Adds a fast memcpy function to Eigen. This takes advantage of the following:

1. For small fixed sizes, the compiler generates inline code for memcpy, which is much faster.

2. My colleague eriche at googl dot com discovered that for large sizes, memmove is significantly faster than memcpy (at least on Linux with GCC or Clang). See benchmark numbers measured on a Haswell (HP Z440) workstation here: https://docs.google.com/a/google.com/spreadsheets/d/1jLs5bKzXwhpTySw65MhG1pZpsIwkszZqQTjwrd_n0ic/pubhtml This is of course surprising since memcpy is a less constrained version of memmove. This stackoverflow thread contains some speculation as to the causes: http://stackoverflow.com/questions/22793669/poor-memcpy-performance-on-linux

Below are numbers for copying and slicing tensors using the multithreaded TensorDevice. The numbers show significant improvements for memcpy of very small blocks and for memcpy of large blocks single threaded (we were already able to saturate memory bandwidth for >1 threads before on large blocks). The "slicingSmallPieces" benchmark also shows small consistent improvements, since memcpy cost is a fair portion of that particular computation.

The benchmarks operate on NxN matrices, and the names are of the form BM_$OP_${NUMTHREADS}T/${N}.

Measured improvements in wall clock time:

Run on rmlarsen3.mtv (12 X 3501 MHz CPUs); 2017-01-20T11:26:31.493023454-08:00
CPU: Intel Haswell with HyperThreading (6 cores) dL1:32KB dL2:256KB dL3:15MB
Benchmark                          Base (ns)  New (ns) Improvement
------------------------------------------------------------------
BM_memcpy_1T/2                          3.48      2.39    +31.3%
BM_memcpy_1T/8                          12.3      6.51    +47.0%
BM_memcpy_1T/64                          371       383     -3.2%
BM_memcpy_1T/512                       66922     66720     +0.3%
BM_memcpy_1T/4k                      9892867   6849682    +30.8%
BM_memcpy_1T/5k                     14951099  10332856    +30.9%
BM_memcpy_2T/2                          3.50      2.46    +29.7%
BM_memcpy_2T/8                          12.3      7.66    +37.7%
BM_memcpy_2T/64                          371       376     -1.3%
BM_memcpy_2T/512                       66652     66788     -0.2%
BM_memcpy_2T/4k                      6145012   6117776     +0.4%
BM_memcpy_2T/5k                      9181478   9010942     +1.9%
BM_memcpy_4T/2                          3.47      2.47    +31.0%
BM_memcpy_4T/8                          12.3      6.67    +45.8
BM_memcpy_4T/64                          374       376     -0.5%
BM_memcpy_4T/512                       67833     68019     -0.3%
BM_memcpy_4T/4k                      5057425   5188253     -2.6%
BM_memcpy_4T/5k                      7555638   7779468     -3.0%
BM_memcpy_6T/2                          3.51      2.50    +28.8%
BM_memcpy_6T/8                          12.3      7.61    +38.1%
BM_memcpy_6T/64                          373       378     -1.3%
BM_memcpy_6T/512                       66871     66774     +0.1%
BM_memcpy_6T/4k                      5112975   5233502     -2.4%
BM_memcpy_6T/5k                      7614180   7772246     -2.1%
BM_memcpy_8T/2                          3.47      2.41    +30.5%
BM_memcpy_8T/8                          12.4      10.5    +15.3%
BM_memcpy_8T/64                          372       388     -4.3%
BM_memcpy_8T/512                       67373     66588     +1.2%
BM_memcpy_8T/4k                      5148462   5254897     -2.1%
BM_memcpy_8T/5k                      7660989   7799058     -1.8%
BM_memcpy_12T/2                         3.50      2.40    +31.4%
BM_memcpy_12T/8                         12.4      7.55    +39.1
BM_memcpy_12T/64                         374       378     -1.1%
BM_memcpy_12T/512                      67132     66683     +0.7%
BM_memcpy_12T/4k                     5185125   5292920     -2.1%
BM_memcpy_12T/5k                     7717284   7942684     -2.9%
BM_slicingSmallPieces_1T/2              47.3      47.5     +0.4%
BM_slicingSmallPieces_1T/8              53.6      52.3     +2.4%
BM_slicingSmallPieces_1T/64              491       476     +3.1%
BM_slicingSmallPieces_1T/512           21734     18814    +13.4%
BM_slicingSmallPieces_1T/4k           394660    396760     -0.5%
BM_slicingSmallPieces_1T/5k           218722    209244     +4.3%
BM_slicingSmallPieces_2T/2              80.7      79.9     +1.0%
BM_slicingSmallPieces_2T/8              54.2      53.1     +2.0
BM_slicingSmallPieces_2T/64              497       477     +4.0%
BM_slicingSmallPieces_2T/512           21732     18822    +13.4%
BM_slicingSmallPieces_2T/4k           392885    390490     +0.6%
BM_slicingSmallPieces_2T/5k           221988    208678     +6.0%
BM_slicingSmallPieces_4T/2              80.8      80.1     +0.9%
BM_slicingSmallPieces_4T/8              54.1      53.2     +1.7%
BM_slicingSmallPieces_4T/64              493       476     +3.4%
BM_slicingSmallPieces_4T/512           21702     18758    +13.6%
BM_slicingSmallPieces_4T/4k           393962    404023     -2.6%
BM_slicingSmallPieces_4T/5k           249667    211732    +15.2%
BM_slicingSmallPieces_6T/2              80.5      80.1     +0.5%
BM_slicingSmallPieces_6T/8              54.4      53.4     +1.8%
BM_slicingSmallPieces_6T/64              488       478     +2.0%
BM_slicingSmallPieces_6T/512           21719     18841    +13.3%
BM_slicingSmallPieces_6T/4k           394950    397583     -0.7%
BM_slicingSmallPieces_6T/5k           223080    210148     +5.8%
BM_slicingSmallPieces_8T/2              81.2      80.4     +1.0%
BM_slicingSmallPieces_8T/8              58.1      53.5     +7.9%
BM_slicingSmallPieces_8T/64              489       480     +1.8%
BM_slicingSmallPieces_8T/512           21586     18798    +12.9%
BM_slicingSmallPieces_8T/4k           394592    400165     -1.4%
BM_slicingSmallPieces_8T/5k           219688    208301     +5.2%
BM_slicingSmallPieces_12T/2             80.2      79.8     +0.7%
BM_slicingSmallPieces_12T/8             54.4      53.4     +1.8
BM_slicingSmallPieces_12T/64             488       476     +2.5%
BM_slicingSmallPieces_12T/512          21931     18831    +14.1%
BM_slicingSmallPieces_12T/4k          393962    396541     -0.7%
BM_slicingSmallPieces_12T/5k          218803    207965     +5.0%

1 files changed, 2 insertions, 2 deletions

diff --git a/unsupported/Eigen/CXX11/src/Tensor/TensorFFT.h b/unsupported/Eigen/CXX11/src/Tensor/TensorFFT.h
index 08eb5595a..f060191ab 100644
--- a/unsupported/Eigen/CXX11/src/Tensor/TensorFFT.h
+++ b/unsupported/Eigen/CXX11/src/Tensor/TensorFFT.h
@@ -253,7 +253,7 @@ struct TensorEvaluator<const TensorFFTOp<FFT, ArgType, FFTResultType, FFTDir>, D
         // get data into line_buf
         const Index stride = m_strides[dim];
         if (stride == 1) {
-          memcpy(line_buf, &buf[base_offset], line_len*sizeof(ComplexScalar));
+          m_device.memcpy(line_buf, &buf[base_offset], line_len*sizeof(ComplexScalar));
         } else {
           Index offset = base_offset;
           for (int j = 0; j < line_len; ++j, offset += stride) {
@@ -271,7 +271,7 @@ struct TensorEvaluator<const TensorFFTOp<FFT, ArgType, FFTResultType, FFTDir>, D
 
         // write back
         if (FFTDir == FFT_FORWARD && stride == 1) {
-          memcpy(&buf[base_offset], line_buf, line_len*sizeof(ComplexScalar));
+          m_device.memcpy(&buf[base_offset], line_buf, line_len*sizeof(ComplexScalar));
         } else {
           Index offset = base_offset;
           const ComplexScalar div_factor =  ComplexScalar(1.0 / line_len, 0);