- template runs/passes with CUDA 3.1, but requires that CUDA 2.3

is installed for math intrinsics used in instructions.cc (since
CUDA 3.1 does not seem to define __uint2float).
- currently cuda-math.h has hardcoded paths to my own install of
CUDA 2.3 (need to determine whether we can build simulator with
CUDA 2.3 and run CUDA 3.1 / compute_2x PTX, or need to make 
current setup more portable)
- modified ptxinfo.l to print out meaningful error message if 
error occurs on first line
- modified ptxinfo.l,y to understand "for 'compute_NN'" syntax
- updated template to 3.1 SDK version  
- updated cuda_runtime_api.cc to select highest compute capability
version when multiple versions are present.
- updated template/BlackScholes Makefiles to generate a "DLL build"
instead of static linked build (still confusing... requires one to
copy config files... probably need to modify config scripts)

[git-p4: depot-paths = "//depot/gpgpu_sim_research/fermi/distribution/": change = 6837]

1 files changed, 8 insertions, 15 deletions

diff --git a/src/cuda-sim/cuda-math.h b/src/cuda-sim/cuda-math.h
index ea7f5fd..5abf4f3 100644
--- a/src/cuda-sim/cuda-math.h
+++ b/src/cuda-sim/cuda-math.h
@@ -47,7 +47,6 @@ namespace cuda_math {
 #define __attribute__(a) // to remove warnings inside math_functions.h
 #undef INT_MAX
 
-#if CUDART_VERSION < 3000
 // DEVICE_BUILTIN
    struct int4 {
       int x, y, z, w;
@@ -70,27 +69,21 @@ namespace cuda_math {
    typedef struct float2 float2;
 
 extern float rsqrtf(float); // CUDA 2.3 beta
-#else
-#define UINT_MAX ((unsigned int)-1)
-#endif
 
+#if CUDART_VERSION < 3000
 #define CUDA_FLOAT_MATH_FUNCTIONS
 #include <device_types.h>
 #define __CUDA_INTERNAL_COMPILATION__
-#if CUDART_VERSION >= 3000
-#define __CUDACC__
-#include <device_functions.h>
-#else
 #include <math_functions.h>
-#endif
 #undef __CUDA_INTERNAL_COMPILATION__
 #undef __attribute__
-
-#if CUDART_VERSION >= 3000
-#define __internal_float2int float2int
-#define __internal_float2uint float2uint
-#include <math.h>
-#define __internal_accurate_fdividef fdividef
+#else
+#define CUDA_FLOAT_MATH_FUNCTIONS
+#include "/home/taamodt/nvcuda/2.3/cuda/include/device_types.h"
+#define __CUDA_INTERNAL_COMPILATION__
+#include "/home/taamodt/nvcuda/2.3/cuda/include/math_functions.h"
+#undef __CUDA_INTERNAL_COMPILATION__
+#undef __attribute__
 #endif
 
 }