CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
335 lines
8.4 KiB
YAML
335 lines
8.4 KiB
YAML
---
|
|
include: rocblas_common.yaml
|
|
include: known_bugs.yaml
|
|
|
|
Definitions:
|
|
- &size_t_matrix_size_range
|
|
- { N: 4097, K: 6, lda: 1048600, incx: 1 }
|
|
- { N: 4097, K: 6, lda: 6, incx: 1048600 }
|
|
|
|
- &small_matrix_size_range
|
|
- { N: 4, K: 2, lda: 10 }
|
|
- { N: 10, K: 2, lda: 10 }
|
|
- { N: 10, K: 8, lda: 9 }
|
|
- { N: 1, K: 0, lda: 1 }
|
|
- { N: 10, K: 10, lda: 2 }
|
|
- { N: 9, K: 9, lda: 20 }
|
|
- { N: 9, K: 15, lda: 20 }
|
|
- { N: 9, K: 10, lda: 11 }
|
|
- { N: 100, K: 60, lda: 65 }
|
|
|
|
- &special_case_range
|
|
- { N: 0, K: 0, lda: 1, incx: 1, batch_count: 1 }
|
|
- { N: 1, K: 1, lda: 2, incx: 1, batch_count: 0 }
|
|
|
|
- { N: -1, K: 0, lda: 1, incx: 1, batch_count: 0 }
|
|
- { N: 0, K: -1, lda: 1, incx: 1, batch_count: 0 }
|
|
- { N: 0, K: 0, lda: 0, incx: 1, batch_count: 0 }
|
|
- { N: 0, K: 4, lda: 4, incx: 1, batch_count: 0 }
|
|
- { N: 0, K: 0, lda: 1, incx: 0, batch_count: 0 }
|
|
- { N: 0, K: 0, lda: 1, incx: 1, batch_count: -1 }
|
|
|
|
- &manybatch_range
|
|
- { N: 10, K: 5, lda: 7 }
|
|
- { N: 150, K: 125, lda: 151 }
|
|
|
|
- &medium_matrix_size_range
|
|
- { N: 63, K: 8, lda: 128 }
|
|
- { N: 65, K: 8, lda: 10 }
|
|
- { N: 65, K: 12, lda: 128 }
|
|
- { N: 65, K: 32, lda: 128 }
|
|
- { N: 64, K: 8, lda: 128 }
|
|
- { N: 64, K: 45, lda: 128 }
|
|
- { N: 127, K: 8, lda: 127 }
|
|
- { N: 127, K: 100, lda: 101 }
|
|
- { N: 128, K: 20, lda: 128 }
|
|
- { N: 128, K: 60, lda: 63 }
|
|
- { N: 128, K: 63, lda: 128 }
|
|
- { N: 128, K: 64, lda: 128 }
|
|
- { N: 128, K: 100, lda: 128 }
|
|
- { N: 512, K: 256, lda: 512 }
|
|
- { N: 512, K: 5, lda: 512 }
|
|
- { N: 512, K: 9, lda: 512 }
|
|
- { N: 512, K: 20, lda: 511 }
|
|
- { N: 600, K: 500, lda: 601 }
|
|
|
|
- &large_matrix_size_range
|
|
- { N: 1000, K: 5, lda: 1000 }
|
|
- { N: 2000, K: 1999, lda: 2000 }
|
|
- { N: 4011, K: 512, lda: 550 }
|
|
|
|
- &incx_range
|
|
- { incx: -5 }
|
|
- { incx: 1 }
|
|
- { incx: 10 }
|
|
|
|
- &incx_range_small
|
|
- { incx: 2 }
|
|
|
|
|
|
Tests:
|
|
- name: tbmv_bad_arg
|
|
category: quick
|
|
function:
|
|
- tbmv_bad_arg
|
|
- tbmv_batched_bad_arg
|
|
- tbmv_strided_batched_bad_arg
|
|
precision: *single_double_precisions
|
|
uplo: U
|
|
transA: N
|
|
diag: N
|
|
api: [ C, FORTRAN, FORTRAN_64 ]
|
|
|
|
- name: tbmv_arg_check
|
|
category: quick
|
|
function:
|
|
- tbmv: *single_double_precisions
|
|
- tbmv_batched: *single_double_precisions
|
|
- tbmv_strided_batched: *single_double_precisions
|
|
uplo: L
|
|
transA: N
|
|
diag: N
|
|
matrix_size: *special_case_range
|
|
|
|
- name: tbmv_fortran
|
|
category: quick
|
|
function: tbmv
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *small_matrix_size_range
|
|
incx_incy: *incx_range_small
|
|
api: FORTRAN
|
|
|
|
- name: tbmv_batched_fortran
|
|
category: quick
|
|
function: tbmv_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *small_matrix_size_range
|
|
incx_incy: *incx_range_small
|
|
batch_count: [ -1, 0, 3 ]
|
|
api: FORTRAN
|
|
|
|
- name: tbmv_strided_batched_fortran
|
|
category: quick
|
|
function: tbmv_strided_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *small_matrix_size_range
|
|
incx_incy: *incx_range_small
|
|
batch_count: [ 3 ]
|
|
stride_scale: [ 2 ]
|
|
api: FORTRAN
|
|
|
|
- name: tbmv_small
|
|
category: quick
|
|
function: tbmv
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *small_matrix_size_range
|
|
incx_incy: *incx_range
|
|
|
|
- name: tbmv_batched_small
|
|
category: quick
|
|
function: tbmv_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *small_matrix_size_range
|
|
incx_incy: *incx_range
|
|
batch_count: [ 3 ]
|
|
|
|
- name: tbmv_strided_batched_small
|
|
category: quick
|
|
function: tbmv_strided_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *small_matrix_size_range
|
|
incx_incy: *incx_range
|
|
stride_scale: [ 2 ]
|
|
batch_count: [ 3 ]
|
|
|
|
- name: tbmv_medium
|
|
category: pre_checkin
|
|
function: tbmv
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *medium_matrix_size_range
|
|
incx_incy: *incx_range
|
|
|
|
- name: tbmv_batched_medium
|
|
category: pre_checkin
|
|
function: tbmv_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
batch_count: [3]
|
|
matrix_size: *medium_matrix_size_range
|
|
incx_incy: *incx_range
|
|
|
|
- name: tbmv_strided_batched_medium
|
|
category: pre_checkin
|
|
function: tbmv_strided_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
stride_scale: [ 1 ]
|
|
batch_count: [3]
|
|
matrix_size: *medium_matrix_size_range
|
|
incx_incy: *incx_range
|
|
|
|
- name: tbmv_large
|
|
category: nightly
|
|
function: tbmv
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *large_matrix_size_range
|
|
incx_incy: *incx_range_small
|
|
batch_count: [ 3 ]
|
|
|
|
- name: tbmv_batched_large
|
|
category: nightly
|
|
function: tbmv_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *large_matrix_size_range
|
|
incx_incy: *incx_range_small
|
|
batch_count: [ 3 ]
|
|
|
|
- name: tbmv_batched_grid_z_16bit
|
|
category: stress
|
|
arguments:
|
|
- { N: 3, K: 3, lda: 3, incx: 1, batch_count: *c_grid_yz_require_passes }
|
|
uplo: [ U, L ]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
pointer_mode_host: false
|
|
function:
|
|
- tbmv_batched: *single_precision
|
|
- tbmv_strided_batched: *single_precision
|
|
stride_scale: 1
|
|
|
|
- name: tbmv_strided_batched_large
|
|
category: nightly
|
|
function: tbmv_strided_batched
|
|
precision: *single_double_precisions_complex_real
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [U, N]
|
|
matrix_size: *large_matrix_size_range
|
|
incx_incy: *incx_range_small
|
|
stride_scale: [ 1 ]
|
|
batch_count: [ 3 ]
|
|
|
|
- name: tbmv_batched_manybatch
|
|
category: nightly
|
|
function: tbmv_batched
|
|
precision: *single_double_precisions
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [N]
|
|
matrix_size: *manybatch_range
|
|
incx_incy: *incx_range_small
|
|
batch_count: [256]
|
|
|
|
- name: tbmv_strided_batched_manybatch
|
|
category: nightly
|
|
function: tbmv_strided_batched
|
|
precision: *single_double_precisions
|
|
uplo: [U, L]
|
|
transA: [ N, T, C ]
|
|
diag: [N]
|
|
matrix_size: *manybatch_range
|
|
incx_incy: *incx_range_small
|
|
stride_scale: [ 1.5 ]
|
|
batch_count: [256]
|
|
|
|
- name: tbmv_ILP64
|
|
category: stress
|
|
arguments:
|
|
# - { N: 2147483649, K: 1, lda: 1, incx: 1, batch_count: 1 }
|
|
# - { N: 2, K: 2147483649, lda: 2147483650, incx: 1, batch_count: 1 }
|
|
- { N: 2, K: 2, lda: 2147483649, incx: 1, batch_count: 1 }
|
|
- { N: 2, K: 2, lda: 2, incx: 2147483649, batch_count: 1 }
|
|
- { N: 2, K: 2, lda: 2, incx: 1, batch_count: *c_grid_yz_require_passes }
|
|
uplo: [ U, L ]
|
|
transA: [ N, T ]
|
|
diag: [ N ]
|
|
stride_scale: [ 1 ]
|
|
api: [ C_64 ]
|
|
os_flags: [ LINUX ]
|
|
function:
|
|
- tbmv: *single_precision
|
|
- tbmv_batched: *single_precision
|
|
- tbmv_strided_batched: *single_precision
|
|
|
|
- name: tbmv_graph_test
|
|
category: pre_checkin
|
|
function:
|
|
- tbmv
|
|
- tbmv_batched
|
|
- tbmv_strided_batched
|
|
precision: *single_double_precisions_complex_real
|
|
matrix_size:
|
|
- { N: 100, K: 60, lda: 65 }
|
|
uplo: [ U ]
|
|
transA: [ N ]
|
|
diag: [ N ]
|
|
stride_scale: [ 1 ]
|
|
batch_count: [3]
|
|
incx_incy: *incx_range
|
|
graph_test: true
|
|
|
|
- name: tbmv_size_t
|
|
category: stress
|
|
function: tbmv
|
|
precision: *single_precision
|
|
matrix_size: *size_t_matrix_size_range
|
|
uplo: [ U, L ]
|
|
transA: [ N, T ]
|
|
diag: [ U, N ]
|
|
gpu_arch: ['90a','942','950']
|
|
os_flags: LINUX
|
|
|
|
- name: tbmv_repeatability_check
|
|
category: stress
|
|
function:
|
|
- tbmv
|
|
- tbmv_batched
|
|
- tbmv_strided_batched
|
|
precision: *single_double_precisions_complex_real
|
|
matrix_size:
|
|
- { N: 100, K: 60, lda: 65 }
|
|
uplo: [ U ]
|
|
transA: [ N ]
|
|
diag: [ N ]
|
|
stride_scale: [ 1 ]
|
|
batch_count: [2]
|
|
incx_incy: *incx_range
|
|
initialization: hpl
|
|
atomics_mode: 0
|
|
pointer_mode_host: false
|
|
iters: 5
|
|
devices: 4
|
|
repeatability_check: true
|
|
...
|