Version of BSGLMM code released on web, 7 Aug 2014

README.md

@@ -0,0 +1 @@
+# BSGLMM

bsglmm/Makefile

@@ -0,0 +1,187 @@
+################################################################################
+#
+# Copyright 1993-2013 NVIDIA Corporation.  All rights reserved.
+#
+# NOTICE TO USER:   
+#
+# This source code is subject to NVIDIA ownership rights under U.S. and 
+# international Copyright laws.  
+#
+# NVIDIA MAKES NO REPRESENTATION ABOUT THE SUITABILITY OF THIS SOURCE 
+# CODE FOR ANY PURPOSE.  IT IS PROVIDED "AS IS" WITHOUT EXPRESS OR 
+# IMPLIED WARRANTY OF ANY KIND.  NVIDIA DISCLAIMS ALL WARRANTIES WITH 
+# REGARD TO THIS SOURCE CODE, INCLUDING ALL IMPLIED WARRANTIES OF 
+# MERCHANTABILITY, NONINFRINGEMENT, AND FITNESS FOR A PARTICULAR PURPOSE.   
+# IN NO EVENT SHALL NVIDIA BE LIABLE FOR ANY SPECIAL, INDIRECT, INCIDENTAL, 
+# OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS 
+# OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE 
+# OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE 
+# OR PERFORMANCE OF THIS SOURCE CODE.  
+#
+# U.S. Government End Users.  This source code is a "commercial item" as 
+# that term is defined at 48 C.F.R. 2.101 (OCT 1995), consisting  of 
+# "commercial computer software" and "commercial computer software 
+# documentation" as such terms are used in 48 C.F.R. 12.212 (SEPT 1995) 
+# and is provided to the U.S. Government only as a commercial end item.  
+# Consistent with 48 C.F.R.12.212 and 48 C.F.R. 227.7202-1 through 
+# 227.7202-4 (JUNE 1995), all U.S. Government End Users acquire the 
+# source code with only those rights set forth herein.
+#
+################################################################################
+#
+# Makefile project only supported on Mac OS X and Linux Platforms)
+#
+################################################################################
+
+# include /home/tdjtdj/NVIDIA_CUDA-5.5_Samples/common/findcudalib.mk
+
+
+# OS Name (Linux or Darwin)                                                                                                        
+OSUPPER = $(shell uname -s 2>/dev/null | tr [:lower:] [:upper:])
+OSLOWER = $(shell uname -s 2>/dev/null | tr [:upper:] [:lower:])
+
+# Flags to detect 32-bit or 64-bit OS platform                                                                                     
+OS_SIZE = $(shell uname -m | sed -e "s/i.86/32/" -e "s/x86_64/64/")
+OS_ARCH = $(shell uname -m | sed -e "s/i386/i686/")
+
+# These flags will override any settings                                                                                           
+ifeq ($(i386),1)
+        OS_SIZE = 32
+        OS_ARCH = i686
+endif
+
+ifeq ($(x86_64),1)
+        OS_SIZE = 64
+        OS_ARCH = x86_64
+endif
+
+
+# Location of the CUDA Toolkit
+CUDA_PATH       ?= /usr/local/cuda-5.0
+CUDA_BIN_PATH   ?= $(CUDA_PATH)/bin
+
+
+# Common binaries
+NVCC            ?= $(CUDA_BIN_PATH)/nvcc
+GCC             ?= g++
+
+
+# internal flags
+NVCCFLAGS   := -m${OS_SIZE}
+CCFLAGS     := -O3
+NVCCLDFLAGS :=
+LDFLAGS     :=
+
+# Extra user flags
+EXTRA_NVCCFLAGS   ?=
+EXTRA_NVCCLDFLAGS ?=
+EXTRA_LDFLAGS     ?=
+EXTRA_CCFLAGS     ?=
+
+# OS-specific build flags
+ifneq ($(DARWIN),) 
+  LDFLAGS += -rpath $(CUDA_PATH)/lib
+  CCFLAGS += -arch $(OS_ARCH) $(STDLIB)
+else
+  ifeq ($(OS_ARCH),armv7l)
+    ifeq ($(abi),gnueabi)
+      CCFLAGS += -mfloat-abi=softfp
+    else
+      # default to gnueabihf
+      override abi := gnueabihf
+      LDFLAGS += --dynamic-linker=/lib/ld-linux-armhf.so.3
+      CCFLAGS += -mfloat-abi=hard
+    endif
+  endif
+endif
+
+ifeq ($(ARMv7),1)
+NVCCFLAGS += -target-cpu-arch ARM
+ifneq ($(TARGET_FS),) 
+CCFLAGS += --sysroot=$(TARGET_FS)
+LDFLAGS += --sysroot=$(TARGET_FS)
+LDFLAGS += -rpath-link=$(TARGET_FS)/lib
+LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib
+LDFLAGS += -rpath-link=$(TARGET_FS)/usr/lib/arm-linux-$(abi)
+endif
+endif
+
+# Debug build flags
+ifeq ($(dbg),1)
+      NVCCFLAGS += -g -G
+      TARGET := debug
+else
+      TARGET := release
+endif
+
+ALL_CCFLAGS :=
+ALL_CCFLAGS += $(NVCCFLAGS)
+ALL_CCFLAGS += $(addprefix -Xcompiler ,$(CCFLAGS))
+ALL_CCFLAGS += $(EXTRA_NVCCFLAGS)
+ALL_CCFLAGS += $(addprefix -Xcompiler ,$(EXTRA_CCFLAGS))
+
+ALL_LDFLAGS :=
+ALL_LDFLAGS += $(ALL_CCFLAGS)
+ALL_LDFLAGS += $(NVCCLDFLAGS)
+ALL_LDFLAGS += $(addprefix -Xlinker ,$(LDFLAGS))
+ALL_LDFLAGS += $(EXTRA_NVCCLDFLAGS)
+ALL_LDFLAGS += $(addprefix -Xlinker ,$(EXTRA_LDFLAGS))
+
+# Common includes and paths for CUDA
+INCLUDES  := -I../../common/inc 
+LIBRARIES := 
+
+################################################################################
+
+# CUDA code generation flags
+ifneq ($(OS_ARCH),armv7l)
+GENCODE_SM10    := -gencode arch=compute_10,code=sm_10
+endif
+GENCODE_SM20    := -gencode arch=compute_20,code=sm_20
+GENCODE_SM30    := -gencode arch=compute_30,code=sm_30 -gencode arch=compute_35,code=\"sm_35,compute_35\"
+GENCODE_FLAGS   := $(GENCODE_SM10) $(GENCODE_SM20) $(GENCODE_SM30)
+
+################################################################################
+
+# Target rules
+all: build
+
+build: BinCar
+
+main.o: main.cu
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+randgen.o: randgen.cpp 
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+read_data.o: read_data.cpp 
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+mcmc.o: mcmc.cpp 
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+covar.o: covar.cpp 
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+nifti1_read_write.o: nifti1_read_write.cpp 
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+cholesky.o: cholesky.cpp 
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS) -o $@ -c $<
+
+covarGPU.o: covarGPU.cu
+	$(NVCC) $(INCLUDES) $(ALL_CCFLAGS) $(GENCODE_FLAGS)  -o $@ -c $<
+
+BinCar: main.o mcmc.o randgen.o read_data.o covar.o nifti1_read_write.o cholesky.o covarGPU.o
+	$(NVCC) $(ALL_LDFLAGS) -o $@ $+ $(LIBRARIES) 
+	#mkdir -p ../../bin/$(OS_ARCH)/$(OSLOWER)/$(TARGET)$(if $(abi),/$(abi))
+	#cp $@ ../../bin/$(OS_ARCH)/$(OSLOWER)/$(TARGET)$(if $(abi),/$(abi))
+
+run: build
+	./BinCar
+
+clean:
+	rm -f BinCarGPU main.o mcmc.o randgen.o read_data.o covar.o nifti1_read.write.o cholesky.o covarGPU.o
+	#rm -rf ../../bin/$(OS_ARCH)/$(OSLOWER)/$(TARGET)$(if $(abi),/$(abi))/matrixMul
+
+clobber: clean

bsglmm/binCAR.h

@@ -0,0 +1,21 @@
+#define blocks_per_grid  512
+#define threads_per_block  512
+
+
+typedef struct subdata{
+	float *hostCovar;
+	float *deviceCovar;
+	float *hostZ;
+	float *deviceZ;
+} SUB;
+
+typedef struct idxtype{
+	int *hostVox;
+	int *deviceVox;
+	unsigned char *hostNBRS;
+	unsigned char *deviceNBRS;
+	int hostN;
+	int devN;
+} INDEX;
+
+