* Copyright (c) 2026 Huawei Technologies Co., Ltd.
* This program is free software, you can redistribute it and/or modify it under the terms and conditions of
* the CANN Open Software License Agreement Version 2.0 (the "License").
* Please refer to the License for details. You may not use this file except in compliance with the License.
* THIS SOFTWARE IS PROVIDED ON AN "AS IS" BASIS, WITHOUT WARRANTIES OF ANY KIND, EITHER EXPRESS OR IMPLIED,
* INCLUDING BUT NOT LIMITED TO NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
* See LICENSE in the root of the software repository for the full text of the License.
*/
* \file test_aclnn_causal_conv1d_update.cpp
* \brief Example for aclnnCausalConv1dUpdate (decode / update mode).
*/
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_causal_conv1d_update.h"
#define CHECK_RET(cond, return_expr) \
do { \
if (!(cond)) { \
return_expr; \
} \
} while (0)
#define LOG_PRINT(message, ...) \
do { \
printf(message, ##__VA_ARGS__); \
} while (0)
int64_t GetShapeSize(const std::vector<int64_t> &shape)
{
int64_t shapeSize = 1;
for (auto i : shape) {
shapeSize *= i;
}
return shapeSize;
}
void PrintOutResult(const char *name, std::vector<int64_t> &shape, void **deviceAddr)
{
auto size = GetShapeSize(shape);
std::vector<aclFloat16> resultData(size, 0);
auto ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), *deviceAddr,
size * sizeof(resultData[0]), ACL_MEMCPY_DEVICE_TO_HOST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("copy result from device to host failed. ERROR: %d\n", ret); return);
LOG_PRINT("%s (first 5 elements):\n", name);
for (int64_t i = 0; i < 5 && i < size; i++) {
LOG_PRINT(" [%ld] = %f\n", i, (double)aclFloat16ToFloat(resultData[i]));
}
}
int Init(int32_t deviceId, aclrtContext *context, aclrtStream *stream)
{
auto ret = aclInit(nullptr);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclInit failed. ERROR: %d\n", ret); return ret);
ret = aclrtSetDevice(deviceId);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetDevice failed. ERROR: %d\n", ret); return ret);
ret = aclrtCreateContext(context, deviceId);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateContext failed. ERROR: %d\n", ret); return ret);
ret = aclrtSetCurrentContext(*context);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSetCurrentContext failed. ERROR: %d\n", ret); return ret);
ret = aclrtCreateStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtCreateStream failed. ERROR: %d\n", ret); return ret);
return 0;
}
template <typename T>
int CreateAclTensor(const std::vector<T> &hostData, const std::vector<int64_t> &shape, void **deviceAddr,
aclDataType dataType, aclTensor **tensor)
{
auto size = GetShapeSize(shape) * sizeof(T);
auto ret = aclrtMalloc(deviceAddr, size, ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMalloc failed. ERROR: %d\n", ret); return ret);
ret = aclrtMemcpy(*deviceAddr, size, hostData.data(), size, ACL_MEMCPY_HOST_TO_DEVICE);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtMemcpy failed. ERROR: %d\n", ret); return ret);
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, nullptr, 0, aclFormat::ACL_FORMAT_ND, shape.data(),
shape.size(), *deviceAddr);
return ACL_SUCCESS;
}
int main()
{
int32_t deviceId = 0;
aclrtContext context;
aclrtStream stream;
auto ret = Init(deviceId, &context, &stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
void *xDeviceAddr = nullptr;
void *weightDeviceAddr = nullptr;
void *biasDeviceAddr = nullptr;
void *convStatesDeviceAddr = nullptr;
void *yDeviceAddr = nullptr;
aclTensor *x = nullptr;
aclTensor *weight = nullptr;
aclTensor *bias = nullptr;
aclTensor *convStates = nullptr;
aclTensor *y = nullptr;
int32_t batchSize = 4;
int32_t dim = 512;
int32_t width = 2;
int32_t stateLen = 4;
std::vector<int64_t> xShape = {batchSize, 1, dim};
std::vector<int64_t> weightShape = {width, dim};
std::vector<int64_t> biasShape = {dim};
std::vector<int64_t> convStatesShape = {batchSize, stateLen, dim};
std::vector<int64_t> yShape = {batchSize, 1, dim};
std::vector<int16_t> xHostData(GetShapeSize(xShape), 1);
std::vector<int16_t> weightHostData(GetShapeSize(weightShape), 1);
std::vector<int16_t> biasHostData(GetShapeSize(biasShape), 0);
std::vector<int16_t> convStatesHostData(GetShapeSize(convStatesShape), 0);
std::vector<int16_t> yHostData(GetShapeSize(yShape), 0);
ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_BF16, &x);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_BF16, &weight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(biasHostData, biasShape, &biasDeviceAddr, aclDataType::ACL_BF16, &bias);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret =
CreateAclTensor(convStatesHostData, convStatesShape, &convStatesDeviceAddr, aclDataType::ACL_BF16, &convStates);
CHECK_RET(ret == ACL_SUCCESS, return ret);
ret = CreateAclTensor(yHostData, yShape, &yDeviceAddr, aclDataType::ACL_BF16, &y);
CHECK_RET(ret == ACL_SUCCESS, return ret);
uint64_t workspaceSize = 0;
aclOpExecutor *executor;
const char *activation = "silu";
int64_t nullBlockId = 0;
int64_t maxQueryLen = -1;
ret = aclnnCausalConv1dUpdateGetWorkspaceSize(x, weight, convStates, bias, nullptr, nullptr, nullptr, nullptr,
nullptr, activation, nullBlockId, maxQueryLen, y, &workspaceSize,
&executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCausalConv1dUpdateGetWorkspaceSize failed. ERROR: %d\n", ret);
return ret);
void *workspaceAddr = nullptr;
if (workspaceSize > 0) {
ret = aclrtMalloc(&workspaceAddr, workspaceSize, ACL_MEM_MALLOC_HUGE_FIRST);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("allocate workspace failed. ERROR: %d\n", ret); return ret);
}
ret = aclnnCausalConv1dUpdate(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCausalConv1dUpdate failed. ERROR: %d\n", ret); return ret);
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
PrintOutResult("convStates (in-place updated)", convStatesShape, &convStatesDeviceAddr);
PrintOutResult("y", yShape, &yDeviceAddr);
aclDestroyTensor(x);
aclDestroyTensor(weight);
aclDestroyTensor(bias);
aclDestroyTensor(convStates);
aclDestroyTensor(y);
aclrtFree(xDeviceAddr);
aclrtFree(weightDeviceAddr);
aclrtFree(biasDeviceAddr);
aclrtFree(convStatesDeviceAddr);
aclrtFree(yDeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtDestroyContext(context);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}