def test_matmul_add():
n = 1024
l = 128
m = 235
A = tvm.placeholder((n, l), name='A')
B = tvm.placeholder((l, m), name='B')
C = rocblas.matmul(A, B)
s = tvm.create_schedule(C.op)
def verify(target="rocm"):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func("tvm.contrib.rocblas.matmul", True):
print("skip because extern function is not available")
return
ctx = tvm.rocm(0)
f = tvm.build(s, [A, B, C], target)
a = tvm.nd.array(np.random.uniform(size=(n, l)).astype(A.dtype), ctx)
b = tvm.nd.array(np.random.uniform(size=(l, m)).astype(B.dtype), ctx)
c = tvm.nd.array(np.zeros((n, m), dtype=C.dtype), ctx)
f(a, b, c)
tvm.testing.assert_allclose(
c.asnumpy(), np.dot(a.asnumpy(), b.asnumpy()), rtol=1e-5)
verify()
def dense_rocm(data, weight, bias=None):
"""Dense operator for rocm backend.
Parameters
----------
data : tvm.Tensor
2-D with shape [batch, in_dim]
weight : tvm.Tensor
2-D with shape [out_dim, in_dim]
bias : tvm.Tensor, optional
1-D with shape [out_dim]
Returns
-------
output : tvm.Tensor
2-D with shape [batch, out_dim]
"""
assert len(data.shape) == 2 and len(weight.shape) == 2, \
"only support 2-dim dense"
if bias is not None:
assert len(bias.shape) == 1
batch, in_dim = data.shape
out_dim, _ = weight.shape
target = tvm.target.current_target()
if "rocblas" in target.libs:
matmul = rocblas.matmul(data, weight, False, True)
if bias is not None:
matmul = tvm.compute((batch, out_dim), \
lambda i, j: matmul[i, j] + bias[j], \
tag=tag.BROADCAST)
return matmul
return dense_default(data, weight, bias)
def test_matmul_add():
n = 1024
l = 128
m = 235
A = tvm.placeholder((n, l), name='A')
B = tvm.placeholder((l, m), name='B')
C = rocblas.matmul(A, B)
s = tvm.create_schedule(C.op)
def verify(target="rocm"):
if not tvm.module.enabled(target):
print("skip because %s is not enabled..." % target)
return
if not tvm.get_global_func("tvm.contrib.rocblas.matmul", True):
print("skip because extern function is not available")
return
ctx = tvm.rocm(0)
f = tvm.build(s, [A, B, C], target)
a = tvm.nd.array(np.random.uniform(size=(n, l)).astype(A.dtype), ctx)
b = tvm.nd.array(np.random.uniform(size=(l, m)).astype(B.dtype), ctx)
c = tvm.nd.array(np.zeros((n, m), dtype=C.dtype), ctx)
f(a, b, c)
tvm.testing.assert_allclose(c.asnumpy(),
np.dot(a.asnumpy(), b.asnumpy()),
rtol=1e-5)
verify()
def dense_rocblas(cfg, data, weight, bias=None, out_dtype=None):
"""Dense operator for rocm backend with cblas.
Parameters
----------
data : tvm.Tensor
2-D with shape [batch, in_dim]
weight : tvm.Tensor
2-D with shape [out_dim, in_dim]
bias : tvm.Tensor, optional
1-D with shape [out_dim]
out_dtype : str
The output type. This is used for mixed precision.
Returns
-------
output : tvm.Tensor
2-D with shape [batch, out_dim]
"""
assert out_dtype == data.dtype, "Mixed precision not supported."
matmul = rocblas.matmul(data, weight, False, True)
batch, in_dim = data.shape
out_dim, _ = weight.shape
cfg.add_flop(batch * in_dim * out_dim * 2)
if bias is not None:
matmul = tvm.compute((batch, out_dim),
lambda i, j: matmul[i, j] + bias[j],
tag=tag.BROADCAST)
return matmul
def dense_rocm(data, weight, bias=None):
"""Dense operator for rocm backend.
Parameters
----------
data : tvm.Tensor
2-D with shape [batch, in_dim]
weight : tvm.Tensor
2-D with shape [out_dim, in_dim]
bias : tvm.Tensor, optional
1-D with shape [out_dim]
Returns
-------
output : tvm.Tensor
2-D with shape [batch, out_dim]
"""
assert len(data.shape) == 2 and len(weight.shape) == 2, \
"only support 2-dim dense"
if bias is not None:
assert len(bias.shape) == 1
batch, in_dim = data.shape
out_dim, _ = weight.shape
target = tvm.target.current_target()
if "rocblas" in target.libs:
matmul = rocblas.matmul(data, weight, False, True)
if bias is not None:
matmul = tvm.compute((batch, out_dim), \
lambda i, j: matmul[i, j] + bias[j], \
tag=tag.BROADCAST)
return matmul
return dense_default(data, weight, bias)
def dense_rocm(cfg, data, weight, bias=None, out_dtype=None):
"""Dense operator for rocm backend.
Parameters
----------
data : tvm.Tensor
2-D with shape [batch, in_dim]
weight : tvm.Tensor
2-D with shape [out_dim, in_dim]
bias : tvm.Tensor, optional
1-D with shape [out_dim]
out_dtype : str
The output type. This is used for mixed precision.
Returns
-------
output : tvm.Tensor
2-D with shape [batch, out_dim]
"""
assert len(data.shape) == 2 and len(weight.shape) == 2, \
"only support 2-dim dense"
if bias is not None:
assert len(bias.shape) == 1
if out_dtype is None:
out_dtype = data.dtype
batch, in_dim = data.shape
out_dim, _ = weight.shape
target = tvm.target.current_target()
if "rocblas" in target.libs:
assert out_dtype == data.dtype, "Mixed precision not supported."
matmul = rocblas.matmul(data, weight, False, True)
if bias is not None:
matmul = tvm.compute((batch, out_dim), \
lambda i, j: matmul[i, j] + bias[j], \
tag=tag.BROADCAST)
return matmul
return dense_default(data, weight, bias, out_dtype)
