Merge pull request #2132 from fireice-uk/dev

bug fix release 2.7.1

doc/compile_Windows.md

@@ -30,15 +30,16 @@
     - CUDA/Runtime
     - Driver components
 
-### AMD DRIVER/APP SDK 3.0 (only needed for AMD GPUs)
+### AMD DRIVER/OCL-SDK (only needed for AMD GPUs)
 
 - Download & install the AMD driver: https://www.amd.com/en/support
 
 **ATTENTION** Many windows driver 18.5+ creating invalid shares.
 If you have an issue with `invalid shares` please downgrade your driver.
 
-- Download and install the latest version from http://amd-dev.wpengine.netdna-cdn.com/app-sdk/installers/APPSDKInstaller/3.0.130.135-GA/full/AMD-APP-SDKInstaller-v3.0.130.135-GA-windows-F-x64.exe
-  (do not wonder why it is a link to a netdna-cdn.com but AMD has removed the SDK downloads, see https://community.amd.com/thread/222855)
+- Download and install the latest version of the OCL-SDK from https://github.com/GPUOpen-LibrariesAndSDKs/OCL-SDK/releases 
+
+Do not follow old information that you need the AMD APP SDK. AMD has removed the APP SDK and is now shipping the OCL-SDK_light.
 
 ### Dependencies OpenSSL/Hwloc and Microhttpd
 - For CUDA 8*:
@@ -115,4 +116,4 @@ If you have an issue with `invalid shares` please downgrade your driver.
 
   copy C:\xmr-stak-dep\openssl\bin\* .
   ```
-- Miner is by default compiled for NVIDIA GPUs (if CUDA is installed), AMD GPUs (if the AMD APP SDK is installed) and CPUs.
+- Miner is by default compiled for NVIDIA GPUs (if CUDA is installed), AMD GPUs (if the AMD OCL-SDK_light is installed) and CPUs.

xmrstak/backend/amd/amd_gpu/opencl/cryptonight.cl

@@ -662,7 +662,7 @@ __kernel void JOIN(cn1,ALGO) (__global uint4 *Scratchpad, __global ulong *states
 			((uint4 *)c)[0] = SCRATCHPAD_CHUNK(0);
 // cryptonight_bittube2
 #if(ALGO == 10)
-			((uint4 *)c)[0] = AES_Round2(AES0, AES1, ~((uint4 *)c)[0], ((uint4 *)a)[0]);
+			((uint4 *)c)[0] = AES_Round2_bittube2(AES0, AES1, ~((uint4 *)c)[0], ((uint4 *)a)[0]);
 #else
 			((uint4 *)c)[0] = AES_Round2(AES0, AES1, ((uint4 *)c)[0], ((uint4 *)a)[0]);
 #endif

xmrstak/backend/amd/amd_gpu/opencl/wolf-aes.cl

@@ -119,6 +119,19 @@ uint4 AES_Round2(const __local uint *AES0, const __local uint *AES1, const uint4
 	return key;
 }
 
+uint4 AES_Round2_bittube2(const __local uint *AES0, const __local uint *AES1, uint4 X, uint4 key)
+{
+	key.s0 ^= AES0[BYTE(X.s0, 0)] ^ rotate(AES0[BYTE(X.s2, 2)] ^ AES1[BYTE(X.s3, 3)], 16u) ^ AES1[BYTE(X.s1, 1)];
+	X.s0 ^= key.s0;
+	key.s1 ^= AES0[BYTE(X.s1, 0)] ^ rotate(AES0[BYTE(X.s3, 2)] ^ AES1[BYTE(X.s0, 3)], 16u) ^  AES1[BYTE(X.s2, 1)];
+	X.s1 ^= key.s1;
+	key.s2 ^= AES0[BYTE(X.s2, 0)] ^ rotate(AES0[BYTE(X.s0, 2)] ^ AES1[BYTE(X.s1, 3)], 16u) ^ AES1[BYTE(X.s3, 1)];
+	X.s2 ^= key.s2;
+	key.s3 ^= AES0[BYTE(X.s3, 0)] ^ rotate(AES0[BYTE(X.s1, 2)] ^ AES1[BYTE(X.s2, 3)], 16u) ^ AES1[BYTE(X.s0, 1)];
+
+	return key;
+}
+
 #endif
 
 )==="

xmrstak/backend/amd/config.tpl

@@ -48,7 +48,7 @@ GPUCONFIG
  * WARNING: experimental option
  *
  * 0 = disable auto tuning
- * 10 or higher = recommended value if you not already know the best intensity
+ * 10 or higher = recommended value if you don't already know the best intensity
  */
 "auto_tune" : 0,
 

xmrstak/version.cpp

@@ -18,7 +18,7 @@
 #endif
 
 #define XMR_STAK_NAME "xmr-stak"
-#define XMR_STAK_VERSION "2.7.0"
+#define XMR_STAK_VERSION "2.7.1"
 
 #if defined(_WIN32)
 #define OS_TYPE "win"