Re: Performance patch for jdk1.5.0/amd64

[Huang wen hui <hwh@xxxxxxxxxxxx>]

Michael Vince wrote:

> Hi,
> Do you have this as an attached file? I tried to use this patch but it 
> appears to be mangled.
>
> Regards,
> Mike
check this.

--- ../../hotspot/src/cpu/amd64/vm/amd64.ad.orig	Sat Jan 14 20:06:02 2006
+++ ../../hotspot/src/cpu/amd64/vm/amd64.ad	Sat Jan 14 20:05:37 2006
@@ -6095,6 +6095,18 @@
   ins_pipe(pipe_slow); // XXX
 %}
 
+instruct prefetcht0(memory mem)
+%{
+  match(Prefetch mem);
+  predicate(!VM_Version::has_prefetchw());
+  ins_cost(125);
+
+  format %{ "prefetcht0 $mem\t# prefetch into L1" %}
+  opcode(0x0F, 0x18); /* Opcode 0F 18 /1 */
+  ins_encode(REX_mem(mem), OpcP, OpcS, RM_opc_mem(0x01, mem));
+  ins_pipe(pipe_slow);
+%}
+
 instruct prefetch(memory mem)
 %{
   match(Prefetch mem);

--- ../../hotspot/src/os_cpu/bsd_amd64/vm/prefetch_bsd_amd64.inline.hpp.orig	Sat Jan 14 23:51:41 2006
+++ ../../hotspot/src/os_cpu/bsd_amd64/vm/prefetch_bsd_amd64.inline.hpp	Sat Jan 14 23:52:54 2006
@@ -6,24 +6,14 @@
  * SUN PROPRIETARY/CONFIDENTIAL.  Use is subject to license terms.
  */
 
-inline void Prefetch::read(void* loc, intx interval) 
+inline void Prefetch::read(void* loc, intx interval)
 {
-  __builtin_prefetch((char*) loc + interval, 0); // prefetcht0 (%rsi, %rdi,1)
+  __asm__ ("prefetcht0 (%0,%1,1)" : : "r" (loc), "r" (interval));
 }
 
 inline void Prefetch::write(void* loc, intx interval)
 {
-  // Force prefetchw.  The gcc builtin produces prefetcht0 or prefetchw
-  // depending on command line switches we don't control here.
-  // Use of this method should be gated by VM_Version::has_prefetchw.
-  /*
-   * How do we invoke VM_Version::has_prefetchw here?
-   * Can we do something at compile time instead to remove that overhead?
-   */
-//#ifdef __amd64__
-//  __asm__ ("prefetchw (%0,%1,1)" : : "r" (loc), "r" (interval));
-//#elif __em64t__
+  // Do not use the 3dnow prefetchw instruction.  It isn't supported on em64t.
+  //  __asm__ ("prefetchw (%0,%1,1)" : : "r" (loc), "r" (interval));
   __asm__ ("prefetcht0 (%0,%1,1)" : : "r" (loc), "r" (interval));
-//#endif
-  //  __builtin_prefetch((char*) loc + interval, 1); // prefetcht0/prefetchw (%rsi,%rdi,1)
 }