Merge remote-tracking branch 'remotes/rth/tags/pull-tcg-20170110' into staging

TCG opcodes for extract, clz, ctz, ctpop

# gpg: Signature made Wed 11 Jan 2017 02:12:41 GMT
# gpg:                using RSA key 0xAD1270CC4DD0279B
# gpg: Good signature from "Richard Henderson <rth7680@gmail.com>"
# gpg:                 aka "Richard Henderson <rth@redhat.com>"
# gpg:                 aka "Richard Henderson <rth@twiddle.net>"
# Primary key fingerprint: 9CB1 8DDA F8E8 49AD 2AFC  16A4 AD12 70CC 4DD0 279B

* remotes/rth/tags/pull-tcg-20170110: (65 commits)
  tcg/i386: Handle ctpop opcode
  tcg/ppc: Handle ctpop opcode
  tcg: Use ctpop to generate ctz if needed
  tests: New test-bitcnt
  qemu/host-utils.h: Reduce the operation count in the fallback ctpop
  target-i386: Use ctpop helper
  target-tilegx: Use ctpop helper
  target-sparc: Use ctpop helper
  target-s390x: Avoid a loop for popcnt
  target-ppc: Use ctpop helper
  target-alpha: Use ctpop helper
  tcg: Add opcode for ctpop
  target-xtensa: Use clrsb helper
  target-tricore: Use clrsb helper
  target-arm: Use clrsb helper
  tcg: Add helpers for clrsb
  tcg/i386: Rely on undefined/undocumented behaviour of BSF/BSR
  tcg/i386: Handle ctz and clz opcodes
  tcg/i386: Allow bmi2 shiftx to have non-matching operands
  tcg/i386: Hoist common arguments in tcg_out_op
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 11 insertions, 14 deletions

diff --git a/include/qemu/host-utils.h b/include/qemu/host-utils.h
index 46187bbc7e..96288d0bce 100644
--- a/include/qemu/host-utils.h
+++ b/include/qemu/host-utils.h
@@ -327,7 +327,7 @@ static inline int ctpop8(uint8_t val)
 #else
     val = (val & 0x55) + ((val >> 1) & 0x55);
     val = (val & 0x33) + ((val >> 2) & 0x33);
-    val = (val & 0x0f) + ((val >> 4) & 0x0f);
+    val = (val + (val >> 4)) & 0x0f;
 
     return val;
 #endif
@@ -344,8 +344,8 @@ static inline int ctpop16(uint16_t val)
 #else
     val = (val & 0x5555) + ((val >> 1) & 0x5555);
     val = (val & 0x3333) + ((val >> 2) & 0x3333);
-    val = (val & 0x0f0f) + ((val >> 4) & 0x0f0f);
-    val = (val & 0x00ff) + ((val >> 8) & 0x00ff);
+    val = (val + (val >> 4)) & 0x0f0f;
+    val = (val + (val >> 8)) & 0x00ff;
 
     return val;
 #endif
@@ -360,11 +360,10 @@ static inline int ctpop32(uint32_t val)
 #if QEMU_GNUC_PREREQ(3, 4)
     return __builtin_popcount(val);
 #else
-    val = (val & 0x55555555) + ((val >>  1) & 0x55555555);
-    val = (val & 0x33333333) + ((val >>  2) & 0x33333333);
-    val = (val & 0x0f0f0f0f) + ((val >>  4) & 0x0f0f0f0f);
-    val = (val & 0x00ff00ff) + ((val >>  8) & 0x00ff00ff);
-    val = (val & 0x0000ffff) + ((val >> 16) & 0x0000ffff);
+    val = (val & 0x55555555) + ((val >> 1) & 0x55555555);
+    val = (val & 0x33333333) + ((val >> 2) & 0x33333333);
+    val = (val + (val >> 4)) & 0x0f0f0f0f;
+    val = (val * 0x01010101) >> 24;
 
     return val;
 #endif
@@ -379,12 +378,10 @@ static inline int ctpop64(uint64_t val)
 #if QEMU_GNUC_PREREQ(3, 4)
     return __builtin_popcountll(val);
 #else
-    val = (val & 0x5555555555555555ULL) + ((val >>  1) & 0x5555555555555555ULL);
-    val = (val & 0x3333333333333333ULL) + ((val >>  2) & 0x3333333333333333ULL);
-    val = (val & 0x0f0f0f0f0f0f0f0fULL) + ((val >>  4) & 0x0f0f0f0f0f0f0f0fULL);
-    val = (val & 0x00ff00ff00ff00ffULL) + ((val >>  8) & 0x00ff00ff00ff00ffULL);
-    val = (val & 0x0000ffff0000ffffULL) + ((val >> 16) & 0x0000ffff0000ffffULL);
-    val = (val & 0x00000000ffffffffULL) + ((val >> 32) & 0x00000000ffffffffULL);
+    val = (val & 0x5555555555555555ULL) + ((val >> 1) & 0x5555555555555555ULL);
+    val = (val & 0x3333333333333333ULL) + ((val >> 2) & 0x3333333333333333ULL);
+    val = (val + (val >> 4)) & 0x0f0f0f0f0f0f0f0fULL;
+    val = (val * 0x0101010101010101ULL) >> 56;
 
     return val;
 #endif