Patchwork [AArch64] Make zero_extends explicit for some SImode patterns

login
register
mail settings
Submitter Ian Bolton
Date Jan. 15, 2013, 4:13 p.m.
Message ID <000001cdf33b$495faf40$dc1f0dc0$@bolton@arm.com>
Download mbox | patch
Permalink /patch/212216/
State New
Headers show

Comments

Ian Bolton - Jan. 15, 2013, 4:13 p.m.
Greetings!
 
I've made zero_extend versions of SI mode patterns that write
to W registers in order to make the implicit zero_extend that
they do explicit, so GCC can be smarter about when it actually
needs to plant a zero_extend (uxtw).

If that sounds familiar, it's because this patch continues the
work of one already committed. :)

This has been regression-tested for linux and bare-metal.

OK for trunk and backport to ARM/aarch64-4.7-branch?

Cheers,
Ian


2013-01-15  Ian Bolton  <ian.bolton@arm.com>

	* gcc/config/aarch64/aarch64.md
	(*cstoresi_neg_uxtw): New pattern.
	(*cmovsi_insn_uxtw): New pattern.
	(*<optab>si3_uxtw): New pattern.
	(*<LOGICAL:optab>_<SHIFT:optab>si3_uxtw): New pattern.
	(*<optab>si3_insn_uxtw): New pattern.
	(*bswapsi2_uxtw): New pattern.
Marcus Shawcroft - Jan. 15, 2013, 4:32 p.m.
On 15/01/13 16:13, Ian Bolton wrote:
> Greetings!
>
> I've made zero_extend versions of SI mode patterns that write
> to W registers in order to make the implicit zero_extend that
> they do explicit, so GCC can be smarter about when it actually
> needs to plant a zero_extend (uxtw).
>
> If that sounds familiar, it's because this patch continues the
> work of one already committed. :)
>
> This has been regression-tested for linux and bare-metal.
>
> OK for trunk and backport to ARM/aarch64-4.7-branch?
>
> Cheers,
> Ian
>
>
> 2013-01-15  Ian Bolton  <ian.bolton@arm.com>
>
> 	* gcc/config/aarch64/aarch64.md
> 	(*cstoresi_neg_uxtw): New pattern.
> 	(*cmovsi_insn_uxtw): New pattern.
> 	(*<optab>si3_uxtw): New pattern.
> 	(*<LOGICAL:optab>_<SHIFT:optab>si3_uxtw): New pattern.
> 	(*<optab>si3_insn_uxtw): New pattern.
> 	(*bswapsi2_uxtw): New pattern.
>


OK

Patch

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index ec65b3c..8dd6c22 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -1,5 +1,5 @@ 
 ;; Machine description for AArch64 architecture.
-;; Copyright (C) 2009, 2010, 2011, 2012 Free Software Foundation, Inc.
+;; Copyright (C) 2009, 2010, 2011, 2012, 2013 Free Software Foundation, Inc.
 ;; Contributed by ARM Ltd.
 ;;
 ;; This file is part of GCC.
@@ -2193,6 +2193,18 @@ 
    (set_attr "mode" "<MODE>")]
 )
 
+;; zero_extend version of the above
+(define_insn "*cstoresi_insn_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(zero_extend:DI
+	 (match_operator:SI 1 "aarch64_comparison_operator"
+	  [(match_operand 2 "cc_register" "") (const_int 0)])))]
+  ""
+  "cset\\t%w0, %m1"
+  [(set_attr "v8type" "csel")
+   (set_attr "mode" "SI")]
+)
+
 (define_insn "*cstore<mode>_neg"
   [(set (match_operand:ALLI 0 "register_operand" "=r")
 	(neg:ALLI (match_operator:ALLI 1 "aarch64_comparison_operator"
@@ -2203,6 +2215,18 @@ 
    (set_attr "mode" "<MODE>")]
 )
 
+;; zero_extend version of the above
+(define_insn "*cstoresi_neg_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(zero_extend:DI
+	 (neg:SI (match_operator:SI 1 "aarch64_comparison_operator"
+		  [(match_operand 2 "cc_register" "") (const_int 0)]))))]
+  ""
+  "csetm\\t%w0, %m1"
+  [(set_attr "v8type" "csel")
+   (set_attr "mode" "SI")]
+)
+
 (define_expand "cmov<mode>6"
   [(set (match_operand:GPI 0 "register_operand" "")
 	(if_then_else:GPI
@@ -2257,6 +2281,30 @@ 
    (set_attr "mode" "<MODE>")]
 )
 
+;; zero_extend version of above
+(define_insn "*cmovsi_insn_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r,r,r,r,r,r,r")
+	(zero_extend:DI
+	 (if_then_else:SI
+	  (match_operator 1 "aarch64_comparison_operator"
+	   [(match_operand 2 "cc_register" "") (const_int 0)])
+	  (match_operand:SI 3 "aarch64_reg_zero_or_m1_or_1" "rZ,rZ,UsM,rZ,Ui1,UsM,Ui1")
+	  (match_operand:SI 4 "aarch64_reg_zero_or_m1_or_1" "rZ,UsM,rZ,Ui1,rZ,UsM,Ui1"))))]
+  "!((operands[3] == const1_rtx && operands[4] == constm1_rtx)
+     || (operands[3] == constm1_rtx && operands[4] == const1_rtx))"
+  ;; Final two alternatives should be unreachable, but included for completeness
+  "@
+   csel\\t%w0, %w3, %w4, %m1
+   csinv\\t%w0, %w3, wzr, %m1
+   csinv\\t%w0, %w4, wzr, %M1
+   csinc\\t%w0, %w3, wzr, %m1
+   csinc\\t%w0, %w4, wzr, %M1
+   mov\\t%w0, -1
+   mov\\t%w0, 1"
+  [(set_attr "v8type" "csel")
+   (set_attr "mode" "SI")]
+)
+
 (define_insn "*cmov<mode>_insn"
   [(set (match_operand:GPF 0 "register_operand" "=w")
 	(if_then_else:GPF
@@ -2369,6 +2417,17 @@ 
   [(set_attr "v8type" "logic,logic_imm")
    (set_attr "mode" "<MODE>")])
 
+;; zero_extend version of above
+(define_insn "*<optab>si3_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r,rk")
+	(zero_extend:DI
+         (LOGICAL:SI (match_operand:SI 1 "register_operand" "%r,r")
+		     (match_operand:SI 2 "aarch64_logical_operand" "r,K"))))]
+  ""
+  "<logical>\\t%w0, %w1, %w2"
+  [(set_attr "v8type" "logic,logic_imm")
+   (set_attr "mode" "SI")])
+
 (define_insn "*<LOGICAL:optab>_<SHIFT:optab><mode>3"
   [(set (match_operand:GPI 0 "register_operand" "=r")
 	(LOGICAL:GPI (SHIFT:GPI
@@ -2380,6 +2439,19 @@ 
   [(set_attr "v8type" "logic_shift")
    (set_attr "mode" "<MODE>")])
 
+;; zero_extend version of above
+(define_insn "*<LOGICAL:optab>_<SHIFT:optab>si3_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(zero_extend:DI
+	 (LOGICAL:SI (SHIFT:SI
+		      (match_operand:SI 1 "register_operand" "r")
+		      (match_operand:QI 2 "aarch64_shift_imm_si" "n"))
+		     (match_operand:SI 3 "register_operand" "r"))))]
+  ""
+  "<LOGICAL:logical>\\t%w0, %w3, %w1, <SHIFT:shift> %2"
+  [(set_attr "v8type" "logic_shift")
+   (set_attr "mode" "SI")])
+
 (define_insn "one_cmpl<mode>2"
   [(set (match_operand:GPI 0 "register_operand" "=r")
 	(not:GPI (match_operand:GPI 1 "register_operand" "r")))]
@@ -2591,6 +2663,18 @@ 
    (set_attr "mode" "<MODE>")]
 )
 
+;; zero_extend version of above
+(define_insn "*<optab>si3_insn_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+	(zero_extend:DI (SHIFT:SI
+	 (match_operand:SI 1 "register_operand" "r")
+	 (match_operand:QI 2 "aarch64_reg_or_shift_imm_si" "rUss"))))]
+  ""
+  "<shift>\\t%w0, %w1, %w2"
+  [(set_attr "v8type" "shift")
+   (set_attr "mode" "SI")]
+)
+
 (define_insn "*ashl<mode>3_insn"
   [(set (match_operand:SHORT 0 "register_operand" "=r")
 	(ashift:SHORT (match_operand:SHORT 1 "register_operand" "r")
@@ -2728,6 +2812,16 @@ 
    (set_attr "mode" "HI")]
 )
 
+;; zero_extend version of above
+(define_insn "*bswapsi2_uxtw"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+        (zero_extend:DI (bswap:SI (match_operand:SI 1 "register_operand" "r"))))]
+  ""
+  "rev\\t%w0, %w1"
+  [(set_attr "v8type" "rev")
+   (set_attr "mode" "SI")]
+)
+
 ;; -------------------------------------------------------------------
 ;; Floating-point intrinsics
 ;; -------------------------------------------------------------------