Make UnalignedCopy64 not exhibit undefined behavior when src and dst overlap.

name         old speed      new speed      delta
BM_UFlat/0   3.09GB/s ± 3%  3.07GB/s ± 2%  -0.78%  (p=0.009 n=19+19)
BM_UFlat/1   1.63GB/s ± 2%  1.62GB/s ± 2%    ~     (p=0.099 n=19+20)
BM_UFlat/2   19.7GB/s ±19%  20.7GB/s ±11%    ~     (p=0.054 n=20+19)
BM_UFlat/3   1.61GB/s ± 2%  1.60GB/s ± 1%  -0.48%  (p=0.049 n=20+17)
BM_UFlat/4   15.8GB/s ± 7%  15.6GB/s ±10%    ~     (p=0.234 n=20+20)
BM_UFlat/5   2.47GB/s ± 1%  2.46GB/s ± 2%    ~     (p=0.608 n=19+19)
BM_UFlat/6   1.07GB/s ± 2%  1.07GB/s ± 1%    ~     (p=0.128 n=20+19)
BM_UFlat/7   1.01GB/s ± 1%  1.00GB/s ± 2%    ~     (p=0.656 n=15+19)
BM_UFlat/8   1.13GB/s ± 1%  1.13GB/s ± 1%    ~     (p=0.532 n=18+19)
BM_UFlat/9    918MB/s ± 1%   916MB/s ± 1%    ~     (p=0.443 n=19+18)
BM_UFlat/10  3.90GB/s ± 1%  3.90GB/s ± 1%    ~     (p=0.895 n=20+19)
BM_UFlat/11  1.30GB/s ± 1%  1.29GB/s ± 2%    ~     (p=0.156 n=19+19)
BM_UFlat/12  2.35GB/s ± 2%  2.34GB/s ± 1%    ~     (p=0.349 n=19+17)
BM_UFlat/13  2.07GB/s ± 1%  2.06GB/s ± 2%    ~     (p=0.475 n=18+19)
BM_UFlat/14  2.23GB/s ± 1%  2.23GB/s ± 1%    ~     (p=0.983 n=19+19)
BM_UFlat/15  1.55GB/s ± 1%  1.55GB/s ± 1%    ~     (p=0.314 n=19+19)
BM_UFlat/16  1.26GB/s ± 1%  1.26GB/s ± 1%    ~     (p=0.907 n=15+18)
BM_UFlat/17  2.32GB/s ± 1%  2.32GB/s ± 1%    ~     (p=0.604 n=18+19)
BM_UFlat/18  1.61GB/s ± 1%  1.61GB/s ± 1%    ~     (p=0.212 n=18+19)
BM_UFlat/19  1.78GB/s ± 1%  1.78GB/s ± 2%    ~     (p=0.350 n=19+19)
BM_UFlat/20  1.89GB/s ± 1%  1.90GB/s ± 2%    ~     (p=0.092 n=19+19)

Also tested the current version against UNALIGNED_STORE64(dst, UNALIGNED_LOAD64(src)), there is no difference (old is memcpy, new is UNALIGNED*):

name         old speed      new speed      delta
BM_UFlat/0   3.14GB/s ± 1%  3.16GB/s ± 2%    ~     (p=0.156 n=19+19)
BM_UFlat/1   1.62GB/s ± 1%  1.61GB/s ± 2%    ~     (p=0.102 n=19+20)
BM_UFlat/2   18.8GB/s ±17%  19.1GB/s ±11%    ~     (p=0.390 n=20+16)
BM_UFlat/3   1.59GB/s ± 1%  1.58GB/s ± 1%  -1.06%  (p=0.000 n=18+18)
BM_UFlat/4   15.8GB/s ± 6%  15.6GB/s ± 7%    ~     (p=0.184 n=19+20)
BM_UFlat/5   2.46GB/s ± 1%  2.44GB/s ± 1%  -0.95%  (p=0.000 n=19+18)
BM_UFlat/6   1.08GB/s ± 1%  1.06GB/s ± 1%  -1.17%  (p=0.000 n=19+18)
BM_UFlat/7   1.00GB/s ± 1%  0.99GB/s ± 1%  -1.16%  (p=0.000 n=19+18)
BM_UFlat/8   1.14GB/s ± 2%  1.12GB/s ± 1%  -1.12%  (p=0.000 n=19+18)
BM_UFlat/9    921MB/s ± 1%   914MB/s ± 1%  -0.84%  (p=0.000 n=20+17)
BM_UFlat/10  3.94GB/s ± 2%  3.92GB/s ± 1%    ~     (p=0.058 n=19+17)
BM_UFlat/11  1.29GB/s ± 1%  1.28GB/s ± 1%  -0.77%  (p=0.001 n=19+17)
BM_UFlat/12  2.34GB/s ± 1%  2.31GB/s ± 1%  -1.10%  (p=0.000 n=18+18)
BM_UFlat/13  2.06GB/s ± 1%  2.05GB/s ± 1%  -0.73%  (p=0.001 n=19+18)
BM_UFlat/14  2.22GB/s ± 1%  2.20GB/s ± 1%  -0.73%  (p=0.000 n=18+18)
BM_UFlat/15  1.55GB/s ± 1%  1.53GB/s ± 1%  -1.07%  (p=0.000 n=19+18)
BM_UFlat/16  1.26GB/s ± 1%  1.25GB/s ± 1%  -0.79%  (p=0.000 n=18+18)
BM_UFlat/17  2.31GB/s ± 1%  2.29GB/s ± 1%  -0.98%  (p=0.000 n=20+18)
BM_UFlat/18  1.61GB/s ± 1%  1.60GB/s ± 2%  -0.71%  (p=0.001 n=20+19)
BM_UFlat/19  1.77GB/s ± 1%  1.76GB/s ± 1%  -0.61%  (p=0.007 n=19+18)
BM_UFlat/20  1.89GB/s ± 1%  1.88GB/s ± 1%  -0.75%  (p=0.000 n=20+18)

snappy.cc

@@ -89,7 +89,9 @@ size_t MaxCompressedLength(size_t source_len) {
 namespace {
 
 void UnalignedCopy64(const void* src, void* dst) {
-  memcpy(dst, src, 8);
+  char tmp[8];
+  memcpy(tmp, src, 8);
+  memcpy(dst, tmp, 8);
 }
 
 void UnalignedCopy128(const void* src, void* dst) {
@@ -99,7 +101,9 @@ void UnalignedCopy128(const void* src, void* dst) {
   __m128i x = _mm_loadu_si128(static_cast<const __m128i*>(src));
   _mm_storeu_si128(static_cast<__m128i*>(dst), x);
 #else
-  memcpy(dst, src, 16);
+  char tmp[16];
+  memcpy(tmp, src, 16);
+  memcpy(dst, tmp, 16);
 #endif
 }