const_int 27)
+ (const_int 14) (const_int 30)
+ (const_int 15) (const_int 31)])))]
+ "TARGET_AVX512F"
+ "vpunpckhdq\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
+
(define_insn "vec_interleave_highv4si"
[(set (match_operand:V4SI 0 "register_operand" "=x,x")
(vec_select:V4SI
@@ -7663,6 +8465,26 @@
(set_attr "prefix" "vex")
(set_attr "mode" "OI")])
+(define_insn "avx512f_interleave_lowv16si"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (vec_select:V16SI
+ (vec_concat:V32SI
+ (match_operand:V16SI 1 "register_operand" "v")
+ (match_operand:V16SI 2 "nonimmediate_operand" "vm"))
+ (parallel [(const_int 0) (const_int 16)
+ (const_int 1) (const_int 17)
+ (const_int 4) (const_int 20)
+ (const_int 5) (const_int 21)
+ (const_int 8) (const_int 24)
+ (const_int 9) (const_int 25)
+ (const_int 12) (const_int 28)
+ (const_int 13) (const_int 29)])))]
+ "TARGET_AVX512F"
+ "vpunpckldq\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "sselog")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "vec_interleave_lowv4si"
[(set (match_operand:V4SI 0 "register_operand" "=x,x")
(vec_select:V4SI
@@ -9763,6 +10585,16 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
+(define_insn "avx512f_<code>v16qiv16si2"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (any_extend:V16SI
+ (match_operand:V16QI 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vpmov<extsuffix>bd\t{%1, %0|%0, %q1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "avx2_<code>v8qiv8si2"
[(set (match_operand:V8SI 0 "register_operand" "=x")
(any_extend:V8SI
@@ -9793,6 +10625,16 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
+(define_insn "avx512f_<code>v16hiv16si2"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (any_extend:V16SI
+ (match_operand:V16HI 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vpmov<extsuffix>wd\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "avx2_<code>v8hiv8si2"
[(set (match_operand:V8SI 0 "register_operand" "=x")
(any_extend:V8SI
@@ -9818,6 +10660,21 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
+(define_insn "avx512f_<code>v8qiv8di2"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (any_extend:V8DI
+ (vec_select:V8QI
+ (match_operand:V16QI 1 "nonimmediate_operand" "vm")
+ (parallel [(const_int 0) (const_int 1)
+ (const_int 2) (const_int 3)
+ (const_int 4) (const_int 5)
+ (const_int 6) (const_int 7)]))))]
+ "TARGET_AVX512F"
+ "vpmov<extsuffix>bq\t{%1, %0|%0, %k1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "avx2_<code>v4qiv4di2"
[(set (match_operand:V4DI 0 "register_operand" "=x")
(any_extend:V4DI
@@ -9845,6 +10702,16 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
+(define_insn "avx512f_<code>v8hiv8di2"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (any_extend:V8DI
+ (match_operand:V8HI 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vpmov<extsuffix>wq\t{%1, %0|%0, %q1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "avx2_<code>v4hiv4di2"
[(set (match_operand:V4DI 0 "register_operand" "=x")
(any_extend:V4DI
@@ -9872,6 +10739,16 @@
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "TI")])
+(define_insn "avx512f_<code>v8siv8di2"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (any_extend:V8DI
+ (match_operand:V8SI 1 "nonimmediate_operand" "vm")))]
+ "TARGET_AVX512F"
+ "vpmov<extsuffix>dq\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssemov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
(define_insn "avx2_<code>v4siv4di2"
[(set (match_operand:V4DI 0 "register_operand" "=x")
(any_extend:V4DI
@@ -11908,6 +12785,28 @@
(set_attr "prefix" "vex")
(set_attr "mode" "<sseinsnmode>")])
+(define_insn "avx512cd_maskb_vec_dupv8di"
+ [(set (match_operand:V8DI 0 "register_operand" "=v")
+ (vec_duplicate:V8DI
+ (zero_extend:DI
+ (match_operand:QI 1 "register_operand" "k"))))]
+ "TARGET_AVX512CD"
+ "vpbroadcastmb2q\t{%1, %0|%0, %1}"
+ [(set_attr "type" "mskmov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
+(define_insn "avx512cd_maskw_vec_dupv16si"
+ [(set (match_operand:V16SI 0 "register_operand" "=v")
+ (vec_duplicate:V16SI
+ (zero_extend:SI
+ (match_operand:HI 1 "register_operand" "k"))))]
+ "TARGET_AVX512CD"
+ "vpbroadcastmw2d\t{%1, %0|%0, %1}"
+ [(set_attr "type" "mskmov")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "XI")])
+
;; Recognize broadcast as a vec_select as produced by builtin_vec_perm.
;; If it so happens that the input is in memory, use vbroadcast.
;; Otherwise use vpermilp (and in the case of 256-bit modes, vperm2f128).
@@ -12575,6 +13474,16 @@
(set_attr "btver2_decode" "double")
(set_attr "mode" "V8SF")])
+(define_insn "avx512f_vcvtph2ps512"
+ [(set (match_operand:V16SF 0 "register_operand" "=v")
+ (unspec:V16SF [(match_operand:V16HI 1 "nonimmediate_operand" "vm")]
+ UNSPEC_VCVTPH2PS))]
+ "TARGET_AVX512F"
+ "vcvtph2ps\t{%1, %0|%0, %1}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
(define_expand "vcvtps2ph"
[(set (match_operand:V8HI 0 "register_operand")
(vec_concat:V8HI
@@ -12621,6 +13530,17 @@
(set_attr "btver2_decode" "vector")
(set_attr "mode" "V8SF")])
+(define_insn "avx512f_vcvtps2ph512"
+ [(set (match_operand:V16HI 0 "nonimmediate_operand" "=vm")
+ (unspec:V16HI [(match_operand:V16SF 1 "register_operand" "v")
+ (match_operand:SI 2 "const_0_to_255_operand" "N")]
+ UNSPEC_VCVTPS2PH))]
+ "TARGET_AVX512F"
+ "vcvtps2ph\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "type" "ssecvt")
+ (set_attr "prefix" "evex")
+ (set_attr "mode" "V16SF")])
+
;; For gather* insn patterns
(define_mode_iterator VEC_GATHER_MODE
[V2DI V2DF V4DI V4DF V4SI V4SF V8SI V8SF])
More information about the Gcc-patches
mailing list