Index: ioemu/hw/vga.c
===================================================================
--- ioemu.orig/hw/vga.c	2007-05-02 10:32:35.000000000 +0100
+++ ioemu/hw/vga.c	2007-05-02 10:35:05.000000000 +0100
@@ -1359,6 +1359,105 @@
     }
 }
 
+static inline int cmp_vram(VGAState *s, int offset, int n)
+{
+    long *vp, *sp;
+
+    if (s->vram_shadow == NULL)
+        return 1;
+    vp = (long *)(s->vram_ptr + offset);
+    sp = (long *)(s->vram_shadow + offset);
+    while ((n -= sizeof(*vp)) >= 0) {
+        if (*vp++ != *sp++) {
+            memcpy(sp - 1, vp - 1, n + sizeof(*vp));
+            return 1;
+        }
+    }
+    return 0;
+}
+
+#ifdef USE_SSE2
+
+#include <signal.h>
+#include <setjmp.h>
+#include <emmintrin.h>
+
+int sse2_ok = 1;
+
+static inline unsigned int cpuid_edx(unsigned int op)
+{
+    unsigned int eax, edx;
+
+#ifdef __x86_64__
+#define __bx "rbx"
+#else
+#define __bx "ebx"
+#endif
+    __asm__("push %%"__bx"; cpuid; pop %%"__bx
+            : "=a" (eax), "=d" (edx)
+            : "0" (op)
+            : "cx");
+#undef __bx
+
+    return edx;
+}
+
+jmp_buf sse_jbuf;
+
+void intr(int sig)
+{
+    sse2_ok = 0;
+    longjmp(sse_jbuf, 1);
+}
+
+void check_sse2(void)
+{
+    /* Check 1: What does CPUID say? */
+    if ((cpuid_edx(1) & 0x4000000) == 0) {
+        sse2_ok = 0;
+        return;
+    }
+
+    /* Check 2: Can we use SSE2 in anger? */
+    signal(SIGILL, intr);
+    if (setjmp(sse_jbuf) == 0)
+        __asm__("xorps %xmm0,%xmm0\n");
+}
+
+int vram_dirty(VGAState *s, int offset, int n)
+{
+    __m128i *sp, *vp;
+
+    if (s->vram_shadow == NULL)
+        return 1;
+    if (sse2_ok == 0)
+        return cmp_vram(s, offset, n);
+    vp = (__m128i *)(s->vram_ptr + offset);
+    sp = (__m128i *)(s->vram_shadow + offset);
+    while ((n -= sizeof(*vp)) >= 0) {
+        if (_mm_movemask_epi8(_mm_cmpeq_epi8(*sp, *vp)) != 0xffff) {
+            while (n >= 0) {
+                _mm_store_si128(sp++, _mm_load_si128(vp++));
+                n -= sizeof(*vp);
+            }
+            return 1;
+        }
+        sp++;
+        vp++;
+    }
+    return 0;
+}
+#else /* !USE_SSE2 */
+int vram_dirty(VGAState *s, int offset, int n)
+{
+    return cmp_vram(s, offset, n);
+}
+
+void check_sse2(void)
+{
+}
+#endif /* !USE_SSE2 */
+
 /* 
  * graphic modes
  */
@@ -1454,6 +1553,11 @@
     printf("w=%d h=%d v=%d line_offset=%d cr[0x09]=0x%02x cr[0x17]=0x%02x linecmp=%d sr[0x01]=0x%02x\n",
            width, height, v, line_offset, s->cr[9], s->cr[0x17], s->line_compare, s->sr[0x01]);
 #endif
+
+    for (y = 0; y < s->vram_size; y += TARGET_PAGE_SIZE)
+        if (vram_dirty(s, y, TARGET_PAGE_SIZE))
+            cpu_physical_memory_set_dirty(s->vram_offset + y);
+
     addr1 = (s->start_addr * 4);
     bwidth = width * 4;
     y_start = -1;
@@ -1889,7 +1993,18 @@
 
     vga_reset(s);
 
-    s->vram_ptr = qemu_malloc(vga_ram_size);
+    check_sse2();
+    s->vram_shadow = qemu_malloc(vga_ram_size+TARGET_PAGE_SIZE+1);
+    if (s->vram_shadow == NULL)
+        fprintf(stderr, "Cannot allocate %d bytes for VRAM shadow, "
+                "mouse will be slow\n", vga_ram_size);
+    s->vram_shadow = (uint8_t *)((long)(s->vram_shadow + TARGET_PAGE_SIZE - 1)
+                                 & ~(TARGET_PAGE_SIZE - 1));
+
+    /* Video RAM must be 128-bit aligned for SSE optimizations later */
+    s->vram_alloc = qemu_malloc(vga_ram_size + 15);
+    s->vram_ptr = (uint8_t *)((long)(s->vram_alloc + 15) & ~15L);
+
     s->vram_offset = vga_ram_offset;
     s->vram_size = vga_ram_size;
     s->ds = ds;
@@ -2013,7 +2128,7 @@
     }
 
     if (!vga_ram_base) {
-        vga_ram_base = qemu_malloc(vga_ram_size);
+        vga_ram_base = qemu_malloc(vga_ram_size + TARGET_PAGE_SIZE + 1);
         if (!vga_ram_base) {
             fprintf(stderr, "reallocate error\n");
             return NULL;
@@ -2021,8 +2136,10 @@
     }
 
     /* XXX lock needed? */
+    old_pointer = s->vram_alloc;
+    s->vram_alloc = vga_ram_base;
+    vga_ram_base = (uint8_t *)((long)(vga_ram_base + 15) & ~15L);
     memcpy(vga_ram_base, s->vram_ptr, vga_ram_size);
-    old_pointer = s->vram_ptr;
     s->vram_ptr = vga_ram_base;
 
     return old_pointer;
Index: ioemu/hw/vga_int.h
===================================================================
--- ioemu.orig/hw/vga_int.h	2007-05-02 10:32:35.000000000 +0100
+++ ioemu/hw/vga_int.h	2007-05-02 10:35:10.000000000 +0100
@@ -78,7 +78,9 @@
 #define VGA_MAX_HEIGHT 2048
 
 #define VGA_STATE_COMMON                                                \
+    uint8_t *vram_alloc;                                                \
     uint8_t *vram_ptr;                                                  \
+    uint8_t *vram_shadow;                                               \
     unsigned long vram_offset;                                          \
     unsigned int vram_size;                                             \
     unsigned long bios_offset;                                          \