gemm! fails for some combinations of transpose characters

[jdnz]

using OpenCL
import OpenCL.cl.CLArray
import CLBLAS

CLBLAS.setup()
device, ctx, queue = CLBLAS.get_next_compute_context()

hA = rand(5, 10) + im*rand(5, 10)
hB = rand(10, 5) + im*rand(10, 5)
hC = rand(5, 5) + im*rand(5, 5)
hC2 = rand(10, 10) + im*rand(10, 10)

A = CLArray(queue, hA)
B = CLArray(queue, hB)
C = CLArray(queue, hC)
C2 = CLArray(queue, hC2)

BLAS.gemm!('N', 'N', complex(1.0), hA, hB, complex(0.0), hC)
CLBLAS.gemm!('N', 'N', complex(1.0), A, B, complex(0.0), C)
hC ≈ cl.to_host(C) # true

BLAS.gemm!('T', 'T', complex(1.0), hA, hB, complex(0.0), hC2)
CLBLAS.gemm!('T', 'T', complex(1.0), A, B, complex(0.0), C2) # produces error CLError(code=-1016, CL_UNKNOWN_ERROR_CODE)

BLAS.gemm!('C', 'C', complex(1.0), hA, hB, complex(0.0), hC2)
CLBLAS.gemm!('C', 'C', complex(1.0), A, B, complex(0.0), C2)
hC2 ≈ cl.to_host(C2) # false

BLAS.gemm!('T', 'N', complex(1.0), hA, hA, complex(0.0), hC2)
CLBLAS.gemm!('T', 'N', complex(1.0), A, A, complex(0.0), C2) # produces error CLError(code=-1016, CL_UNKNOWN_ERROR_CODE)

Examples with real numbers also fail.