[gcc r14-1921] xtensa: constantsynth: Add new 2-insns synthesis pattern

[Max Filippov]

https://gcc.gnu.org/g:7360cba833cd921631818428a851e03ea88f1e8a

commit r14-1921-g7360cba833cd921631818428a851e03ea88f1e8a
Author: Takayuki 'January June' Suwa <jjsuwa_sys3175@yahoo.co.jp>
Date:   Sun Jun 18 16:09:10 2023 +0900

    xtensa: constantsynth: Add new 2-insns synthesis pattern
    
    This patch adds a new 2-instructions constant synthesis pattern:
    
    -  A non-negative square value that root can fit into a signed 12-bit:
        => "MOVI(.N) Ax, simm12" + "MULL Ax, Ax, Ax"
    
    Due to the execution cost of the integer multiply instruction (MULL), this
    synthesis works only when the 32-bit Integer Multiply Option is configured
    and optimize for size is specified.
    
    gcc/ChangeLog:
    
            * config/xtensa/xtensa.cc (xtensa_constantsynth_2insn):
            Add new pattern for the abovementioned case.

Diff:
---
 gcc/config/xtensa/xtensa.cc | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/gcc/config/xtensa/xtensa.cc b/gcc/config/xtensa/xtensa.cc
index 721c99b56a3..dd35e63c094 100644
--- a/gcc/config/xtensa/xtensa.cc
+++ b/gcc/config/xtensa/xtensa.cc
@@ -58,6 +58,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "insn-attr.h"
 #include "tree-pass.h"
 #include "print-rtl.h"
+#include <math.h>
 
 /* This file should be included last.  */
 #include "target-def.h"
@@ -1067,7 +1068,7 @@ xtensa_constantsynth_2insn (rtx dst, HOST_WIDE_INT srcval,
 {
   HOST_WIDE_INT imm = INT_MAX;
   rtx x = NULL_RTX;
-  int shift;
+  int shift, sqr;
 
   gcc_assert (REG_P (dst));
 
@@ -1078,7 +1079,6 @@ xtensa_constantsynth_2insn (rtx dst, HOST_WIDE_INT srcval,
       x = gen_lshrsi3 (dst, dst, GEN_INT (32 - shift));
     }
 
-
   shift = ctz_hwi (srcval);
   if ((!x || (TARGET_DENSITY && ! IN_RANGE (imm, -32, 95)))
       && xtensa_simm12b (srcval >> shift))
@@ -1105,6 +1105,14 @@ xtensa_constantsynth_2insn (rtx dst, HOST_WIDE_INT srcval,
       x = gen_addsi3 (dst, dst, GEN_INT (imm1));
     }
 
+  sqr = (int) floorf (sqrtf (srcval));
+  if (TARGET_MUL32 && optimize_size
+      && !x && IN_RANGE (srcval, 0, (2047 * 2047)) && sqr * sqr == srcval)
+    {
+      imm = sqr;
+      x = gen_mulsi3 (dst, dst, dst);
+    }
+
   if (!x)
     return 0;