Skip to content
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

Update matmul variant configuration for heatmap #316

Merged
merged 1 commit into from
Oct 10, 2024

Conversation

compor
Copy link
Contributor

@compor compor commented Oct 9, 2024

No description provided.

@compor compor requested review from superlopuh and nazavode October 9, 2024 12:14
@compor compor self-assigned this Oct 9, 2024
Copy link

github-actions bot commented Oct 9, 2024

kernels,baseline,linalg,linalg_xdsl,snitch_stream,snrt
conv2d_d1_s1_3x3 4x4xf64,667,858,308,,
ddot 128xf64,956,965,,213,577
dense 8x8xf64,3206,3530,,2741,2723
fill 4x4xf64,50,50,64,,
matmul 4x16x8xf64,2495,2694,708,,
matmul_transb 4x16x16xf32,3386,,,845,849
pooling_nchw_max_d1_s2_3x3 4x4xf64,584,484,275,,
pooling_nchw_sum_d1_s2_3x3 4x4xf64,902,832,271,,
relu 4x4xf64,142,125,72,,
relu 4x8xf32,297,210,,67,85
saxpy 64xf32,634,634,,,140
sum 4x4xf64,129,162,87,,
sum 4x8xf32,238,247,87,,72
sum 8x8xf16,821,,65,,

Copy link

github-actions bot commented Oct 9, 2024

kernels,baseline,linalg,linalg_xdsl,snitch_stream,snrt
conv2d_d1_s1_3x3 4x4xf64,0.22,0.17,0.58,,
ddot 128xf64,0.13,0.13,,0.64,0.22
dense 8x8xf64,0.20,0.18,,0.26,0.26
fill 4x4xf64,0.02,0.02,0.28,,
matmul 4x16x8xf64,0.21,0.19,0.82,,
matmul_transb 4x16x16xf32,0.21,,,0.76,0.79
pooling_nchw_max_d1_s2_3x3 4x4xf64,0.39,0.30,0.65,,
pooling_nchw_sum_d1_s2_3x3 4x4xf64,0.22,0.17,0.66,,
relu 4x4xf64,0.13,0.14,0.25,,
relu 4x8xf32,0.33,0.16,,0.28,0.22
saxpy 64xf32,0.10,0.10,,,0.46
sum 4x4xf64,0.13,0.10,0.20,,
sum 4x8xf32,0.14,0.13,0.20,,0.24
sum 8x8xf16,0.31,,0.26,,

@compor compor merged commit 1c387b6 into main Oct 10, 2024
1 check passed
@compor compor deleted the christos/update-heatmap-config branch October 10, 2024 07:39
Copy link

kernels,baseline,linalg,linalg_xdsl,snitch_stream,snrt
conv2d_d1_s1_3x3 4x4xf64,667,858,308,,
ddot 128xf64,956,965,,213,577
dense 8x8xf64,3206,3530,,2741,2723
fill 4x4xf64,50,50,64,,
matmul 4x16x8xf64,2495,2694,708,,
matmul_transb 4x16x16xf32,3386,,,845,849
pooling_nchw_max_d1_s2_3x3 4x4xf64,584,484,275,,
pooling_nchw_sum_d1_s2_3x3 4x4xf64,902,832,271,,
relu 4x4xf64,142,125,72,,
relu 4x8xf32,297,210,,67,85
saxpy 64xf32,634,634,,,140
sum 4x4xf64,129,162,87,,
sum 4x8xf32,238,247,87,,72
sum 8x8xf16,821,,65,,

Copy link

kernels,baseline,linalg,linalg_xdsl,snitch_stream,snrt
conv2d_d1_s1_3x3 4x4xf64,0.22,0.17,0.58,,
ddot 128xf64,0.13,0.13,,0.64,0.22
dense 8x8xf64,0.20,0.18,,0.26,0.26
fill 4x4xf64,0.02,0.02,0.28,,
matmul 4x16x8xf64,0.21,0.19,0.82,,
matmul_transb 4x16x16xf32,0.21,,,0.76,0.79
pooling_nchw_max_d1_s2_3x3 4x4xf64,0.39,0.30,0.65,,
pooling_nchw_sum_d1_s2_3x3 4x4xf64,0.22,0.17,0.66,,
relu 4x4xf64,0.13,0.14,0.25,,
relu 4x8xf32,0.33,0.16,,0.28,0.22
saxpy 64xf32,0.10,0.10,,,0.46
sum 4x4xf64,0.13,0.10,0.20,,
sum 4x8xf32,0.14,0.13,0.20,,0.24
sum 8x8xf16,0.31,,0.26,,

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants