X-Git-Url: http://git.rrze.uni-erlangen.de/gitweb/?p=LbmBenchmarkKernelsPublic.git;a=blobdiff_plain;f=src%2FVector.h;fp=src%2FVector.h;h=41b9a7984f6e31c704f1089797bcb1c616e5b1a1;hp=0000000000000000000000000000000000000000;hb=109880839321408644c94a34eb31208460b9f46d;hpb=42cf91486fb5c1ad178b3d21935a1be563e5fa39
diff --git a/src/Vector.h b/src/Vector.h
new file mode 100644
index 0000000..41b9a79
--- /dev/null
+++ b/src/Vector.h
@@ -0,0 +1,83 @@
+// --------------------------------------------------------------------------
+//
+// Copyright
+// Markus Wittmann, 2016-2017
+// RRZE, University of Erlangen-Nuremberg, Germany
+// markus.wittmann -at- fau.de or hpc -at- rrze.fau.de
+//
+// Viktor Haag, 2016
+// LSS, University of Erlangen-Nuremberg, Germany
+//
+// This file is part of the Lattice Boltzmann Benchmark Kernels (LbmBenchKernels).
+//
+// LbmBenchKernels is free software: you can redistribute it and/or modify
+// it under the terms of the GNU General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// LbmBenchKernels is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU General Public License for more details.
+//
+// You should have received a copy of the GNU General Public License
+// along with LbmBenchKernels. If not, see .
+//
+// --------------------------------------------------------------------------
+#ifndef __VECTOR_H__
+#define __VECTOR_H__
+
+#if !defined(VECTOR_AVX) && !defined(VECTOR_SSE)
+ #warning Defining VECTOR_AVX as no ISA extension was selected.
+ #define VECTOR_AVX
+#endif
+
+#if defined(VECTOR_AVX) && defined(VECTOR_SSE)
+ #error Only VECTOR_AVX or VECTOR_SSE can be defined at the same time.
+#endif
+
+#ifdef VECTOR_AVX
+
+ #include
+ // Vector size in double-precision floatin-point numbers.
+ #define VSIZE 4
+
+ #define VPDFT __m256d
+
+ #define VSET(scalar) _mm256_set1_pd(scalar)
+
+ #define VLD(expr) _mm256_load_pd(expr)
+ #define VLDU(expr) _mm256_loadu_pd(expr)
+
+ #define VST(dst, src) _mm256_store_pd(dst, src)
+ #define VSTU(dst, src) _mm256_storeu_pd(dst, src)
+ #define VSTNT(dst, src) _mm256_stream_pd(dst, src)
+
+ #define VMUL(a, b) _mm256_mul_pd(a, b)
+ #define VADD(a, b) _mm256_add_pd(a, b)
+ #define VSUB(a, b) _mm256_sub_pd(a, b)
+#endif
+
+#ifdef VECTOR_SSE
+ #include
+ // Vector size in double-precision floatin-point numbers.
+ #define VSIZE 2
+
+ #define VPDFT __m128d
+
+ #define VSET(scalar) _mm_set1_pd(scalar)
+
+ #define VLD(expr) _mm_load_pd(expr)
+ #define VLDU(expr) _mm_loadu_pd(expr)
+
+ #define VST(dst, src) _mm_store_pd(dst, src)
+ #define VSTU(dst, src) _mm_storeu_pd(dst, src)
+ #define VSTNT(dst, src) _mm_stream_pd(dst, src)
+
+ #define VMUL(a, b) _mm_mul_pd(a, b)
+ #define VADD(a, b) _mm_add_pd(a, b)
+ #define VSUB(a, b) _mm_sub_pd(a, b)
+#endif
+
+
+#endif // __VECTOR_H__