src/cpu/x86/vm/vm_version_x86_32.cpp

*** 240,252 ****
      }
    }
    _supports_cx8 = supports_cmpxchg8();
    // if the OS doesn't support SSE, we can't use this feature even if the HW does
    if( !os::supports_sse())
!     _cpuFeatures &= ~(CPU_SSE|CPU_SSE2|CPU_SSE3|CPU_SSSE3|CPU_SSE4|CPU_SSE4A);
    if (UseSSE < 4)
!     _cpuFeatures &= ~CPU_SSE4;
    if (UseSSE < 3) {
      _cpuFeatures &= ~CPU_SSE3;
      _cpuFeatures &= ~CPU_SSSE3;
      _cpuFeatures &= ~CPU_SSE4A;
    }
--- 240,253 ----
      }
    }
    _supports_cx8 = supports_cmpxchg8();
    // if the OS doesn't support SSE, we can't use this feature even if the HW does
    if( !os::supports_sse())
!     _cpuFeatures &= ~(CPU_SSE|CPU_SSE2|CPU_SSE3|CPU_SSSE3|CPU_SSE4A|CPU_SSE4_1|CPU_SSE4_2);
    if (UseSSE < 4)
!     _cpuFeatures &= ~CPU_SSE4_1;
!     _cpuFeatures &= ~CPU_SSE4_2;
    if (UseSSE < 3) {
      _cpuFeatures &= ~CPU_SSE3;
      _cpuFeatures &= ~CPU_SSSE3;
      _cpuFeatures &= ~CPU_SSE4A;
    }
*** 259,269 ****
      // HT processor could be installed on a system which doesn't support HT.
      _cpuFeatures &= ~CPU_HT;
    }
  
    char buf[256];
!   jio_snprintf(buf, sizeof(buf), "(%u cores per cpu, %u threads per core) family %d model %d stepping %d%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
                 cores_per_cpu(), threads_per_core(),
                 cpu_family(), _model, _stepping,
                 (supports_cmov() ? ", cmov" : ""),
                 (supports_cmpxchg8() ? ", cx8" : ""),
                 (supports_fxsr() ? ", fxsr" : ""),
--- 260,270 ----
      // HT processor could be installed on a system which doesn't support HT.
      _cpuFeatures &= ~CPU_HT;
    }
  
    char buf[256];
!   jio_snprintf(buf, sizeof(buf), "(%u cores per cpu, %u threads per core) family %d model %d stepping %d%s%s%s%s%s%s%s%s%s%s%s%s%s%s%s",
                 cores_per_cpu(), threads_per_core(),
                 cpu_family(), _model, _stepping,
                 (supports_cmov() ? ", cmov" : ""),
                 (supports_cmpxchg8() ? ", cx8" : ""),
                 (supports_fxsr() ? ", fxsr" : ""),
*** 270,280 ****
                 (supports_mmx()  ? ", mmx"  : ""),
                 (supports_sse()  ? ", sse"  : ""),
                 (supports_sse2() ? ", sse2" : ""),
                 (supports_sse3() ? ", sse3" : ""),
                 (supports_ssse3()? ", ssse3": ""),
!                (supports_sse4() ? ", sse4" : ""),
                 (supports_mmx_ext() ? ", mmxext" : ""),
                 (supports_3dnow()   ? ", 3dnow"  : ""),
                 (supports_3dnow2()  ? ", 3dnowext" : ""),
                 (supports_sse4a()   ? ", sse4a": ""),
                 (supports_ht() ? ", ht": ""));
--- 271,282 ----
                 (supports_mmx()  ? ", mmx"  : ""),
                 (supports_sse()  ? ", sse"  : ""),
                 (supports_sse2() ? ", sse2" : ""),
                 (supports_sse3() ? ", sse3" : ""),
                 (supports_ssse3()? ", ssse3": ""),
!                (supports_sse4_1() ? ", sse4.1" : ""),
!                (supports_sse4_2() ? ", sse4.2" : ""),
                 (supports_mmx_ext() ? ", mmxext" : ""),
                 (supports_3dnow()   ? ", 3dnow"  : ""),
                 (supports_3dnow2()  ? ", 3dnowext" : ""),
                 (supports_sse4a()   ? ", sse4a": ""),
                 (supports_ht() ? ", ht": ""));
*** 283,293 ****
    // UseSSE is set to the smaller of what hardware supports and what
    // the command line requires.  I.e., you cannot set UseSSE to 2 on
    // older Pentiums which do not support it.
    if( UseSSE > 4 ) UseSSE=4;
    if( UseSSE < 0 ) UseSSE=0;
!   if( !supports_sse4() ) // Drop to 3 if no SSE4 support
      UseSSE = MIN2((intx)3,UseSSE);
    if( !supports_sse3() ) // Drop to 2 if no SSE3 support
      UseSSE = MIN2((intx)2,UseSSE);
    if( !supports_sse2() ) // Drop to 1 if no SSE2 support
      UseSSE = MIN2((intx)1,UseSSE);
--- 285,295 ----
    // UseSSE is set to the smaller of what hardware supports and what
    // the command line requires.  I.e., you cannot set UseSSE to 2 on
    // older Pentiums which do not support it.
    if( UseSSE > 4 ) UseSSE=4;
    if( UseSSE < 0 ) UseSSE=0;
!   if( !supports_sse4_1() ) // Drop to 3 if no SSE4 support
      UseSSE = MIN2((intx)3,UseSSE);
    if( !supports_sse3() ) // Drop to 2 if no SSE3 support
      UseSSE = MIN2((intx)2,UseSSE);
    if( !supports_sse2() ) // Drop to 1 if no SSE2 support
      UseSSE = MIN2((intx)1,UseSSE);
*** 373,384 ****
--- 375,394 ----
          // generated NOP instructions. 11 is the largest size of one
          // address NOP instruction '0F 1F' (see Assembler::nop(i)).
          MaxLoopPad = 11;
        }
  #endif // COMPILER2
+       if( FLAG_IS_DEFAULT(UseXMMForArrayCopy) ) {
+         UseXMMForArrayCopy = true; // use SSE2 movq on new Intel cpus
        }
+       if( supports_sse4_1() && supports_ht() ) { // Newest Intel cpus
+         if( FLAG_IS_DEFAULT(UseUnalignedLoadStores) && UseXMMForArrayCopy ) {
+           UseUnalignedLoadStores = true; // use movdqu on newest Intel cpus
          }
+       }
+     }
+   }
  
    assert(0 <= ReadPrefetchInstr && ReadPrefetchInstr <= 3, "invalid value");
    assert(0 <= AllocatePrefetchInstr && AllocatePrefetchInstr <= 3, "invalid value");
  
    // set valid Prefetch instruction
*** 411,421 ****
    }
    assert(AllocatePrefetchDistance % AllocatePrefetchStepSize == 0, "invalid value");
  
  #ifndef PRODUCT
    if (PrintMiscellaneous && Verbose) {
!     tty->print_cr("Logical CPUs per package: %u",
                    logical_processors_per_package());
      tty->print_cr("UseSSE=%d",UseSSE);
      tty->print("Allocation: ");
      if (AllocatePrefetchStyle <= 0 || UseSSE == 0 && !supports_3dnow()) {
        tty->print_cr("no prefetching");
--- 421,431 ----
    }
    assert(AllocatePrefetchDistance % AllocatePrefetchStepSize == 0, "invalid value");
  
  #ifndef PRODUCT
    if (PrintMiscellaneous && Verbose) {
!     tty->print_cr("Logical CPUs per core: %u",
                    logical_processors_per_package());
      tty->print_cr("UseSSE=%d",UseSSE);
      tty->print("Allocation: ");
      if (AllocatePrefetchStyle <= 0 || UseSSE == 0 && !supports_3dnow()) {
        tty->print_cr("no prefetching");