X-Git-Url: https://git.libre-soc.org/?a=blobdiff_plain;f=libcpp%2Flex.c;h=9d23002d84be19b2a19ff83a246cbbde5c0880af;hb=63737e7a0c43a6f78c3ed5f1960a991e3c6bb72a;hp=fcec329d8b4970a67de3271e2476c2d8f700a2db;hpb=3ce4f9e4d2643273f11647e97b2c7796a64a73dd;p=gcc.git

diff --git a/libcpp/lex.c b/libcpp/lex.c
index fcec329d8b4..9d23002d84b 100644
--- a/libcpp/lex.c
+++ b/libcpp/lex.c
@@ -1,6 +1,6 @@
 /* CPP Library - lexical analysis.
    Copyright (C) 2000, 2001, 2002, 2003, 2004, 2005, 2007, 2008, 2009, 2010,
-   2011 Free Software Foundation, Inc.
+   2011, 2012 Free Software Foundation, Inc.
    Contributed by Per Bothner, 1994-95.
    Based on CCCP program by Paul Rubin, June 1986
    Adapted to ANSI C, Richard Stallman, Jan 1987
@@ -267,7 +267,6 @@ search_line_acc_char (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
 /* Disable on Solaris 2/x86 until the following problems can be properly
    autoconfed:
 
-   The Solaris 8 assembler cannot assemble SSE2/SSE4.2 insns.
    The Solaris 9 assembler cannot assemble SSE4.2 insns.
    Before Solaris 9 Update 6, SSE insns cannot be executed.
    The Solaris 10+ assembler tags objects with the instruction set
@@ -477,7 +476,8 @@ search_line_sse42 (const uchar *s, const uchar *end)
 typedef const uchar * (*search_line_fast_type) (const uchar *, const uchar *);
 static search_line_fast_type search_line_fast;
 
-static void __attribute__((constructor))
+#define HAVE_init_vectorized_lexer 1
+static inline void
 init_vectorized_lexer (void)
 {
   unsigned dummy, ecx = 0, edx = 0;
@@ -629,6 +629,69 @@ search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
   }
 }
 
+#elif defined (__ARM_NEON__)
+#include "arm_neon.h"
+
+static const uchar *
+search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
+{
+  const uint8x16_t repl_nl = vdupq_n_u8 ('\n');
+  const uint8x16_t repl_cr = vdupq_n_u8 ('\r');
+  const uint8x16_t repl_bs = vdupq_n_u8 ('\\');
+  const uint8x16_t repl_qm = vdupq_n_u8 ('?');
+  const uint8x16_t xmask = (uint8x16_t) vdupq_n_u64 (0x8040201008040201ULL);
+
+  unsigned int misalign, found, mask;
+  const uint8_t *p;
+  uint8x16_t data;
+
+  /* Align the source pointer.  */
+  misalign = (uintptr_t)s & 15;
+  p = (const uint8_t *)((uintptr_t)s & -16);
+  data = vld1q_u8 (p);
+
+  /* Create a mask for the bytes that are valid within the first
+     16-byte block.  The Idea here is that the AND with the mask
+     within the loop is "free", since we need some AND or TEST
+     insn in order to set the flags for the branch anyway.  */
+  mask = (-1u << misalign) & 0xffff;
+
+  /* Main loop, processing 16 bytes at a time.  */
+  goto start;
+
+  do
+    {
+      uint8x8_t l;
+      uint16x4_t m;
+      uint32x2_t n;
+      uint8x16_t t, u, v, w;
+
+      p += 16;
+      data = vld1q_u8 (p);
+      mask = 0xffff;
+
+    start:
+      t = vceqq_u8 (data, repl_nl);
+      u = vceqq_u8 (data, repl_cr);
+      v = vorrq_u8 (t, vceqq_u8 (data, repl_bs));
+      w = vorrq_u8 (u, vceqq_u8 (data, repl_qm));
+      t = vandq_u8 (vorrq_u8 (v, w), xmask);
+      l = vpadd_u8 (vget_low_u8 (t), vget_high_u8 (t));
+      m = vpaddl_u8 (l);
+      n = vpaddl_u16 (m);
+      
+      found = vget_lane_u32 ((uint32x2_t) vorr_u64 ((uint64x1_t) n, 
+	      vshr_n_u64 ((uint64x1_t) n, 24)), 0);
+      found &= mask;
+    }
+  while (!found);
+
+  /* FOUND contains 1 in bits for which we matched a relevant
+     character.  Conversion to the byte index is trivial.  */
+  found = __builtin_ctz (found);
+  return (const uchar *)p + found;
+}
+
 #else
 
 /* We only have one accellerated alternative.  Use a direct call so that
@@ -638,6 +701,16 @@ search_line_fast (const uchar *s, const uchar *end ATTRIBUTE_UNUSED)
 
 #endif
 
+/* Initialize the lexer if needed.  */
+
+void
+_cpp_init_lexer (void)
+{
+#ifdef HAVE_init_vectorized_lexer
+  init_vectorized_lexer ();
+#endif
+}
+
 /* Returns with a logical line that contains no escaped newlines or
    trigraphs.  This is a time-critical inner loop.  */
 void