New wi::bitreverse function.

Message ID 005301d9955c$f1d6b410$d5841c30$@nextmovesoftware.com
State Accepted
Headers
Series New wi::bitreverse function. |

Checks

Context Check Description
snail/gcc-patch-check success Github commit url

Commit Message

Roger Sayle June 2, 2023, 2:17 p.m. UTC
  This patch provides a wide-int implementation of bitreverse, that
implements both of Richard Sandiford's suggestions from the review at
https://gcc.gnu.org/pipermail/gcc-patches/2023-May/618215.html of an
improved API (as a stand-alone function matching the bswap refactoring),
and an implementation that works with any bit-width precision.

This patch has been tested on x86_64-pc-linux-gnu with make bootstrap
(and a make check-gcc).  Ok for mainline?  Are the remaining pieces
of the above patch pre-approved (pending re-testing)?  The aim is that
this new code will be thoroughly tested by the new *-2.c test cases in
https://gcc.gnu.org/git/?p=gcc.git;h=c09471fbc7588db2480f036aa56a2403d3c03ae
5
with a minor tweak to use the BITREVERSE rtx in the NVPTX back-end,
followed by similar tests on other targets that provide bit-reverse
built-ins (such as ARM and xstormy16), in advance of support for a
backend-independent solution to PR middle-end/50481.


2023-06-02  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
        * wide-int.cc (wi::bitreverse_large): New function implementing
        bit reversal of an integer.
        * wide-int.h (wi::bitreverse): New (template) function prototype.
        (bitreverse_large): Prototype helper function/implementation.
        (wi::bitreverse): New template wrapper around bitreverse_large.


Thanks again,
Roger
--
  

Comments

Richard Sandiford June 5, 2023, 10:27 a.m. UTC | #1
"Roger Sayle" <roger@nextmovesoftware.com> writes:
> This patch provides a wide-int implementation of bitreverse, that
> implements both of Richard Sandiford's suggestions from the review at
> https://gcc.gnu.org/pipermail/gcc-patches/2023-May/618215.html of an
> improved API (as a stand-alone function matching the bswap refactoring),
> and an implementation that works with any bit-width precision.
>
> This patch has been tested on x86_64-pc-linux-gnu with make bootstrap
> (and a make check-gcc).  Ok for mainline?

OK, thanks.

> Are the remaining pieces
> of the above patch pre-approved (pending re-testing)?  The aim is that
> this new code will be thoroughly tested by the new *-2.c test cases in
> https://gcc.gnu.org/git/?p=gcc.git;h=c09471fbc7588db2480f036aa56a2403d3c03ae
> 5
> with a minor tweak to use the BITREVERSE rtx in the NVPTX back-end,
> followed by similar tests on other targets that provide bit-reverse
> built-ins (such as ARM and xstormy16), in advance of support for a
> backend-independent solution to PR middle-end/50481.

Ah, great.  Yeah, in that case, OK for the rest as well.

Richard
  

Patch

diff --git a/gcc/fold-const-call.cc b/gcc/fold-const-call.cc
index 340cb66..663eae2 100644
--- a/gcc/fold-const-call.cc
+++ b/gcc/fold-const-call.cc
@@ -1060,7 +1060,8 @@  fold_const_call_ss (wide_int *result, combined_fn fn, const wide_int_ref &arg,
     case CFN_BUILT_IN_BSWAP32:
     case CFN_BUILT_IN_BSWAP64:
     case CFN_BUILT_IN_BSWAP128:
-      *result = wide_int::from (arg, precision, TYPE_SIGN (arg_type)).bswap ();
+      *result = wi::bswap (wide_int::from (arg, precision,
+					   TYPE_SIGN (arg_type)));
       return true;
 
     default:
diff --git a/gcc/simplify-rtx.cc b/gcc/simplify-rtx.cc
index d4aeebc..d93d632 100644
--- a/gcc/simplify-rtx.cc
+++ b/gcc/simplify-rtx.cc
@@ -2111,7 +2111,7 @@  simplify_const_unary_operation (enum rtx_code code, machine_mode mode,
 	  break;
 
 	case BSWAP:
-	  result = wide_int (op0).bswap ();
+	  result = wi::bswap (op0);
 	  break;
 
 	case TRUNCATE:
diff --git a/gcc/tree-ssa-ccp.cc b/gcc/tree-ssa-ccp.cc
index 6fb371c..26d5e44 100644
--- a/gcc/tree-ssa-ccp.cc
+++ b/gcc/tree-ssa-ccp.cc
@@ -2401,11 +2401,12 @@  evaluate_stmt (gimple *stmt)
 		  wide_int wval = wi::to_wide (val.value);
 		  val.value
 		    = wide_int_to_tree (type,
-					wide_int::from (wval, prec,
-							UNSIGNED).bswap ());
+					wi::bswap (wide_int::from (wval, prec,
+								   UNSIGNED)));
 		  val.mask
-		    = widest_int::from (wide_int::from (val.mask, prec,
-							UNSIGNED).bswap (),
+		    = widest_int::from (wi::bswap (wide_int::from (val.mask,
+								   prec,
+								   UNSIGNED)),
 					UNSIGNED);
 		  if (wi::sext (val.mask, prec) != -1)
 		    break;
diff --git a/gcc/wide-int.cc b/gcc/wide-int.cc
index c0987aa..1e4c046 100644
--- a/gcc/wide-int.cc
+++ b/gcc/wide-int.cc
@@ -731,16 +731,13 @@  wi::set_bit_large (HOST_WIDE_INT *val, const HOST_WIDE_INT *xval,
     }
 }
 
-/* bswap THIS.  */
-wide_int
-wide_int_storage::bswap () const
+/* Byte swap the integer represented by XVAL and LEN into VAL.  Return
+   the number of blocks in VAL.  Both XVAL and VAL have PRECISION bits.  */
+unsigned int
+wi::bswap_large (HOST_WIDE_INT *val, const HOST_WIDE_INT *xval,
+	         unsigned int len, unsigned int precision)
 {
-  wide_int result = wide_int::create (precision);
   unsigned int i, s;
-  unsigned int len = BLOCKS_NEEDED (precision);
-  unsigned int xlen = get_len ();
-  const HOST_WIDE_INT *xval = get_val ();
-  HOST_WIDE_INT *val = result.write_val ();
 
   /* This is not a well defined operation if the precision is not a
      multiple of 8.  */
@@ -758,7 +755,7 @@  wide_int_storage::bswap () const
       unsigned int block = s / HOST_BITS_PER_WIDE_INT;
       unsigned int offset = s & (HOST_BITS_PER_WIDE_INT - 1);
 
-      byte = (safe_uhwi (xval, xlen, block) >> offset) & 0xff;
+      byte = (safe_uhwi (xval, len, block) >> offset) & 0xff;
 
       block = d / HOST_BITS_PER_WIDE_INT;
       offset = d & (HOST_BITS_PER_WIDE_INT - 1);
@@ -766,8 +763,7 @@  wide_int_storage::bswap () const
       val[block] |= byte << offset;
     }
 
-  result.set_len (canonize (val, len, precision));
-  return result;
+  return canonize (val, len, precision);
 }
 
 /* Fill VAL with a mask where the lower WIDTH bits are ones and the bits
diff --git a/gcc/wide-int.h b/gcc/wide-int.h
index 3d9b87c..a2b3371 100644
--- a/gcc/wide-int.h
+++ b/gcc/wide-int.h
@@ -552,6 +552,7 @@  namespace wi
   UNARY_FUNCTION sext (const T &, unsigned int);
   UNARY_FUNCTION zext (const T &, unsigned int);
   UNARY_FUNCTION set_bit (const T &, unsigned int);
+  UNARY_FUNCTION bswap (const T &);
 
   BINARY_FUNCTION min (const T1 &, const T2 &, signop);
   BINARY_FUNCTION smin (const T1 &, const T2 &);
@@ -1086,9 +1087,6 @@  public:
   static wide_int from_array (const HOST_WIDE_INT *, unsigned int,
 			      unsigned int, bool = true);
   static wide_int create (unsigned int);
-
-  /* FIXME: target-dependent, so should disappear.  */
-  wide_int bswap () const;
 };
 
 namespace wi
@@ -1743,13 +1741,14 @@  namespace wi
   int cmpu_large (const HOST_WIDE_INT *, unsigned int, unsigned int,
 		  const HOST_WIDE_INT *, unsigned int);
   unsigned int sext_large (HOST_WIDE_INT *, const HOST_WIDE_INT *,
-			   unsigned int,
-			   unsigned int, unsigned int);
+			   unsigned int, unsigned int, unsigned int);
   unsigned int zext_large (HOST_WIDE_INT *, const HOST_WIDE_INT *,
-			   unsigned int,
-			   unsigned int, unsigned int);
+			   unsigned int, unsigned int, unsigned int);
   unsigned int set_bit_large (HOST_WIDE_INT *, const HOST_WIDE_INT *,
 			      unsigned int, unsigned int, unsigned int);
+  unsigned int bswap_large (HOST_WIDE_INT *, const HOST_WIDE_INT *,
+			    unsigned int, unsigned int);
+  
   unsigned int lshift_large (HOST_WIDE_INT *, const HOST_WIDE_INT *,
 			     unsigned int, unsigned int, unsigned int);
   unsigned int lrshift_large (HOST_WIDE_INT *, const HOST_WIDE_INT *,
@@ -2267,6 +2266,18 @@  wi::set_bit (const T &x, unsigned int bit)
   return result;
 }
 
+/* Byte swap the integer X.  */
+template <typename T>
+inline WI_UNARY_RESULT (T)
+wi::bswap (const T &x)
+{
+  WI_UNARY_RESULT_VAR (result, val, T, x);
+  unsigned int precision = get_precision (result);
+  WIDE_INT_REF_FOR (T) xi (x, precision);
+  result.set_len (bswap_large (val, xi.val, xi.len, precision));
+  return result;
+}
+
 /* Return the mininum of X and Y, treating them both as having
    signedness SGN.  */
 template <typename T1, typename T2>