---
include: rocblas_common.yaml
include: known_bugs.yaml

Definitions:
  - &quick_matrix_size_range
    - { N:  -1,  lda:   1,  K:  1,  ldc:  1 } # bad n
    - { N:   2,  lda:   2,  K: -1,  ldc:  1 } # bad k
    - { N:   0,  lda:   3,  K:  3,  ldc:  3 } # n==0
    - { N:   3,  lda:   3,  K:  0,  ldc:  3 } # k==0
    - { N:   3,  lda:   1,  K:  1,  ldc:  3 } # bad lda if not transpose
    - { N:   1,  lda:   1,  K:  3,  ldc:  3 } # bad lda if transpose
    - { N:   3,  lda:   3,  K:  3,  ldc:  1 } # bad ldc

  - &tiny_matrix_size
    - { N:   199, lda:  199, K:  32,   ldc: 199 }
    #test the kernels which uses only gemm to compute syrk
    - { N:   2, lda:  501, K:  501,   ldc: 2 }

  - &medium_matrix_size_range
    - { N:   199, lda:  199, K:  32,   ldc: 199 }
    - { N:    88, lda:  200, K:  200,  ldc: 88 }
    #test the kernels which uses only gemm to compute syrk
    - { N:    51, lda:  201, K:  201,  ldc: 51 }
    - { N:    601, lda:  806, K:  805,  ldc: 601 }

  - &large_matrix_size_range
    - { N:  2011, lda:  2011, K:  253, ldc: 2048 }
    - { N:  2048, lda:  2048, K:  512, ldc: 2048 }
    - { N:  5000, lda:  5008, K:  164, ldc: 5000 }
    #test the kernels which uses only gemm to compute syrk
    - { N:  601, lda:  2001, K:  2001, ldc: 601 }
    - { N:  64, lda:  5000, K:  5000, ldc: 64 }

  - &matrix_size_kernel_scan
    - { N:  512, lda:  512, K:  512, ldc: 512 }

  - &alpha_beta_kernel_scan
    - { alpha:  1.0, alphai:  0.0, beta:  1.0, betai: 0.0 }
    - { alpha:  1.0, alphai:  0.0, beta: -1.0, betai: 0.0 }
    - { alpha:  1.0, alphai:  0.0, beta:  0.0, betai: 0.0 }
    - { alpha:  -1.0, alphai:  0.0, beta:  0.0, betai: 0.0 }
    - { alpha:  2.0, alphai:  0.0, beta:  0.0, betai: 0.0 }
    - { alpha:  0.5, alphai:  0.0, beta:  0.5, betai: 0.0 }

  - &alpha_beta_range
    - { alpha:  1.0, alphai:  0.0, beta:  1.0, betai: 0.0 }
    - { alpha: -2.0, alphai:  1.0, beta: -1.0, betai: 0.5 }
    - { alpha:  0.0, alphai:  0.0, beta:  1.0, betai: 0.0 } # quick success
    - { alpha:  0.0, alphai:  0.0, beta:  2.0, betai: 0.5 } # scale step only

  - &alpha_beta
    - { alpha: -1.0, alphai:  0.5, beta: -0.5, betai: 0.5 }
    # These larger values below on large_matrices require a tolerance rather than equality
    # due to least significant digit difference CPU to GPU on windows
    # I expect only accumulation difference from scheduling variation on windows
    # - { alpha: -2.1, alphai:  1.3, beta: -0.5, betai: 0.6 }

Tests:
  #
  # herk_ex
  #

- name: herk_ex_bad
  category: quick
  function:
  - herk_ex_bad_arg
  # - herk_ex_batched_bad_arg
  # - herk_ex_strided_batched_bad_arg
  precision: *herk_ex_precisions
  api: [ C, FORTRAN ]

- name: herk_ex_quick
  category: quick
  function: herk_ex
  precision: *herk_ex_precisions
  uplo: [ U, L ]
  transA: [ N, C ]
  matrix_size: *quick_matrix_size_range
  alpha_beta: *alpha_beta_range
  initialization: rand_int

- name: herk_ex_NaN
  category: pre_checkin
  function: herk_ex
  precision: *herk_ex_precisions
  uplo: [ U ]
  transA: [ N ]
  matrix_size: *tiny_matrix_size
  alpha: [ 2.0, .NaN ]  # NaN is converted to 0.0 in test code
  beta: [ 1.0, .NaN ]

- name: herk_ex_pre_checkin
  category: pre_checkin
  function: herk_ex
  precision: *herk_ex_precisions
  uplo: [ U, L ]
  transA: [ N, C ]
  matrix_size: *medium_matrix_size_range 
  alpha_beta: *alpha_beta_range
  devices: 1
  initialization: rand_int

- name: herk_ex_kernel_scan
  category: pre_checkin
  function: herk_ex
  precision: *herk_ex_precisions
  uplo: [ U, L ]
  transA: [ N, C ]
  matrix_size: *matrix_size_kernel_scan
  alpha_beta: *alpha_beta_kernel_scan
  initialization: hpl

- name: herk_ex_nighlty
  category: nightly
  function: herk_ex
  precision: *herk_ex_precisions
  uplo: [ U, L ]
  transA: [ N, C ]
  matrix_size: *large_matrix_size_range
  alpha_beta: *alpha_beta_range
  initialization: hpl

- name: herk_ex_graph_test
  category: pre_checkin
  function:
    - herk_ex
  precision: *herk_ex_precisions
  uplo: [ L ]
  transA: [ N, C ]
  matrix_size:
    - { N:   199, K:   33,  lda:  199,  ldc: 199 }
    - { N:    32, K:   32,  lda:  32,   ldc: 32 }
  alpha: [ 1 ]
  beta: [ 1 ]
  graph_test: true

- name: herk_ex_repeatability_check
  category: pre_checkin
  function: herk_ex
  precision: *herk_ex_precisions
  uplo: [ U, L ]
  transA: [ N, C ]
  matrix_size: *medium_matrix_size_range 
  alpha: [ 1 ]
  beta: [ 1 ]
  devices: 1
  repeatability_check: true
  initialization: hpl

...