# ----------------------------------------
# PyTorch/Caffe2 Operator Micro-benchmarks
# ----------------------------------------
# Tag : short

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_paddingNone_input_size32_cpu
# Input: vocab: 10000, dim: 64, padding: None, input_size: 32, device: cpu
Forward Execution Time (us) : 6.789

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_paddingNone_input_size32_cuda
# Input: vocab: 10000, dim: 64, padding: None, input_size: 32, device: cuda
Forward Execution Time (us) : 10.663

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_paddingNone_input_size48_cpu
# Input: vocab: 10000, dim: 64, padding: None, input_size: 48, device: cpu
Forward Execution Time (us) : 6.839

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_paddingNone_input_size48_cuda
# Input: vocab: 10000, dim: 64, padding: None, input_size: 48, device: cuda
Forward Execution Time (us) : 10.674

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_paddingNone_input_size64_cpu
# Input: vocab: 10000, dim: 64, padding: None, input_size: 64, device: cpu
Forward Execution Time (us) : 6.995

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_paddingNone_input_size64_cuda
# Input: vocab: 10000, dim: 64, padding: None, input_size: 64, device: cuda
Forward Execution Time (us) : 10.612

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_padding2_input_size32_cpu
# Input: vocab: 10000, dim: 64, padding: 2, input_size: 32, device: cpu
Forward Execution Time (us) : 6.840

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_padding2_input_size32_cuda
# Input: vocab: 10000, dim: 64, padding: 2, input_size: 32, device: cuda
Forward Execution Time (us) : 11.356

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_padding2_input_size48_cpu
# Input: vocab: 10000, dim: 64, padding: 2, input_size: 48, device: cpu
Forward Execution Time (us) : 7.107

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_padding2_input_size48_cuda
# Input: vocab: 10000, dim: 64, padding: 2, input_size: 48, device: cuda
Forward Execution Time (us) : 11.307

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_padding2_input_size64_cpu
# Input: vocab: 10000, dim: 64, padding: 2, input_size: 64, device: cpu
Forward Execution Time (us) : 7.305

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim64_padding2_input_size64_cuda
# Input: vocab: 10000, dim: 64, padding: 2, input_size: 64, device: cuda
Forward Execution Time (us) : 11.359

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_paddingNone_input_size32_cpu
# Input: vocab: 10000, dim: 128, padding: None, input_size: 32, device: cpu
Forward Execution Time (us) : 6.818

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_paddingNone_input_size32_cuda
# Input: vocab: 10000, dim: 128, padding: None, input_size: 32, device: cuda
Forward Execution Time (us) : 10.730

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_paddingNone_input_size48_cpu
# Input: vocab: 10000, dim: 128, padding: None, input_size: 48, device: cpu
Forward Execution Time (us) : 7.361

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_paddingNone_input_size48_cuda
# Input: vocab: 10000, dim: 128, padding: None, input_size: 48, device: cuda
Forward Execution Time (us) : 10.622

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_paddingNone_input_size64_cpu
# Input: vocab: 10000, dim: 128, padding: None, input_size: 64, device: cpu
Forward Execution Time (us) : 7.866

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_paddingNone_input_size64_cuda
# Input: vocab: 10000, dim: 128, padding: None, input_size: 64, device: cuda
Forward Execution Time (us) : 10.711

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_padding2_input_size32_cpu
# Input: vocab: 10000, dim: 128, padding: 2, input_size: 32, device: cpu
Forward Execution Time (us) : 7.320

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_padding2_input_size32_cuda
# Input: vocab: 10000, dim: 128, padding: 2, input_size: 32, device: cuda
Forward Execution Time (us) : 11.306

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_padding2_input_size48_cpu
# Input: vocab: 10000, dim: 128, padding: 2, input_size: 48, device: cpu
Forward Execution Time (us) : 7.668

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_padding2_input_size48_cuda
# Input: vocab: 10000, dim: 128, padding: 2, input_size: 48, device: cuda
Forward Execution Time (us) : 11.330

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_padding2_input_size64_cpu
# Input: vocab: 10000, dim: 128, padding: 2, input_size: 64, device: cpu
Forward Execution Time (us) : 8.007

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab10000_dim128_padding2_input_size64_cuda
# Input: vocab: 10000, dim: 128, padding: 2, input_size: 64, device: cuda
Forward Execution Time (us) : 11.302

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_paddingNone_input_size32_cpu
# Input: vocab: 20000, dim: 64, padding: None, input_size: 32, device: cpu
Forward Execution Time (us) : 6.525

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_paddingNone_input_size32_cuda
# Input: vocab: 20000, dim: 64, padding: None, input_size: 32, device: cuda
Forward Execution Time (us) : 10.749

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_paddingNone_input_size48_cpu
# Input: vocab: 20000, dim: 64, padding: None, input_size: 48, device: cpu
Forward Execution Time (us) : 6.709

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_paddingNone_input_size48_cuda
# Input: vocab: 20000, dim: 64, padding: None, input_size: 48, device: cuda
Forward Execution Time (us) : 10.712

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_paddingNone_input_size64_cpu
# Input: vocab: 20000, dim: 64, padding: None, input_size: 64, device: cpu
Forward Execution Time (us) : 6.876

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_paddingNone_input_size64_cuda
# Input: vocab: 20000, dim: 64, padding: None, input_size: 64, device: cuda
Forward Execution Time (us) : 10.629

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_padding2_input_size32_cpu
# Input: vocab: 20000, dim: 64, padding: 2, input_size: 32, device: cpu
Forward Execution Time (us) : 6.814

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_padding2_input_size32_cuda
# Input: vocab: 20000, dim: 64, padding: 2, input_size: 32, device: cuda
Forward Execution Time (us) : 11.385

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_padding2_input_size48_cpu
# Input: vocab: 20000, dim: 64, padding: 2, input_size: 48, device: cpu
Forward Execution Time (us) : 7.159

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_padding2_input_size48_cuda
# Input: vocab: 20000, dim: 64, padding: 2, input_size: 48, device: cuda
Forward Execution Time (us) : 11.409

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_padding2_input_size64_cpu
# Input: vocab: 20000, dim: 64, padding: 2, input_size: 64, device: cpu
Forward Execution Time (us) : 7.231

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim64_padding2_input_size64_cuda
# Input: vocab: 20000, dim: 64, padding: 2, input_size: 64, device: cuda
Forward Execution Time (us) : 11.354

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_paddingNone_input_size32_cpu
# Input: vocab: 20000, dim: 128, padding: None, input_size: 32, device: cpu
Forward Execution Time (us) : 6.910

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_paddingNone_input_size32_cuda
# Input: vocab: 20000, dim: 128, padding: None, input_size: 32, device: cuda
Forward Execution Time (us) : 10.676

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_paddingNone_input_size48_cpu
# Input: vocab: 20000, dim: 128, padding: None, input_size: 48, device: cpu
Forward Execution Time (us) : 7.350

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_paddingNone_input_size48_cuda
# Input: vocab: 20000, dim: 128, padding: None, input_size: 48, device: cuda
Forward Execution Time (us) : 10.683

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_paddingNone_input_size64_cpu
# Input: vocab: 20000, dim: 128, padding: None, input_size: 64, device: cpu
Forward Execution Time (us) : 7.907

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_paddingNone_input_size64_cuda
# Input: vocab: 20000, dim: 128, padding: None, input_size: 64, device: cuda
Forward Execution Time (us) : 10.656

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_padding2_input_size32_cpu
# Input: vocab: 20000, dim: 128, padding: 2, input_size: 32, device: cpu
Forward Execution Time (us) : 7.231

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_padding2_input_size32_cuda
# Input: vocab: 20000, dim: 128, padding: 2, input_size: 32, device: cuda
Forward Execution Time (us) : 11.284

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_padding2_input_size48_cpu
# Input: vocab: 20000, dim: 128, padding: 2, input_size: 48, device: cpu
Forward Execution Time (us) : 7.565

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_padding2_input_size48_cuda
# Input: vocab: 20000, dim: 128, padding: 2, input_size: 48, device: cuda
Forward Execution Time (us) : 11.371

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_padding2_input_size64_cpu
# Input: vocab: 20000, dim: 128, padding: 2, input_size: 64, device: cpu
Forward Execution Time (us) : 7.939

# Benchmarking PyTorch: embedding
# Mode: Eager
# Name: embedding_vocab20000_dim128_padding2_input_size64_cuda
# Input: vocab: 20000, dim: 128, padding: 2, input_size: 64, device: cuda
Forward Execution Time (us) : 11.291