File size: 4,828 Bytes
85ba398 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
# Copyright (c) Facebook, Inc. and its affiliates.
#
# This source code is licensed under the MIT license found in the
# LICENSE file in the root directory of this source tree.
import itertools
import random
import torch
from torch.utils import benchmark
from fairseq.modules.multihead_attention import MultiheadAttention
BATCH = [20, 41, 97]
SEQ = 64
EMB = 48
HEADS = 4
DROP = 0.1
DEVICE = torch.device("cuda")
ATTN_MASK_DTYPE = [torch.uint8, torch.bool, torch.float]
KEY_PADDING_MASK_DTYPE = [torch.uint8, torch.bool]
def _reset_seeds():
torch.manual_seed(0)
random.seed(0)
def _get_mask(to_dtype: torch.dtype, dim0: int, dim1: int):
if to_dtype == torch.float:
mask = torch.randint(0, 2, (dim0, dim1)).to(dtype=torch.bool)
return mask.to(dtype=to_dtype).masked_fill(mask, -float("inf"))
return torch.randint(0, 2, (dim0, dim1)).to(dtype=to_dtype)
def benchmark_multihead_attention(
label="",
attn_dtype=torch.uint8,
key_padding_dtype=torch.uint8,
add_bias_kv=False,
add_zero_attn=False,
static_kv=False,
batch_size=20,
embedding=EMB,
seq_len=SEQ,
num_heads=HEADS,
):
results = []
# device = torch.device("cuda")
xformers_att_config = '{"name": "scaled_dot_product"}'
attn_mask = _get_mask(to_dtype=attn_dtype, dim0=seq_len, dim1=seq_len)
key_padding_mask = _get_mask(
to_dtype=key_padding_dtype, dim0=batch_size, dim1=seq_len
)
q = torch.rand(seq_len, batch_size, embedding, requires_grad=True)
k = torch.rand(seq_len, batch_size, embedding, requires_grad=True)
v = torch.rand(seq_len, batch_size, embedding, requires_grad=True)
_reset_seeds()
original_mha = MultiheadAttention(
embedding,
num_heads,
dropout=0.0,
xformers_att_config=None,
add_bias_kv=add_bias_kv,
add_zero_attn=add_zero_attn,
)
xformers_mha = MultiheadAttention(
embedding,
num_heads,
dropout=0.0,
xformers_att_config=xformers_att_config,
add_bias_kv=add_bias_kv,
add_zero_attn=add_zero_attn,
)
def original_bench_fw(q, k, v, key_padding_mask, attn_mask, static_kv):
original_mha(
query=q,
key=k,
value=v,
key_padding_mask=key_padding_mask,
attn_mask=attn_mask,
static_kv=static_kv,
)
def xformers_bench_fw(q, k, v, key_padding_mask, attn_mask, static_kv):
xformers_mha(
query=q,
key=k,
value=v,
key_padding_mask=key_padding_mask,
attn_mask=attn_mask,
static_kv=static_kv,
)
def original_bench_fw_bw(q, k, v, key_padding_mask, attn_mask, static_kv):
output, _ = original_mha(
query=q,
key=k,
value=v,
key_padding_mask=key_padding_mask,
attn_mask=attn_mask,
static_kv=static_kv,
)
loss = torch.norm(output)
loss.backward()
def xformers_bench_fw_bw(q, k, v, key_padding_mask, attn_mask, static_kv):
output, _ = xformers_mha(
query=q,
key=k,
value=v,
key_padding_mask=key_padding_mask,
attn_mask=attn_mask,
static_kv=static_kv,
)
loss = torch.norm(output)
loss.backward()
fns = [
original_bench_fw,
xformers_bench_fw,
original_bench_fw_bw,
xformers_bench_fw_bw,
]
for fn in fns:
results.append(
benchmark.Timer(
stmt="fn(q, k, v, key_padding_mask, attn_mask, static_kv)",
globals={
"q": q,
"k": k,
"v": v,
"key_padding_mask": key_padding_mask,
"attn_mask": attn_mask,
"static_kv": static_kv,
"fn": fn,
},
label="multihead fw + bw",
sub_label=f"{fn.__name__}",
description=label,
).blocked_autorange(min_run_time=1)
)
compare = benchmark.Compare(results)
compare.print()
def run_benchmarks():
for attn_dtype, key_padding_dtype, add_bias_kv, add_zero_attn in itertools.product(
ATTN_MASK_DTYPE, KEY_PADDING_MASK_DTYPE, [True, False], [True, False]
):
label = f"attn_dtype {attn_dtype}, key_padding_dtype {key_padding_dtype}, \
add_bias_kv {add_bias_kv}, add_zero_attn {add_zero_attn}"
benchmark_multihead_attention(
label=label,
attn_dtype=attn_dtype,
key_padding_dtype=key_padding_dtype,
add_bias_kv=add_bias_kv,
add_zero_attn=add_zero_attn,
)
run_benchmarks()
|