Modify the examples run in github workflow

[FMarno]

This uses the test_examples target instead of manually specifying examples.

[aacostadiaz]

Thanks!!

[FMarno]

Before:

Run export LD_LIBRARY_PATH=~/dpcpp/lib/:$LD_LIBRARY_PATH
Run sgemm_1
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [24631.0]GFlop/s  (8.7186)ms
Run sgemm_2
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [25928.6]GFlop/s  (8.2823)ms
Run sgemm_sm70
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [31439.5]GFlop/s  (6.8305)ms
Run sgemm_sm80
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [32349.5]GFlop/s  (6.6384)ms
Run tiled_copy
Success.

After

Run export LD_LIBRARY_PATH=~/dpcpp/lib/:$LD_LIBRARY_PATH
[0/2] Re-checking globbed directories...
[1/6] cd /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial && /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial/tiled_copy
Success.
[2/6] cd /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/14_ampere_tf32_tensorop_gemm && /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/14_ampere_tf32_tensorop_gemm/14_ampere_tf32_tensorop_gemm_cute
  Disposition: Passed
  Problem Size: 5120x4096x4096x1
  Avg runtime: 6.6197 ms
  GFLOPS: 25952.6
[3/6] cd /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial && /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial/sgemm_1
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [8017.0]GFlop/s  (26.7866)ms
[4/6] cd /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial && /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial/sgemm_sm70
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [7359.0]GFlop/s  (29.1818)ms
[5/6] cd /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial && /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial/sgemm_sm80
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [7430.4]GFlop/s  (28.9013)ms
[6/6] cd /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial && /home/docker/actions-runner/_work/cutlass-fork/cutlass-fork/examples/cute/tutorial/sgemm_2
M = 5120
N = 5120
K = 4096
C = A^N B^T
CUTE_GEMM:     [7032.0]GFlop/s  (30.5388)ms

There is now an additional example running