Hello community,

here is the log from the commit of package clpeak for openSUSE:Factory checked 
in at 2017-05-31 12:19:42
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Comparing /work/SRC/openSUSE:Factory/clpeak (Old)
 and      /work/SRC/openSUSE:Factory/.clpeak.new (New)
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Package is "clpeak"

Wed May 31 12:19:42 2017 rev:3 rq:499612 version:1.0+git.20170525

Changes:
--------
--- /work/SRC/openSUSE:Factory/clpeak/clpeak.changes    2017-02-03 
17:34:45.197734924 +0100
+++ /work/SRC/openSUSE:Factory/.clpeak.new/clpeak.changes       2017-05-31 
12:20:18.079664600 +0200
@@ -1,0 +2,14 @@
+Tue May 30 08:35:31 UTC 2017 - [email protected]
+
+- Update to version 1.0+git.20170525:
+  * Add GTX 1080 Ti results
+  * Remove non printable chars from log file
+  * Add One Plus 3T results
+  * Macbook pro results submitted by Harry Mallon
+  * Rename Macbook_Pro_2013.log to Mac_Pro_Late_2013_.log
+  * Not passing half as kernel argument
+  * Fix uninitialized variable
+  * Ignore ignored-attributes warning in g++, clang++
+  * Enable support for FreeBSD.
+
+-------------------------------------------------------------------

Old:
----
  clpeak-1.0+git.20160805.tar.xz

New:
----
  _servicedata
  clpeak-1.0+git.20170525.tar.xz

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

Other differences:
------------------
++++++ clpeak.spec ++++++
--- /var/tmp/diff_new_pack.wMk4Ey/_old  2017-05-31 12:20:19.291493532 +0200
+++ /var/tmp/diff_new_pack.wMk4Ey/_new  2017-05-31 12:20:19.295492968 +0200
@@ -18,7 +18,7 @@
 
 
 Name:           clpeak
-Version:        1.0+git.20160805
+Version:        1.0+git.20170525
 Release:        0
 Summary:        Find peak OpenCL capacities like bandwidth & compute
 License:        SUSE-Public-Domain
@@ -51,7 +51,7 @@
 
 %files
 %defattr (-,root,root)
-%doc README.md LICENSE STATUS
+%doc README.md LICENSE STATUS results
 %{_bindir}/%{name}
 
 %changelog

++++++ _servicedata ++++++
<servicedata>
<service name="tar_scm">
                <param name="url">git://github.com/krrishnarraj/clpeak</param>
              <param 
name="changesrevision">c23d2f77a9154d155eefee0538e453272921e5a5</param></service></servicedata>++++++
 clpeak-1.0+git.20160805.tar.xz -> clpeak-1.0+git.20170525.tar.xz ++++++
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' old/clpeak-1.0+git.20160805/.gitmodules 
new/clpeak-1.0+git.20170525/.gitmodules
--- old/clpeak-1.0+git.20160805/.gitmodules     1970-01-01 01:00:00.000000000 
+0100
+++ new/clpeak-1.0+git.20170525/.gitmodules     2017-05-25 06:45:41.000000000 
+0200
@@ -0,0 +1,3 @@
+[submodule "android/app/src/main/jni/libopencl-stub"]
+       path = android/app/src/main/jni/libopencl-stub
+       url = https://github.com/krrishnarraj/libopencl-stub
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' old/clpeak-1.0+git.20160805/CMakeLists.txt 
new/clpeak-1.0+git.20170525/CMakeLists.txt
--- old/clpeak-1.0+git.20160805/CMakeLists.txt  2016-08-05 08:23:31.000000000 
+0200
+++ new/clpeak-1.0+git.20170525/CMakeLists.txt  2017-05-25 06:45:41.000000000 
+0200
@@ -89,7 +89,7 @@
     add_definitions("-march=native")
   endif()
 
-  add_definitions("-fPIC -Wall -Wextra -Wno-deprecated-declarations 
-Wno-unused-parameter")
+  add_definitions("-fPIC -Wall -Wextra -Wno-deprecated-declarations 
-Wno-unused-parameter -Wno-ignored-attributes")
 endif()
 
 # override cl.hp from deps. Its buggy or not present in come systems
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' old/clpeak-1.0+git.20160805/include/common.h 
new/clpeak-1.0+git.20170525/include/common.h
--- old/clpeak-1.0+git.20160805/include/common.h        2016-08-05 
08:23:31.000000000 +0200
+++ new/clpeak-1.0+git.20170525/include/common.h        2017-05-25 
06:45:41.000000000 +0200
@@ -2,7 +2,7 @@
 #define COMMON_H
 
 #include <CL/cl.hpp>
-#if defined(__APPLE__) || defined(__MACOSX)
+#if defined(__APPLE__) || defined(__MACOSX) || defined(__FreeBSD__)
 #include <sys/types.h>
 #endif
 
@@ -12,7 +12,9 @@
 
 #define TAB             "  "
 #define NEWLINE         "\n"
+#ifndef __FreeBSD__
 #define uint            unsigned int
+#endif
 
 #define MAX(X, Y)       \
   (X > Y)? X: Y;
@@ -39,6 +41,8 @@
 #elif defined(__arm__)
 #define OS_NAME     "Linux ARM"
 #endif
+#elif defined(__FreeBSD__)
+#define OS_NAME     "FreeBSD"
 #endif
 
 
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' 
old/clpeak-1.0+git.20160805/results/Apple/Mac_Pro_Late_2013_.log 
new/clpeak-1.0+git.20170525/results/Apple/Mac_Pro_Late_2013_.log
--- old/clpeak-1.0+git.20160805/results/Apple/Mac_Pro_Late_2013_.log    
1970-01-01 01:00:00.000000000 +0100
+++ new/clpeak-1.0+git.20170525/results/Apple/Mac_Pro_Late_2013_.log    
2017-05-25 06:45:41.000000000 +0200
@@ -0,0 +1,76 @@
+Platform: Apple
+  Device: AMD Radeon HD - FirePro D700 Compute Engine
+    Driver version  : 1.2 (Mar 16 2017 18:19:56) (Macintosh)
+    Compute units   : 32
+    Clock frequency : 850 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 182.39
+      float2  : 189.53
+      float4  : 195.73
+      float8  : 101.98
+      float16 : 53.33
+
+    Single-precision compute (GFLOPS)
+      float   : 2593.97
+      float2  : 2591.22
+      float4  : 2584.96
+      float8  : 2572.53
+      float16 : 2543.34
+
+    No half precision support! Skipped
+
+    Double-precision compute (GFLOPS)
+      double   : 654.65
+      double2  : 654.62
+      double4  : 653.86
+      double8  : 652.82
+      double16 : 650.63
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 11.12
+      enqueueReadBuffer          : 11.92
+      enqueueMapBuffer(for read) : 94.12
+        memcpy from mapped ptr   : 6.79
+      enqueueUnmap(after write)  : 7550.93
+        memcpy to mapped ptr     : 7.64
+
+    Kernel launch latency : 9.63 us
+
+  Device: AMD Radeon HD - FirePro D700 Compute Engine
+    Driver version  : 1.2 (Mar 16 2017 18:19:56) (Macintosh)
+    Compute units   : 32
+    Clock frequency : 850 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 184.77
+      float2  : 191.74
+      float4  : 197.64
+      float8  : 102.48
+      float16 : 53.56
+
+    Single-precision compute (GFLOPS)
+      float   : 2599.49
+      float2  : 2594.67
+      float4  : 2590.64
+      float8  : 2576.32
+      float16 : 2547.82
+
+    No half precision support! Skipped
+
+    Double-precision compute (GFLOPS)
+      double   : 654.91
+      double2  : 654.89
+      double4  : 654.75
+      double8  : 654.34
+      double16 : 651.34
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 10.05
+      enqueueReadBuffer          : 9.31
+      enqueueMapBuffer(for read) : 85.90
+        memcpy from mapped ptr   : 6.73
+      enqueueUnmap(after write)  : 7389.83
+        memcpy to mapped ptr     : 7.70
+
+    Kernel launch latency : 10.21 us
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' 
old/clpeak-1.0+git.20160805/results/NVIDIA_CUDA/GeForce_GTX_1080_Ti.log 
new/clpeak-1.0+git.20170525/results/NVIDIA_CUDA/GeForce_GTX_1080_Ti.log
--- old/clpeak-1.0+git.20160805/results/NVIDIA_CUDA/GeForce_GTX_1080_Ti.log     
1970-01-01 01:00:00.000000000 +0100
+++ new/clpeak-1.0+git.20170525/results/NVIDIA_CUDA/GeForce_GTX_1080_Ti.log     
2017-05-25 06:45:41.000000000 +0200
@@ -0,0 +1,45 @@
+
+Platform: NVIDIA CUDA
+  Device: Graphics Device
+    Driver version  : 378.13 (Linux x64)
+    Compute units   : 28
+    Clock frequency : 1683 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 389.99
+      float2  : 394.86
+      float4  : 410.15
+      float8  : 388.05
+      float16 : 263.58
+
+    Single-precision compute (GFLOPS)
+      float   : 11675.87
+      float2  : 13240.07
+      float4  : 13317.21
+      float8  : 13151.05
+      float16 : 12939.08
+
+    Double-precision compute (GFLOPS)
+      double   : 425.21
+      double2  : 432.63
+      double4  : 425.45
+      double8  : 420.62
+      double16 : 409.39
+
+    Integer compute (GIOPS)
+      int   : 3507.68
+      int2  : 3801.87
+      int4  : 3772.84
+      int8  : 3774.45
+      int16 : 3748.59
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 9.96
+      enqueueReadBuffer          : 8.95
+      enqueueMapBuffer(for read) : 11.11
+        memcpy from mapped ptr   : 12.16
+      enqueueUnmap(after write)  : 12.40
+        memcpy to mapped ptr     : 12.48
+
+    Kernel launch latency : 4.22 us
+
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' 
old/clpeak-1.0+git.20160805/results/Qualcomm_Snapdragon/OnePlus_3T.log 
new/clpeak-1.0+git.20170525/results/Qualcomm_Snapdragon/OnePlus_3T.log
--- old/clpeak-1.0+git.20160805/results/Qualcomm_Snapdragon/OnePlus_3T.log      
1970-01-01 01:00:00.000000000 +0100
+++ new/clpeak-1.0+git.20170525/results/Qualcomm_Snapdragon/OnePlus_3T.log      
2017-05-25 06:45:41.000000000 +0200
@@ -0,0 +1,45 @@
+Platform: QUALCOMM Snapdragon(TM)
+  Device: QUALCOMM Adreno(TM)
+    Driver version  : OpenCL 2.0 QUALCOMM build: commit #6ff34ae changeid 
#I0ac3940325 Date: 09/23/16 Fri Local Branch:  Remote Branch: 
refs/tags/AU_LINUX_ANDROID_LA.HB.1.3.2.06.00.01.214.261 Compiler E031.31.00.01 
(Android)
+    Compute units   : 4
+    Clock frequency : 1 MHz
+
+    Global memory bandwidth (GBPS)
+      float   : 15.28
+      float2  : 11.46
+      float4  : 16.31
+      float8  : 20.20
+      float16 : 20.43
+
+    Single-precision compute (GFLOPS)
+      float   : 249.85
+      float2  : 249.99
+      float4  : 237.66
+      float8  : 263.18
+      float16 : 202.15
+
+    half-precision compute (GFLOPS)
+      half   : 260.10
+      half2  : 391.85
+      half4  : 383.45
+      half8  : 270.69
+      half16 : 202.19
+
+    No double precision support! Skipped
+
+    Integer compute (GIOPS)
+      int   : 52.21
+      int2  : 55.46
+      int4  : 71.81
+      int8  : 69.74
+      int16 : 69.22
+
+    Transfer bandwidth (GBPS)
+      enqueueWriteBuffer         : 18.17
+      enqueueReadBuffer          : 8.72
+      enqueueMapBuffer(for read) : 2839.08
+        memcpy from mapped ptr   : 8.45
+      enqueueUnmap(after write)  : 816.78
+        memcpy to mapped ptr     : 9.77
+
+    Kernel launch latency : 296.08 us
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' old/clpeak-1.0+git.20160805/src/common.cpp 
new/clpeak-1.0+git.20170525/src/common.cpp
--- old/clpeak-1.0+git.20160805/src/common.cpp  2016-08-05 08:23:31.000000000 
+0200
+++ new/clpeak-1.0+git.20170525/src/common.cpp  2017-05-25 06:45:41.000000000 
+0200
@@ -34,6 +34,7 @@
   devInfo.maxGlobalSize = (uint)d.getInfo<CL_DEVICE_GLOBAL_MEM_SIZE>();
   devInfo.maxClockFreq = (uint)d.getInfo<CL_DEVICE_MAX_CLOCK_FREQUENCY>();
   devInfo.doubleSupported = false;
+  devInfo.halfSupported = false;
 
   std::string extns = d.getInfo<CL_DEVICE_EXTENSIONS>();
 
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' old/clpeak-1.0+git.20160805/src/compute_hp.cpp 
new/clpeak-1.0+git.20170525/src/compute_hp.cpp
--- old/clpeak-1.0+git.20160805/src/compute_hp.cpp      2016-08-05 
08:23:31.000000000 +0200
+++ new/clpeak-1.0+git.20170525/src/compute_hp.cpp      2017-05-25 
06:45:41.000000000 +0200
@@ -6,7 +6,7 @@
   float timed, gflops;
   cl_uint workPerWI;
   cl::NDRange globalSize, localSize;
-  cl_half A = 0x1234;
+  cl_float A = 1.3f;
   int iters = devInfo.computeIters;
 
   if(!isComputeDP)
diff -urN '--exclude=CVS' '--exclude=.cvsignore' '--exclude=.svn' 
'--exclude=.svnignore' 
old/clpeak-1.0+git.20160805/src/kernels/compute_hp_kernels.cl 
new/clpeak-1.0+git.20170525/src/kernels/compute_hp_kernels.cl
--- old/clpeak-1.0+git.20160805/src/kernels/compute_hp_kernels.cl       
2016-08-05 08:23:31.000000000 +0200
+++ new/clpeak-1.0+git.20170525/src/kernels/compute_hp_kernels.cl       
2017-05-25 06:45:41.000000000 +0200
@@ -21,8 +21,9 @@
 \n
 
 
-__kernel void compute_hp_v1(__global half *ptr, half _A)
+__kernel void compute_hp_v1(__global half *ptr, float _B)
 {
+    half _A = (half)_B;
     half x = _A;
     half y = (half)get_local_id(0);
 
@@ -48,8 +49,9 @@
 }
 
 
-__kernel void compute_hp_v2(__global half *ptr, half _A)
+__kernel void compute_hp_v2(__global half *ptr, float _B)
 {
+    half _A = (half)_B;
     half2 x = (half2)(_A, (_A+1));
     half2 y = (half2)get_local_id(0);
 
@@ -65,8 +67,9 @@
     ptr[get_global_id(0)] = (y.S0) + (y.S1);
 }
 
-__kernel void compute_hp_v4(__global half *ptr, half _A)
+__kernel void compute_hp_v4(__global half *ptr, float _B)
 {
+    half _A = (half)_B;
     half4 x = (half4)(_A, (_A+1), (_A+2), (_A+3));
     half4 y = (half4)get_local_id(0);
 
@@ -83,8 +86,9 @@
 }
 
 
-__kernel void compute_hp_v8(__global half *ptr, half _A)
+__kernel void compute_hp_v8(__global half *ptr, float _B)
 {
+    half _A = (half)_B;
     half8 x = (half8)(_A, (_A+1), (_A+2), (_A+3), (_A+4), (_A+5), (_A+6), 
(_A+7));
     half8 y = (half8)get_local_id(0);
 
@@ -96,8 +100,9 @@
     ptr[get_global_id(0)] = (y.S0) + (y.S1) + (y.S2) + (y.S3) + (y.S4) + 
(y.S5) + (y.S6) + (y.S7);
 }
 
-__kernel void compute_hp_v16(__global half *ptr, half _A)
+__kernel void compute_hp_v16(__global half *ptr, float _B)
 {
+    half _A = (half)_B;
     half16 x = (half16)(_A, (_A+1), (_A+2), (_A+3), (_A+4), (_A+5), (_A+6), 
(_A+7),
                     (_A+8), (_A+9), (_A+10), (_A+11), (_A+12), (_A+13), 
(_A+14), (_A+15));
     half16 y = (half16)get_local_id(0);


Reply via email to