Skip to content

R
riscv-gcc-1
Commit 6eacd27c by Alexander Ivchenko Committed by Kirill Yukhin
Options

AVX-512. Add mov[dlh]dup insns support. 

gcc/
	* config/i386/sse.md
	(define_insn "avx_movshdup256<mask_name>"): Add masking.
	(define_insn "sse3_movshdup<mask_name>"): Ditto.
	(define_insn "avx_movsldup256<mask_name>"): Ditto.
	(define_insn "sse3_movsldup<mask_name>"): Ditto.
	(define_insn "vec_dupv2df<mask_name>"): Ditto.
	(define_insn "*vec_concatv2df"): Add EVEX version.

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: r215589
parent deb90bb5
Showing with 45 additions and 28 deletions
gcc/ChangeLog
...@@ -8,6 +8,23 @@ ...@@ -8,6 +8,23 @@
Michael Zolotukhin <michael.v.zolotukhin@intel.com> Michael Zolotukhin <michael.v.zolotukhin@intel.com>
* config/i386/sse.md * config/i386/sse.md
(define_insn "avx_movshdup256<mask_name>"): Add masking.
(define_insn "sse3_movshdup<mask_name>"): Ditto.
(define_insn "avx_movsldup256<mask_name>"): Ditto.
(define_insn "sse3_movsldup<mask_name>"): Ditto.
(define_insn "vec_dupv2df<mask_name>"): Ditto.
(define_insn "*vec_concatv2df"): Add EVEX version.
2014-09-25 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 "vec_set<mode>_0"): Add EVEX version. (define_insn "vec_set<mode>_0"): Add EVEX version.
2014-09-25 Alexander Ivchenko <alexander.ivchenko@intel.com> 2014-09-25 Alexander Ivchenko <alexander.ivchenko@intel.com>
gcc/config/i386/sse.md
...@@ -5735,34 +5735,34 @@ ...@@ -5735,34 +5735,34 @@
;; These are modeled with the same vec_concat as the others so that we ;; These are modeled with the same vec_concat as the others so that we
;; capture users of shufps that can use the new instructions ;; capture users of shufps that can use the new instructions
(define_insn "avx_movshdup256" (define_insn "avx_movshdup256<mask_name>"
[(set (match_operand:V8SF 0 "register_operand" "=x") [(set (match_operand:V8SF 0 "register_operand" "=v")
(vec_select:V8SF (vec_select:V8SF
(vec_concat:V16SF (vec_concat:V16SF
(match_operand:V8SF 1 "nonimmediate_operand" "xm") (match_operand:V8SF 1 "nonimmediate_operand" "vm")
(match_dup 1)) (match_dup 1))
(parallel [(const_int 1) (const_int 1) (parallel [(const_int 1) (const_int 1)
(const_int 3) (const_int 3) (const_int 3) (const_int 3)
(const_int 5) (const_int 5) (const_int 5) (const_int 5)
(const_int 7) (const_int 7)])))] (const_int 7) (const_int 7)])))]
"TARGET_AVX" "TARGET_AVX && <mask_avx512vl_condition>"
"vmovshdup\t{%1, %0|%0, %1}" "vmovshdup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "sse") [(set_attr "type" "sse")
(set_attr "prefix" "vex") (set_attr "prefix" "vex")
(set_attr "mode" "V8SF")]) (set_attr "mode" "V8SF")])
(define_insn "sse3_movshdup" (define_insn "sse3_movshdup<mask_name>"
[(set (match_operand:V4SF 0 "register_operand" "=x") [(set (match_operand:V4SF 0 "register_operand" "=v")
(vec_select:V4SF (vec_select:V4SF
(vec_concat:V8SF (vec_concat:V8SF
(match_operand:V4SF 1 "nonimmediate_operand" "xm") (match_operand:V4SF 1 "nonimmediate_operand" "vm")
(match_dup 1)) (match_dup 1))
(parallel [(const_int 1) (parallel [(const_int 1)
(const_int 1) (const_int 1)
(const_int 7) (const_int 7)
(const_int 7)])))] (const_int 7)])))]
"TARGET_SSE3" "TARGET_SSE3 && <mask_avx512vl_condition>"
"%vmovshdup\t{%1, %0|%0, %1}" "%vmovshdup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "sse") [(set_attr "type" "sse")
(set_attr "prefix_rep" "1") (set_attr "prefix_rep" "1")
(set_attr "prefix" "maybe_vex") (set_attr "prefix" "maybe_vex")
...@@ -5788,34 +5788,34 @@ ...@@ -5788,34 +5788,34 @@
(set_attr "prefix" "evex") (set_attr "prefix" "evex")
(set_attr "mode" "V16SF")]) (set_attr "mode" "V16SF")])
(define_insn "avx_movsldup256" (define_insn "avx_movsldup256<mask_name>"
[(set (match_operand:V8SF 0 "register_operand" "=x") [(set (match_operand:V8SF 0 "register_operand" "=v")
(vec_select:V8SF (vec_select:V8SF
(vec_concat:V16SF (vec_concat:V16SF
(match_operand:V8SF 1 "nonimmediate_operand" "xm") (match_operand:V8SF 1 "nonimmediate_operand" "vm")
(match_dup 1)) (match_dup 1))
(parallel [(const_int 0) (const_int 0) (parallel [(const_int 0) (const_int 0)
(const_int 2) (const_int 2) (const_int 2) (const_int 2)
(const_int 4) (const_int 4) (const_int 4) (const_int 4)
(const_int 6) (const_int 6)])))] (const_int 6) (const_int 6)])))]
"TARGET_AVX" "TARGET_AVX && <mask_avx512vl_condition>"
"vmovsldup\t{%1, %0|%0, %1}" "vmovsldup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "sse") [(set_attr "type" "sse")
(set_attr "prefix" "vex") (set_attr "prefix" "vex")
(set_attr "mode" "V8SF")]) (set_attr "mode" "V8SF")])
(define_insn "sse3_movsldup" (define_insn "sse3_movsldup<mask_name>"
[(set (match_operand:V4SF 0 "register_operand" "=x") [(set (match_operand:V4SF 0 "register_operand" "=v")
(vec_select:V4SF (vec_select:V4SF
(vec_concat:V8SF (vec_concat:V8SF
(match_operand:V4SF 1 "nonimmediate_operand" "xm") (match_operand:V4SF 1 "nonimmediate_operand" "vm")
(match_dup 1)) (match_dup 1))
(parallel [(const_int 0) (parallel [(const_int 0)
(const_int 0) (const_int 0)
(const_int 6) (const_int 6)
(const_int 6)])))] (const_int 6)])))]
"TARGET_SSE3" "TARGET_SSE3 && <mask_avx512vl_condition>"
"%vmovsldup\t{%1, %0|%0, %1}" "%vmovsldup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "type" "sse") [(set_attr "type" "sse")
(set_attr "prefix_rep" "1") (set_attr "prefix_rep" "1")
(set_attr "prefix" "maybe_vex") (set_attr "prefix" "maybe_vex")
...@@ -8301,24 +8301,24 @@ ...@@ -8301,24 +8301,24 @@
(set_attr "prefix" "orig,vex,orig,vex,maybe_vex,orig,orig,vex,maybe_vex") (set_attr "prefix" "orig,vex,orig,vex,maybe_vex,orig,orig,vex,maybe_vex")
(set_attr "mode" "DF,DF,V1DF,V1DF,V1DF,V2DF,V1DF,V1DF,V1DF")]) (set_attr "mode" "DF,DF,V1DF,V1DF,V1DF,V2DF,V1DF,V1DF,V1DF")])
(define_insn "vec_dupv2df" (define_insn "vec_dupv2df<mask_name>"
[(set (match_operand:V2DF 0 "register_operand" "=x,x") [(set (match_operand:V2DF 0 "register_operand" "=x,v")
(vec_duplicate:V2DF (vec_duplicate:V2DF
(match_operand:DF 1 "nonimmediate_operand" " 0,xm")))] (match_operand:DF 1 "nonimmediate_operand" " 0,vm")))]
"TARGET_SSE2" "TARGET_SSE2 && <mask_avx512vl_condition>"
"@ "@
unpcklpd\t%0, %0 unpcklpd\t%0, %0
%vmovddup\t{%1, %0|%0, %1}" %vmovddup\t{%1, %0<mask_operand2>|%0<mask_operand2>, %1}"
[(set_attr "isa" "noavx,sse3") [(set_attr "isa" "noavx,sse3")
(set_attr "type" "sselog1") (set_attr "type" "sselog1")
(set_attr "prefix" "orig,maybe_vex") (set_attr "prefix" "orig,maybe_vex")
(set_attr "mode" "V2DF,DF")]) (set_attr "mode" "V2DF,DF")])
(define_insn "*vec_concatv2df" (define_insn "*vec_concatv2df"
[(set (match_operand:V2DF 0 "register_operand" "=x,x,x,x,x,x,x,x") [(set (match_operand:V2DF 0 "register_operand" "=x,v,v,x,x,v,x,x")
(vec_concat:V2DF (vec_concat:V2DF
(match_operand:DF 1 "nonimmediate_operand" " 0,x,m,0,x,m,0,0") (match_operand:DF 1 "nonimmediate_operand" " 0,v,m,0,x,m,0,0")
(match_operand:DF 2 "vector_move_operand" " x,x,1,m,m,C,x,m")))] (match_operand:DF 2 "vector_move_operand" " x,v,1,m,m,C,x,m")))]
"TARGET_SSE" "TARGET_SSE"
"@ "@
unpcklpd\t{%2, %0|%0, %2} unpcklpd\t{%2, %0|%0, %2}
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment