Add BLAKE2s and ChaCha CORE SIMD function (GH #656)

The CORE function provides the implementation for ChaCha_OperateKeystream_ALTIVEC, ChaCha_OperateKeystream_POWER7, BLAKE2_Compress32_ALTIVEC and BLAKE2_Compress32_POWER7. Depending on the options used to compile the source files, either POWER7 or ALTIVEC will be used.
This is needed to support the "new toolchain, ancient hardware" use case.

1 files changed, 19 insertions, 3 deletions

diff --git a/blake2s_simd.cpp b/blake2s_simd.cpp
index 1456ad23..1d756f9e 100644
--- a/blake2s_simd.cpp
+++ b/blake2s_simd.cpp
@@ -681,7 +681,7 @@ void BLAKE2_Compress32_NEON(const byte* input, BLAKE2s_State& state)
 }

 #endif  // CRYPTOPP_ARM_NEON_AVAILABLE

 

-#if (CRYPTOPP_ALTIVEC_AVAILABLE)

+#if (CRYPTOPP_POWER7_AVAILABLE || CRYPTOPP_ALTIVEC_AVAILABLE)

 

 inline uint32x4_p VecLoad32(const void* p)

 {

@@ -847,7 +847,7 @@ uint32x4_p VectorSet32<3,1,3,1>(const uint32x4_p a, const uint32x4_p b,
     return VecPermute(a, c, mask);

 }

 

-void BLAKE2_Compress32_POWER7(const byte* input, BLAKE2s_State& state)

+void BLAKE2_Compress32_CORE(const byte* input, BLAKE2s_State& state)

 {

     # define m1 m0

     # define m2 m0

@@ -994,6 +994,22 @@ void BLAKE2_Compress32_POWER7(const byte* input, BLAKE2s_State& state)
     VecStore32LE(&state.h[0], VecXor(ff0, VecXor(row1, row3)));

     VecStore32LE(&state.h[4], VecXor(ff1, VecXor(row2, row4)));

 }

-#endif  // CRYPTOPP_ALTIVEC_AVAILABLE

+#endif  // CRYPTOPP_POWER7_AVAILABLE || CRYPTOPP_ALTIVEC_AVAILABLE

+

+#if (CRYPTOPP_POWER7_AVAILABLE)

+

+void BLAKE2_Compress32_POWER7(const byte* input, BLAKE2s_State& state)

+{

+	BLAKE2_Compress32_CORE(input, state);

+}

+

+#elif (CRYPTOPP_ALTIVEC_AVAILABLE)

+

+void BLAKE2_Compress32_ALTIVEC(const byte* input, BLAKE2s_State& state)

+{

+	BLAKE2_Compress32_CORE(input, state);

+}

+

+#endif

 

 NAMESPACE_END