About the make_tensor function

[LANSHANGH]

`template <class ProblemShape, class CtaTiler, class TA, class AStride, class TB, class BStride, class TC, class CStride> global static void mak_tensor(ProblemShape shape_MNK, CtaTiler cta_tiler, TA const* A, AStride dA, TB const* B, BStride dB, TC const* C, CStride dC
) { using namespace cute;

// Preconditions

// // Full and Tiled Tensors //

// Represent the full tensors Tensor mA = make_tensor(make_gmem_ptr(A), select<0,2>(shape_MNK), dA); // (M,K) Tensor mB = make_tensor(make_gmem_ptr(B), select<1,2>(shape_MNK), dB); // (N,K) Tensor mC = make_tensor(make_gmem_ptr(C), select<0,1>(shape_MNK), dC); // (M,N)

// Get the appropriate blocks for this thread block auto cta_coord = make_coord(blockIdx.x, blockIdx.y, _); // (m,n,k) Tensor gA = local_tile(mA, cta_tiler, cta_coord, Step<_1, X,_1>{}); // (BLK_M,BLK_K,k) Tensor gB = local_tile(mB, cta_tiler, cta_coord, Step< X,_1,_1>{}); // (BLK_N,BLK_K,k) Tensor gC = local_tile(mC, cta_tiler, cta_coord, Step<_1,_1, X>{}); // (BLK_M,BLK_N) #if 1 if(thread0()) { print(" mB : "); print( mB); print("\n"); // print(" gB : "); print( gB); print("\n"); // print(" sB : "); print( (sB)); print("\n"); // print("tBgB : "); print(tBgB); print("\n"); // print("tBsB : "); print(tBsB); print("\n"); // print("tArA : "); print(tArA); print("\n"); } #endif // (BLK_N,BLK_K) }`

cudaErrorLaunchFailure: unspecified launch failure

I don't know why make_tensor call inside kernel function must provide ld step parameter, otherwise it will report error, but call outside kernel function can not provide ld parameter, I don't know why, hope you can give me an answer, thank you

[Junkai-Wu]

I don't quite understand what's your issue here from the description above. From my observation, there is only one type of make_tensor call here:

Tensor mA = make_tensor(make_gmem_ptr(A), select<0,2>(shape_MNK), dA); // (M,K)
Tensor mB = make_tensor(make_gmem_ptr(B), select<1,2>(shape_MNK), dB); // (N,K)
Tensor mC = make_tensor(make_gmem_ptr(C), select<0,1>(shape_MNK), dC); // (M,N)

The other one is just your global function name. Could you state your issue more specifically?

[LANSHANGH]

What I'm trying to say is that make_tensor creates a tensor of the same shape, sometimes it works, sometimes it doesn't, and here I'm using make_tensor inside a CUDA kernel where I have to provide ld arguments, otherwise I'll get an error, If I call make_tensor from inside the kernel instead of inside the main function, I can still succeed without providing ld arguments, I don't know why.

[thakkarV]

sometimes it works, sometimes it doesn't

What does this mean?

This launch error likely has nothing to do with make tensor. Please provide your full repro steps starting at cd-ing into the build directory

[github-actions[bot]]

This issue has been labeled inactive-30d due to no recent activity in the past 30 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed. This issue will be labeled inactive-90d if there is no activity in the next 60 days.

[github-actions[bot]]

This issue has been labeled inactive-90d due to no recent activity in the past 90 days. Please close this issue if no further response or action is needed. Otherwise, please respond with a comment indicating any updates or changes to the original issue and/or confirm this issue still needs to be addressed.