public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
* [PATCH 1/4] xtensa: Tweak some widen multiplications
@ 2022-06-10  4:17 Takayuki 'January June' Suwa
  2022-06-11 23:13 ` Max Filippov
  0 siblings, 1 reply; 2+ messages in thread
From: Takayuki 'January June' Suwa @ 2022-06-10  4:17 UTC (permalink / raw)
  To: GCC Patches

umulsidi3 is faster than umuldi3 even if library call, and is also
prerequisite for fast constant division by multiplication.

gcc/ChangeLog:

	* config/xtensa/xtensa.md (mulsidi3, umulsidi3):
	Split into individual signedness, in order to use libcall
	"__umulsidi3" but not the other.
	(<u>mulhisi3): Merge into one by using code iterator.
	(<u>mulsidi3, mulhisi3, umulhisi3): Remove.
---
  gcc/config/xtensa/xtensa.md | 56 +++++++++++++++++++++----------------
  1 file changed, 32 insertions(+), 24 deletions(-)

diff --git a/gcc/config/xtensa/xtensa.md b/gcc/config/xtensa/xtensa.md
index 8ff6f9a95fe..33cbd546de3 100644
--- a/gcc/config/xtensa/xtensa.md
+++ b/gcc/config/xtensa/xtensa.md
@@ -224,20 +224,42 @@
  \f
  ;; Multiplication.

-(define_expand "<u>mulsidi3"
+(define_expand "mulsidi3"
    [(set (match_operand:DI 0 "register_operand")
-	(mult:DI (any_extend:DI (match_operand:SI 1 "register_operand"))
-		 (any_extend:DI (match_operand:SI 2 "register_operand"))))]
+	(mult:DI (sign_extend:DI (match_operand:SI 1 "register_operand"))
+		 (sign_extend:DI (match_operand:SI 2 "register_operand"))))]
    "TARGET_MUL32_HIGH"
  {
    rtx temp = gen_reg_rtx (SImode);
    emit_insn (gen_mulsi3 (temp, operands[1], operands[2]));
-  emit_insn (gen_<u>mulsi3_highpart (gen_highpart (SImode, operands[0]),
-				     operands[1], operands[2]));
+  emit_insn (gen_mulsi3_highpart (gen_highpart (SImode, operands[0]),
+				  operands[1], operands[2]));
    emit_insn (gen_movsi (gen_lowpart (SImode, operands[0]), temp));
    DONE;
  })

+(define_expand "umulsidi3"
+  [(set (match_operand:DI 0 "register_operand")
+	(mult:DI (zero_extend:DI (match_operand:SI 1 "register_operand"))
+		 (zero_extend:DI (match_operand:SI 2 "register_operand"))))]
+  ""
+{
+  if (TARGET_MUL32_HIGH)
+    {
+      rtx temp = gen_reg_rtx (SImode);
+      emit_insn (gen_mulsi3 (temp, operands[1], operands[2]));
+      emit_insn (gen_umulsi3_highpart (gen_highpart (SImode, operands[0]),
+				       operands[1], operands[2]));
+      emit_insn (gen_movsi (gen_lowpart (SImode, operands[0]), temp));
+    }
+  else
+    emit_library_call_value (gen_rtx_SYMBOL_REF (Pmode, "__umulsidi3"),
+			     operands[0], LCT_NORMAL, DImode,
+			     operands[1], SImode,
+			     operands[2], SImode);
+   DONE;
+})
+
  (define_insn "<u>mulsi3_highpart"
    [(set (match_operand:SI 0 "register_operand" "=a")
  	(truncate:SI
@@ -261,30 +283,16 @@
     (set_attr "mode"	"SI")
     (set_attr "length"	"3")])

-(define_insn "mulhisi3"
-  [(set (match_operand:SI 0 "register_operand" "=C,A")
-	(mult:SI (sign_extend:SI
-		  (match_operand:HI 1 "register_operand" "%r,r"))
-		 (sign_extend:SI
-		  (match_operand:HI 2 "register_operand" "r,r"))))]
-  "TARGET_MUL16 || TARGET_MAC16"
-  "@
-   mul16s\t%0, %1, %2
-   mul.aa.ll\t%1, %2"
-  [(set_attr "type"	"mul16,mac16")
-   (set_attr "mode"	"SI")
-   (set_attr "length"	"3,3")])
-
-(define_insn "umulhisi3"
+(define_insn "<u>mulhisi3"
    [(set (match_operand:SI 0 "register_operand" "=C,A")
-	(mult:SI (zero_extend:SI
+	(mult:SI (any_extend:SI
  		  (match_operand:HI 1 "register_operand" "%r,r"))
-		 (zero_extend:SI
+		 (any_extend:SI
  		  (match_operand:HI 2 "register_operand" "r,r"))))]
    "TARGET_MUL16 || TARGET_MAC16"
    "@
-   mul16u\t%0, %1, %2
-   umul.aa.ll\t%1, %2"
+   mul16<su>\t%0, %1, %2
+   <u>mul.aa.ll\t%1, %2"
    [(set_attr "type"	"mul16,mac16")
     (set_attr "mode"	"SI")
     (set_attr "length"	"3,3")])
-- 
2.20.1

^ permalink raw reply	[flat|nested] 2+ messages in thread

* Re: [PATCH 1/4] xtensa: Tweak some widen multiplications
  2022-06-10  4:17 [PATCH 1/4] xtensa: Tweak some widen multiplications Takayuki 'January June' Suwa
@ 2022-06-11 23:13 ` Max Filippov
  0 siblings, 0 replies; 2+ messages in thread
From: Max Filippov @ 2022-06-11 23:13 UTC (permalink / raw)
  To: Takayuki 'January June' Suwa; +Cc: GCC Patches

On Thu, Jun 9, 2022 at 9:26 PM Takayuki 'January June' Suwa
<jjsuwa_sys3175@yahoo.co.jp> wrote:
>
> umulsidi3 is faster than umuldi3 even if library call, and is also
> prerequisite for fast constant division by multiplication.
>
> gcc/ChangeLog:
>
>         * config/xtensa/xtensa.md (mulsidi3, umulsidi3):
>         Split into individual signedness, in order to use libcall
>         "__umulsidi3" but not the other.
>         (<u>mulhisi3): Merge into one by using code iterator.
>         (<u>mulsidi3, mulhisi3, umulhisi3): Remove.
> ---
>   gcc/config/xtensa/xtensa.md | 56 +++++++++++++++++++++----------------
>   1 file changed, 32 insertions(+), 24 deletions(-)

Regtested for target=xtensa-linux-uclibc, no new regressions.
Committed to master.

-- 
Thanks.
-- Max

^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2022-06-11 23:13 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-06-10  4:17 [PATCH 1/4] xtensa: Tweak some widen multiplications Takayuki 'January June' Suwa
2022-06-11 23:13 ` Max Filippov

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).