-
Notifications
You must be signed in to change notification settings - Fork 147
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[GCU] update to develop and fix kernels #1438
Open
EnflameGCU
wants to merge
3
commits into
PaddlePaddle:develop
Choose a base branch
from
EnflameGCU:gcu_develop
base: develop
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Thanks for your contribution! |
Test project /home/***/PaddleCustomDevice/backends/gcu/build
Start 1: test_accuracy
1/103 Test #1: test_accuracy .......................... Passed 1.97 sec
Start 2: test_add_n
2/103 Test #2: test_add_n ............................. Passed 1.81 sec
Start 3: test_arange
3/103 Test #3: test_arange ............................ Passed 1.66 sec
Start 4: test_argmax
4/103 Test #4: test_argmax ............................ Passed 1.67 sec
Start 5: test_argmin
5/103 Test #5: test_argmin ............................ Passed 1.67 sec
Start 6: test_argsort
6/103 Test #6: test_argsort ........................... Passed 1.80 sec
Start 7: test_assign
7/103 Test #7: test_assign ............................ Passed 1.62 sec
Start 8: test_atan2
8/103 Test #8: test_atan2 ............................. Passed 1.62 sec
Start 9: test_batch_norm
9/103 Test #9: test_batch_norm ........................ Passed 3.81 sec
Start 10: test_binary_ops
10/103 Test #10: test_binary_ops ........................ Passed 2.02 sec
Start 11: test_bitwise_ops
11/103 Test #11: test_bitwise_ops ....................... Passed 1.79 sec
Start 12: test_cast
12/103 Test #12: test_cast .............................. Passed 1.69 sec
Start 13: test_cholesky
13/103 Test #13: test_cholesky .......................... Passed 1.62 sec
Start 14: test_clip
14/103 Test #14: test_clip .............................. Passed 1.65 sec
Start 15: test_compare_ops
15/103 Test #15: test_compare_ops ....................... Passed 1.84 sec
Start 16: test_concat
16/103 Test #16: test_concat ............................ Passed 1.83 sec
Start 17: test_contiguous
17/103 Test #17: test_contiguous ........................ Passed 2.93 sec
Start 18: test_conv_ops
18/103 Test #18: test_conv_ops .......................... Passed 1.82 sec
Start 19: test_conv_transpose_ops
19/103 Test #19: test_conv_transpose_ops ................ Passed 1.69 sec
Start 20: test_copysign
20/103 Test #20: test_copysign .......................... Passed 1.61 sec
Start 21: test_cross
21/103 Test #21: test_cross ............................. Passed 1.70 sec
Start 22: test_cumulate_ops
22/103 Test #22: test_cumulate_ops ...................... Passed 1.68 sec
Start 23: test_diag
23/103 Test #23: test_diag .............................. Passed 1.63 sec
Start 24: test_diagonal
24/103 Test #24: test_diagonal .......................... Passed 1.64 sec
Start 25: test_dropout
25/103 Test #25: test_dropout ........................... Passed 1.63 sec
Start 26: test_einsum
26/103 Test #26: test_einsum ............................ Passed 1.73 sec
Start 27: test_embedding
27/103 Test #27: test_embedding ......................... Passed 1.66 sec
Start 28: test_expand
28/103 Test #28: test_expand ............................ Passed 1.66 sec
Start 29: test_expand_as
29/103 Test #29: test_expand_as ......................... Passed 1.66 sec
Start 30: test_eye_kernel
30/103 Test #30: test_eye_kernel ........................ Passed 1.62 sec
Start 31: test_fc
31/103 Test #31: test_fc ................................ Passed 1.94 sec
Start 32: test_flatten
32/103 Test #32: test_flatten ........................... Passed 1.62 sec
Start 33: test_flip
33/103 Test #33: test_flip .............................. Passed 1.78 sec
Start 34: test_full
34/103 Test #34: test_full .............................. Passed 1.68 sec
Start 35: test_fused_add_rms_norm
35/103 Test #35: test_fused_add_rms_norm ................ Passed 3.41 sec
Start 36: test_fused_conv2d_add
36/103 Test #36: test_fused_conv2d_add .................. Passed 1.72 sec
Start 37: test_fused_conv2d_add_act
37/103 Test #37: test_fused_conv2d_add_act .............. Passed 1.88 sec
Start 38: test_fused_conv2d_transpose_bias_act
38/103 Test #38: test_fused_conv2d_transpose_bias_act ... Passed 1.80 sec
Start 39: test_fused_rotary_embedding
39/103 Test #39: test_fused_rotary_embedding ............ Passed 5.84 sec
Start 40: test_fused_sdp_flash_attention
40/103 Test #40: test_fused_sdp_flash_attention ......... Passed 10.44 sec
Start 41: test_gather_nd
41/103 Test #41: test_gather_nd ......................... Passed 1.67 sec
Start 42: test_gather_op
42/103 Test #42: test_gather_op ......................... Passed 1.66 sec
Start 43: test_gaussian_random
43/103 Test #43: test_gaussian_random ................... Passed 1.64 sec
Start 44: test_grid_sample
44/103 Test #44: test_grid_sample ....................... Passed 1.62 sec
Start 45: test_huber_loss
45/103 Test #45: test_huber_loss ........................ Passed 1.66 sec
Start 46: test_increment
46/103 Test #46: test_increment ......................... Passed 1.64 sec
Start 47: test_index_add
47/103 Test #47: test_index_add ......................... Passed 1.69 sec
Start 48: test_index_put
48/103 Test #48: test_index_put ......................... Passed 1.67 sec
Start 49: test_index_sample
49/103 Test #49: test_index_sample ...................... Passed 1.69 sec
Start 50: test_index_select
50/103 Test #50: test_index_select ...................... Passed 1.69 sec
Start 51: test_instance_norm
51/103 Test #51: test_instance_norm ..................... Passed 1.69 sec
Start 52: test_interpolate
52/103 Test #52: test_interpolate ....................... Passed 1.73 sec
Start 53: test_is_empty
53/103 Test #53: test_is_empty .......................... Passed 1.61 sec
Start 54: test_isclose
54/103 Test #54: test_isclose ........................... Passed 1.74 sec
Start 55: test_isfinite
55/103 Test #55: test_isfinite .......................... Passed 1.65 sec
Start 56: test_isinf
56/103 Test #56: test_isinf ............................. Passed 1.62 sec
Start 57: test_isnan
57/103 Test #57: test_isnan ............................. Passed 1.63 sec
Start 58: test_layer_norm
58/103 Test #58: test_layer_norm ........................ Passed 1.74 sec
Start 59: test_lerp
59/103 Test #59: test_lerp .............................. Passed 1.68 sec
Start 60: test_log_loss
60/103 Test #60: test_log_loss .......................... Passed 1.71 sec
Start 61: test_log_softmax
61/103 Test #61: test_log_softmax ....................... Passed 1.65 sec
Start 62: test_logcumsumexp
62/103 Test #62: test_logcumsumexp ...................... Passed 1.68 sec
Start 63: test_logical_ops
63/103 Test #63: test_logical_ops ....................... Passed 1.72 sec
Start 64: test_logsumexp
64/103 Test #64: test_logsumexp ......................... Passed 1.68 sec
Start 65: test_masked_select
65/103 Test #65: test_masked_select ..................... Passed 1.60 sec
Start 66: test_matmul
66/103 Test #66: test_matmul ............................ Passed 14.58 sec
Start 67: test_mean_all
67/103 Test #67: test_mean_all .......................... Passed 1.63 sec
Start 68: test_meshgrid
68/103 Test #68: test_meshgrid .......................... Passed 1.96 sec
Start 69: test_multinomial
69/103 Test #69: test_multinomial ....................... Passed 1.64 sec
Start 70: test_numel
70/103 Test #70: test_numel ............................. Passed 1.62 sec
Start 71: test_one_hot
71/103 Test #71: test_one_hot ........................... Passed 1.67 sec
Start 72: test_pool2d
72/103 Test #72: test_pool2d ............................ Passed 6.95 sec
Start 73: test_reduce_ops
73/103 Test #73: test_reduce_ops ........................ Passed 1.88 sec
Start 74: test_rms_norm
74/103 Test #74: test_rms_norm .......................... Passed 2.59 sec
Start 75: test_rnn
75/103 Test #75: test_rnn ............................... Passed 1.77 sec
Start 76: test_roll
76/103 Test #76: test_roll .............................. Passed 1.75 sec
Start 77: test_scale
77/103 Test #77: test_scale ............................. Passed 1.68 sec
Start 78: test_scatter
78/103 Test #78: test_scatter ........................... Passed 1.68 sec
Start 79: test_set_value
79/103 Test #79: test_set_value ......................... Passed 2.71 sec
Start 80: test_sign
80/103 Test #80: test_sign .............................. Passed 1.69 sec
Start 81: test_slice
81/103 Test #81: test_slice ............................. Passed 1.65 sec
Start 82: test_softmax
82/103 Test #82: test_softmax ........................... Passed 1.66 sec
Start 83: test_split
83/103 Test #83: test_split ............................. Passed 8.62 sec
Start 84: test_squeeze
84/103 Test #84: test_squeeze ........................... Passed 1.61 sec
Start 85: test_stack
85/103 Test #85: test_stack ............................. Passed 1.97 sec
Start 86: test_strided_slice
86/103 Test #86: test_strided_slice ..................... Passed 1.66 sec
Start 87: test_swiglu
87/103 Test #87: test_swiglu ............................ Passed 7.47 sec
Start 88: test_take_along_axis
88/103 Test #88: test_take_along_axis ................... Passed 1.62 sec
Start 89: test_tile
89/103 Test #89: test_tile .............................. Passed 1.65 sec
Start 90: test_topk
90/103 Test #90: test_topk .............................. Passed 2.27 sec
Start 91: test_transpose
91/103 Test #91: test_transpose ......................... Passed 3.61 sec
Start 92: test_tril_triu
92/103 Test #92: test_tril_triu ......................... Passed 1.67 sec
Start 93: test_trunc
93/103 Test #93: test_trunc ............................. Passed 1.63 sec
Start 94: test_unary_ops
94/103 Test #94: test_unary_ops ......................... Passed 2.37 sec
Start 95: test_unbind
95/103 Test #95: test_unbind ............................ Passed 1.88 sec
Start 96: test_uniform_random
96/103 Test #96: test_uniform_random .................... Passed 1.65 sec
Start 97: test_unsqueeze
97/103 Test #97: test_unsqueeze ......................... Passed 1.61 sec
Start 98: test_unstack
98/103 Test #98: test_unstack ........................... Passed 1.88 sec
Start 99: test_where
99/103 Test #99: test_where ............................. Passed 2.14 sec
Start 100: test_conv_bn_hard_swish_pass
100/103 Test #100: test_conv_bn_hard_swish_pass ........... Passed 14.08 sec
Start 101: test_conv_bn_pass
101/103 Test #101: test_conv_bn_pass ...................... Passed 9.96 sec
Start 102: test_conv_bn_relu_pass
102/103 Test #102: test_conv_bn_relu_pass ................. Passed 14.24 sec
Start 103: test_custom_pass_gcu
103/103 Test #103: test_custom_pass_gcu ................... Passed 6.13 sec
100% tests passed, 0 tests failed out of 103
Total Test time (real) = 268.49 sec
|
EnflameGCU
changed the title
update to develop and fix kernels
[GCU] update to develop and fix kernels
Nov 1, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
develop
关于PIR
开关的控制;conv
系列kernels
中padding
和dilation
的计算问题;full kernel
空tensor
问题。