Start SSE2 implementation based on SSE4.1 version

Wire up basic functions and features for SSE2 support using the SSE4.1 version
as a basis without implementing the SSE2 instructions yet.

 * Cargo.toml: add no_sse2 feature
 * benches/bench.rs: wire SSE2 benchmarks
 * build.rs: add SSE2 rust intrinsics and assembly builds
 * c/Makefile.testing: add SSE2 C and assembly targets
 * c/README.md: add SSE2 to C build instructions
 * c/blake3_c_rust_bindings/build.rs: add SSE2 C rust binding builds
 * c/blake3_c_rust_bindings/src/lib.rs: add SSE2 C rust bindings
 * c/blake3_dispatch.c: add SSE2 C dispatch
 * c/blake3_impl.h: add SSE2 C function prototypes
 * c/blake3_sse2.c: add SSE2 C intrinsic file starting with SSE4.1 version
 * c/blake3_sse2_x86-64_{unix.S,windows_gnu.S,windows_msvc.asm}: add SSE2
   assembly files starting with SSE4.1 version
 * src/ffi_sse2.rs: add rust implementation using SSE2 C rust bindings
 * src/lib.rs: add SSE2 rust intrinsics and SSE2 C rust binding rust SSE2 module
   configurations
 * src/platform.rs: add SSE2 rust platform detection and dispatch
 * src/rust_sse2.rs: add SSE2 rust intrinsic file starting with SSE4.1 version
 * tools/instruction_set_support/src/main.rs: add SSE2 feature detection

1 files changed, 15 insertions, 0 deletions

diff --git a/c/blake3_impl.h b/c/blake3_impl.h
index c384671..b4a38c7 100644
--- a/c/blake3_impl.h
+++ b/c/blake3_impl.h
@@ -182,6 +182,21 @@ void blake3_hash_many_portable(const uint8_t *const *inputs, size_t num_inputs,
                                uint8_t flags_end, uint8_t *out);
 
 #if defined(IS_X86)
+#if !defined(BLAKE3_NO_SSE2)
+void blake3_compress_in_place_sse2(uint32_t cv[8],
+                                   const uint8_t block[BLAKE3_BLOCK_LEN],
+                                   uint8_t block_len, uint64_t counter,
+                                   uint8_t flags);
+void blake3_compress_xof_sse2(const uint32_t cv[8],
+                              const uint8_t block[BLAKE3_BLOCK_LEN],
+                              uint8_t block_len, uint64_t counter,
+                              uint8_t flags, uint8_t out[64]);
+void blake3_hash_many_sse2(const uint8_t *const *inputs, size_t num_inputs,
+                           size_t blocks, const uint32_t key[8],
+                           uint64_t counter, bool increment_counter,
+                           uint8_t flags, uint8_t flags_start,
+                           uint8_t flags_end, uint8_t *out);
+#endif
 #if !defined(BLAKE3_NO_SSE41)
 void blake3_compress_in_place_sse41(uint32_t cv[8],
                                     const uint8_t block[BLAKE3_BLOCK_LEN],