Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Revert "Skein sp-mod #1" #65

Open
wants to merge 1 commit into
base: windows
Choose a base branch
from
Open

Revert "Skein sp-mod #1" #65

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 4 additions & 16 deletions cuda_helper.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -579,9 +579,7 @@ static __device__ __forceinline__ uint2 operator& (uint2 a, uint2 b) { return ma
static __device__ __forceinline__ uint2 operator| (uint2 a, uint2 b) { return make_uint2(a.x | b.x, a.y | b.y); }
static __device__ __forceinline__ uint2 operator~ (uint2 a) { return make_uint2(~a.x, ~a.y); }
static __device__ __forceinline__ void operator^= (uint2 &a, uint2 b) { a = a ^ b; }


/*static __device__ __forceinline__ uint2 operator+ (uint2 a, uint2 b)
static __device__ __forceinline__ uint2 operator+ (uint2 a, uint2 b)
{
uint2 result;
asm(
Expand All @@ -590,12 +588,6 @@ static __device__ __forceinline__ void operator^= (uint2 &a, uint2 b) { a = a ^
: "=r"(result.x), "=r"(result.y) : "r"(a.x), "r"(a.y), "r"(b.x), "r"(b.y));
return result;
}
*/
static __device__ __forceinline__ uint2 operator+ (uint2 a, uint2 b)
{
return vectorize(devectorize(a) + devectorize(b));
}


static __device__ __forceinline__ uint2 operator+ (uint2 a, uint32_t b)
{
Expand All @@ -606,7 +598,7 @@ static __device__ __forceinline__ uint2 operator+ (uint2 a, uint32_t b)
return result;
}

/**/

static __device__ __forceinline__ uint2 operator- (uint2 a, uint32_t b)
{
uint2 result;
Expand All @@ -616,7 +608,7 @@ static __device__ __forceinline__ uint2 operator- (uint2 a, uint32_t b)
return result;
}

/*

static __device__ __forceinline__ uint2 operator- (uint2 a, uint2 b)
{
uint2 result;
Expand All @@ -625,12 +617,7 @@ static __device__ __forceinline__ uint2 operator- (uint2 a, uint2 b)
: "=r"(result.x), "=r"(result.y) : "r"(a.x), "r"(a.y), "r"(b.x), "r"(b.y));
return result;
}
*/

static __device__ __forceinline__ uint2 operator- (uint2 a, uint2 b)
{
return vectorize(devectorize(a) - devectorize(b));
}


static __device__ __forceinline__ uint4 operator^ (uint4 a, uint4 b) { return make_uint4(a.x ^ b.x, a.y ^ b.y, a.z ^ b.z, a.w ^ b.w); }
Expand Down Expand Up @@ -763,6 +750,7 @@ __device__ __inline__ uint2 ROL24(const uint2 a)
}



#if __CUDA_ARCH__ >= 350
__inline__ __device__ uint2 ROL2(const uint2 a, const int offset) {
uint2 result;
Expand Down
Loading