Permalink
Browse files

nanashi r10 with proper utf8

  • Loading branch information...
1 parent 4a8e3d9 commit f262850270c377690c4348c3f600954c48dc3a99 @tpruvot committed Jul 16, 2016
Oops, something went wrong.
View
Oops, something went wrong.
Oops, something went wrong.
Oops, something went wrong.
View
Oops, something went wrong.
View
@@ -41,10 +41,7 @@
<LinkIncremental>false</LinkIncremental>
</PropertyGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.props" />
- <ImportGroup Label="ExtensionSettings" Condition="'$(Platform)'=='Win32'">
- <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.props" />
- </ImportGroup>
- <ImportGroup Label="ExtensionSettings" Condition="'$(Platform)'=='x64'">
+ <ImportGroup Label="ExtensionSettings">
<Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 7.5.props" />
</ImportGroup>
<ImportGroup Label="PropertySheets" Condition="'$(Configuration)|$(Platform)'=='Debug|Win32'">
@@ -83,10 +80,10 @@
<CudaCompile>
<CInterleavedPTX>false</CInterleavedPTX>
<GenerateLineInfo>true</GenerateLineInfo>
- <MaxRegCount>80</MaxRegCount>
+ <MaxRegCount>255</MaxRegCount>
<PtxAsOptionV>true</PtxAsOptionV>
<Keep>true</Keep>
- <CodeGeneration>compute_50,sm_50</CodeGeneration>
+ <CodeGeneration>compute_50,sm_50;compute_52,sm_52;compute_35,sm_35;compute_30,sm_30;compute_20,sm_20</CodeGeneration>
<Include>$(NVTOOLSEXT_PATH)\include;..\..\..\Common\C99</Include>
</CudaCompile>
</ItemDefinitionGroup>
@@ -115,15 +112,16 @@
<CudaCompile>
<CInterleavedPTX>false</CInterleavedPTX>
<GenerateLineInfo>true</GenerateLineInfo>
- <MaxRegCount>80</MaxRegCount>
+ <MaxRegCount>255</MaxRegCount>
<PtxAsOptionV>true</PtxAsOptionV>
<Keep>true</Keep>
- <CodeGeneration>compute_50,sm_50</CodeGeneration>
+ <CodeGeneration>compute_50,sm_50;compute_52,sm_52;compute_35,sm_35;compute_30,sm_30;compute_20,sm_20</CodeGeneration>
<Include>$(NVTOOLSEXT_PATH)\include;..\..\..\Common\C99</Include>
<TargetMachinePlatform>64</TargetMachinePlatform>
</CudaCompile>
<CudaLink>
<PerformDeviceLink>false</PerformDeviceLink>
+ <Optimization>O3</Optimization>
</CudaLink>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|Win32'">
@@ -158,16 +156,16 @@
</Link>
<CudaCompile>
<CInterleavedPTX>false</CInterleavedPTX>
- <MaxRegCount>80</MaxRegCount>
+ <MaxRegCount>255</MaxRegCount>
<PtxAsOptionV>true</PtxAsOptionV>
<Keep>true</Keep>
- <CodeGeneration>compute_50,sm_50;compute_52,sm_52;compute_30,sm_30;compute_20,sm_21</CodeGeneration>
+ <CodeGeneration>compute_50,sm_50;compute_52,sm_52;compute_35,sm_35;compute_30,sm_30;compute_20,sm_20</CodeGeneration>
<AdditionalOptions>--ptxas-options="-O2" %(AdditionalOptions)</AdditionalOptions>
- <Optimization>O2</Optimization>
+ <Optimization>O3</Optimization>
</CudaCompile>
<CudaLink>
<GPUDebugInfo>false</GPUDebugInfo>
- <Optimization>O3</Optimization>
+ <Optimization>O2</Optimization>
</CudaLink>
</ItemDefinitionGroup>
<ItemDefinitionGroup Condition="'$(Configuration)|$(Platform)'=='Release|x64'">
@@ -201,10 +199,10 @@
</Link>
<CudaCompile>
<CInterleavedPTX>false</CInterleavedPTX>
- <MaxRegCount>80</MaxRegCount>
+ <MaxRegCount>255</MaxRegCount>
<PtxAsOptionV>true</PtxAsOptionV>
<Keep>true</Keep>
- <CodeGeneration>compute_52,sm_52;compute_50,sm_50;compute_35,sm_35;compute_30,sm_30;compute_20,sm_21</CodeGeneration>
+ <CodeGeneration>compute_50,sm_50;compute_52,sm_52;compute_35,sm_35;compute_30,sm_30;compute_20,sm_20</CodeGeneration>
<Include>$(NVTOOLSEXT_PATH)\include;..\..\..\Common\C99</Include>
<Optimization>O3</Optimization>
<TargetMachinePlatform>64</TargetMachinePlatform>
@@ -250,6 +248,7 @@
<ClCompile Include="lyra2\Lyra2.c" />
<ClCompile Include="lyra2\Sponge.c" />
<ClInclude Include="lyra2\cuda_lyra2_sm2.cuh" />
+ <ClInclude Include="lyra2\cuda_lyra2_sm5.cuh" />
<ClInclude Include="neoscrypt\neoscrypt.h" />
<ClCompile Include="neoscrypt\neoscrypt.cpp" />
<ClCompile Include="neoscrypt\neoscrypt-cpu.c" />
@@ -347,7 +346,6 @@
<ClInclude Include="uint256.h" />
<ClInclude Include="lyra2\Lyra2.h" />
<ClInclude Include="lyra2\Sponge.h" />
- <ClInclude Include="lyra2\cuda_lyra2v2_sm3.cuh" />
<ClInclude Include="quark\groestl_transf_quad.h" />
<ClInclude Include="quark\groestl_functions_quad.h" />
<ClInclude Include="quark\cuda_quark.h" />
@@ -527,10 +525,7 @@
<Text Include="README.txt" />
</ItemGroup>
<Import Project="$(VCTargetsPath)\Microsoft.Cpp.targets" />
- <ImportGroup Label="ExtensionTargets" Condition="'$(Platform)'=='Win32'">
- <Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 6.5.targets" />
- </ImportGroup>
- <ImportGroup Label="ExtensionTargets" Condition="'$(Platform)'=='x64'">
+ <ImportGroup Label="ExtensionTargets">
<Import Project="$(VCTargetsPath)\BuildCustomizations\CUDA 7.5.targets" />
</ImportGroup>
<!-- Copy the required dlls -->
@@ -540,4 +535,4 @@
<Target Name="AfterClean">
<Delete Files="@(FilesToCopy->'$(OutDir)%(Filename)%(Extension)')" TreatErrorsAsWarnings="true" />
</Target>
-</Project>
+</Project>
@@ -437,9 +437,6 @@
<ClInclude Include="bignum.hpp">
<Filter>Header Files</Filter>
</ClInclude>
- <ClInclude Include="lyra2\cuda_lyra2v2_sm3.cuh">
- <Filter>Source Files\CUDA\lyra2</Filter>
- </ClInclude>
<ClInclude Include="lyra2\cuda_lyra2_sm2.cuh">
<Filter>Source Files\CUDA\lyra2</Filter>
</ClInclude>
@@ -455,6 +452,9 @@
<ClInclude Include="x11\cuda_x11_simd512_sm2.cuh">
<Filter>Source Files\CUDA\x11</Filter>
</ClInclude>
+ <ClInclude Include="lyra2\cuda_lyra2_sm5.cuh">
+ <Filter>Source Files\CUDA\lyra2</Filter>
+ </ClInclude>
</ItemGroup>
<ItemGroup>
<CudaCompile Include="cuda.cpp">
@@ -728,4 +728,4 @@
<Filter>Ressources</Filter>
</Text>
</ItemGroup>
-</Project>
+</Project>
View
@@ -1,4 +1,4 @@
-AC_INIT([ccminer], [1.7.6], [], [ccminer], [http://github.com/tpruvot/ccminer])
+AC_INIT([ccminer], [1.7.6-r10], [], [ccminer], [http://github.com/tpruvot/ccminer])
AC_PREREQ([2.59c])
AC_CANONICAL_SYSTEM
View
@@ -96,7 +96,6 @@ __device__ __forceinline__ uint64_t REPLACE_LODWORD(const uint64_t &x, const uin
return (x & 0xFFFFFFFF00000000ULL) | ((uint64_t)y);
}
-// Endian Drehung für 32 Bit Typen
#ifdef __CUDA_ARCH__
__device__ __forceinline__ uint32_t cuda_swab32(uint32_t x)
{
@@ -471,6 +470,15 @@ static __host__ __device__ __forceinline__ uint64_t devectorize(uint2 v) {
#endif
}
+static __device__ __forceinline__ uint2 eorswap32(uint2 u, uint2 v)
+{
+ uint2 result;
+ result.y = u.x ^ v.x;
+ result.x = u.y ^ v.y;
+ return result;
+}
+
+
/**
* uint2 direct ops by c++ operator definitions
*/
@@ -561,11 +569,9 @@ uint2 ROR2(const uint2 a, const int offset)
return result;
}
-__device__ __forceinline__
-uint2 ROL2(const uint2 a, const int offset)
-{
+#if __CUDA_ARCH__ >= 350
+__inline__ __device__ uint2 ROL2(const uint2 a, const int offset) {
uint2 result;
-#if __CUDA_ARCH__ > 300
if (offset >= 32) {
asm("shf.l.wrap.b32 %0, %1, %2, %3;" : "=r"(result.x) : "r"(a.x), "r"(a.y), "r"(offset));
asm("shf.l.wrap.b32 %0, %1, %2, %3;" : "=r"(result.y) : "r"(a.y), "r"(a.x), "r"(offset));
@@ -574,14 +580,20 @@ uint2 ROL2(const uint2 a, const int offset)
asm("shf.l.wrap.b32 %0, %1, %2, %3;" : "=r"(result.x) : "r"(a.y), "r"(a.x), "r"(offset));
asm("shf.l.wrap.b32 %0, %1, %2, %3;" : "=r"(result.y) : "r"(a.x), "r"(a.y), "r"(offset));
}
+ return result;
+}
#else
- if (!offset)
- result = a;
+__inline__ __device__ uint2 ROL2(const uint2 v, const int n)
+{
+ uint2 result;
+ if (!n)
+ result = v;
else
- result = ROR2(a, 64 - offset);
-#endif
+ result = ROR2(v, 64 - n);
+
return result;
}
+#endif
__device__ __forceinline__
uint2 SWAPUINT2(uint2 value)
Oops, something went wrong.

0 comments on commit f262850

Please sign in to comment.