BaseMemoryLibSse2: Take advantage of write combining buffers

The current SSE2 implementation of the ZeroMem(), SetMem(),
SetMem16(), SetMem32 and SetMem64 functions is writing 16 bytes per 16
bytes. It hurts the performances so bad that this is even slower than
a simple 'rep stos' (4% slower) in regular DRAM.

To take full advantages of the 'movntdq' instruction it is better to
"queue" a total of 64 bytes in the write combining buffers.  This
patch implement such a change.  Below is a table where I measured
(with 'rdtsc') the time to write an entire 100MB RAM buffer. These
functions operate almost two times faster.

| Function | Arch | Untouched | 64 bytes | Result |
|----------+------+-----------+----------+--------|
| ZeroMem  | Ia32 |  17765947 |  9136062 | 1.945x |
| ZeroMem  | X64  |  17525170 |  9233391 | 1.898x |
| SetMem   | Ia32 |  17522291 |  9137272 | 1.918x |
| SetMem   | X64  |  17949261 |  9176978 | 1.956x |
| SetMem16 | Ia32 |  18219673 |  9372062 | 1.944x |
| SetMem16 | X64  |  17523331 |  9275184 | 1.889x |
| SetMem32 | Ia32 |  18495036 |  9273053 | 1.994x |
| SetMem32 | X64  |  17368864 |  9285885 | 1.870x |
| SetMem64 | Ia32 |  18564473 |  9241362 | 2.009x |
| SetMem64 | X64  |  17506951 |  9280148 | 1.886x |

Signed-off-by: Jeremy Compostella <jeremy.compostella@intel.com>
Reviewed-by: Liming Gao <gaoliming@byosoft.com.cn>

MdePkg/Library/BaseMemoryLibSse2/X64/SetMem.nasm

@@ -42,8 +42,8 @@ ASM_PFX(InternalMemSetMem):
     rep     stosb
 .0:
     mov     rcx, rdx
-    and     rdx, 15
-    shr     rcx, 4
+    and     rdx, 63
+    shr     rcx, 6
     jz      @SetBytes
     mov     ah, al                      ; ax <- Value repeats twice
     movdqa  [rsp + 0x10], xmm0           ; save xmm0
@@ -52,7 +52,10 @@ ASM_PFX(InternalMemSetMem):
     movlhps xmm0, xmm0                  ; xmm0 <- Value repeats 16 times
 .1:
     movntdq [rdi], xmm0                 ; rdi should be 16-byte aligned
-    add     rdi, 16
+    movntdq [rdi + 16], xmm0
+    movntdq [rdi + 32], xmm0
+    movntdq [rdi + 48], xmm0
+    add     rdi, 64
     loop    .1
     mfence
     movdqa  xmm0, [rsp + 0x10]           ; restore xmm0