Merge pull request krrishnarraj#8 from atom-symbol/master

Add AMD A10-7850K and GeForce GTX 750

results/AMD_Accelerated_Parallel_Processing/AMD_A10-7850K_APU.log

@@ -0,0 +1,74 @@
+
+Platform: AMD Accelerated Parallel Processing
+  Device: Spectre
+    Driver version  : 1573.4 (VM) (Linux x64)
+    Compute units   : 8
+    Clock frequency : 720 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 27.21
+      float2  : 28.08
+      float4  : 22.67
+      float8  : 15.10
+      float16 : 8.28
+
+    Single-precision compute (GFLOPS)
+      float   : 733.13
+      float2  : 732.25
+      float4  : 730.70
+      float8  : 726.86
+      float16 : 718.54
+
+    Double-precision compute (GFLOPS)
+      double   : 45.98
+      double2  : 45.95
+      double4  : 45.91
+      double8  : 45.81
+      double16 : 45.61
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 8.42
+      enqueueReadBuffer          : 5.40
+      enqueueMapBuffer(for read) : 4357.72
+        memcpy from mapped ptr   : 3.76
+      enqueueUnmap(after write)  : 8918.12
+        memcpy to mapped ptr     : 3.54
+
+    Kernel launch latency : 33.79 us
+
+  Device: AMD A10-7850K APU with Radeon(TM) R7 Graphics
+    Driver version  : 1573.4 (sse2,avx,fma4) (Linux x64)
+    Compute units   : 4
+    Clock frequency : 4000 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 9.72
+      float2  : 10.97
+      float4  : 12.09
+      float8  : 11.17
+      float16 : 14.40
+
+    Single-precision compute (GFLOPS)
+      float   : 3.12
+      float2  : 5.69
+      float4  : 12.62
+      float8  : 22.69
+      float16 : 44.04
+
+    Double-precision compute (GFLOPS)
+      double   : 3.11
+      double2  : 6.28
+      double4  : 11.28
+      double8  : 23.00
+      double16 : 28.83
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 8.31
+      enqueueReadBuffer          : 5.45
+      enqueueMapBuffer(for read) : 10324.44
+        memcpy from mapped ptr   : 3.76
+      enqueueUnmap(after write)  : 19311.90
+        memcpy to mapped ptr     : 3.56
+
+    Kernel launch latency : 11.89 us
+

results/Intel(R)_OpenCL/AMD_A10-7850K_APU.log

@@ -0,0 +1,38 @@
+
+Platform: Intel(R) OpenCL
+  Device: AMD A10-7850K APU with Radeon(TM) R7 Graphics  
+    Driver version  : 1.2.0.117 (Linux x64)
+    Compute units   : 4
+    Clock frequency : 4000 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 13.31
+      float2  : 12.38
+      float4  : 13.23
+      float8  : 14.21
+      float16 : 14.76
+
+    Single-precision compute (GFLOPS)
+      float   : 12.65
+      float2  : 50.25
+      float4  : 62.71
+      float8  : 23.14
+      float16 : 46.36
+
+    Double-precision compute (GFLOPS)
+      double   : 11.87
+      double2  : 31.64
+      double4  : 15.13
+      double8  : 24.39
+      double16 : 30.34
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 1.87
+      enqueueReadBuffer          : 3.52
+      enqueueMapBuffer(for read) : 15123.12
+        memcpy from mapped ptr   : 3.52
+      enqueueUnmap(after write)  : 16468.43
+        memcpy to mapped ptr     : 3.46
+
+    Kernel launch latency : 3.08 us
+

results/NVIDIA_CUDA/GeForce_GTX_750.log

@@ -0,0 +1,38 @@
+
+Platform: NVIDIA CUDA
+  Device: GeForce GTX 750
+    Driver version  : 343.22 (Linux x64)
+    Compute units   : 4
+    Clock frequency : 1137 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 68.31
+      float2  : 71.03
+      float4  : 72.28
+      float8  : 68.97
+      float16 : 65.70
+
+    Single-precision compute (GFLOPS)
+      float   : 750.57
+      float2  : 962.20
+      float4  : 1172.67
+      float8  : 1177.41
+      float16 : 1168.44
+
+    Double-precision compute (GFLOPS)
+      double   : 38.06
+      double2  : 38.03
+      double4  : 37.97
+      double8  : 37.82
+      double16 : 37.55
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 7.97
+      enqueueReadBuffer          : 4.65
+      enqueueMapBuffer(for read) : 8.75
+        memcpy from mapped ptr   : 3.58
+      enqueueUnmap(after write)  : 12.40
+        memcpy to mapped ptr     : 3.50
+
+    Kernel launch latency : 4.60 us
+