def linear_test(self, Module, profiler_output_path=""):
D_in = 10
H = 5
D_out = 15
B = 8
NUM_INPUTS = 2
module = Module(D_in, H, D_out)
inputs = []
for i in range(NUM_INPUTS):
inputs.append([torch.randn(B, D_in), torch.randn(B, D_in)])
bench = ThroughputBenchmark(module)
for input in inputs:
# can do both args and kwargs here
bench.add_input(input[0], x2=input[1])
for i in range(NUM_INPUTS):
# or just unpack the list of inputs
module_result = module(*inputs[i])
bench_result = bench.run_once(*inputs[i])
torch.testing.assert_close(bench_result, module_result)
stats = bench.benchmark(
num_calling_threads=4,
num_warmup_iters=100,
num_iters=1000,
profiler_output_path=profiler_output_path,
)
print(stats)
def linear_test(self, Module):
D_in = 10
H = 5
D_out = 15
B = 8
NUM_INPUTS = 2
module = Module(D_in, H, D_out)
inputs = []
for i in range(NUM_INPUTS):
inputs.append([torch.randn(B, D_in), torch.randn(B, D_in)])
bench = ThroughputBenchmark(module)
for input in inputs:
# can do both args and kwargs here
bench.add_input(input[0], x2=input[1])
for i in range(NUM_INPUTS):
# or just unpack the list of inputs
module_result = module(*inputs[i])
bench_result = bench.run_once(*inputs[i])
assert_allclose(bench_result, module_result)
stats = bench.benchmark(
num_calling_threads=4,
num_warmup_iters=100,
num_iters=1000,
)
print("Avg latency (ms): {}".format(stats.latency_avg_ms))
print("Number of iterations: {}".format(stats.num_iters))