aclnnConvertWeightToINT4Pack
支持的产品型号
CPU实现不涉及
接口原型
每个算子分为两段式接口，必须先调用“aclnnConvertWeightToINT4PackGetWorkspaceSize”接口获取计算所需workspace大小以及包含了算子计算流程的执行器，再调用“aclnnConvertWeightToINT4Pack”接口执行计算。
aclnnStatus aclnnConvertWeightToINT4PackGetWorkspaceSize(const aclTensor *weight, aclTensor *weightInt4Pack, uint64_t *workspaceSize, aclOpExecutor **executor)aclnnStatus aclnnConvertWeightToINT4Pack(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor, aclrtStream stream)
功能描述
算子功能：将int32的输入weight打包为int4，并进行交叠排放。当输出weightInt4Pack的数据格式为FRACTAL_NZ时，会将数据格式从ND转为FRACTAL_NZ之后输出。
- weightInt4Pack的数据类型为INT32时：输入weight的shape为[dim0, dim1]，按int4Pack打包后输出weightInt4Pack的shape为[dim0, dim1/8], 当weightInt4Pack的format为FRACTAL_NZ时，接口内部会将输出数据的数据格式转为FRACTAL_NZ，weightInt4Pack storage shape为[ceil_div(dim1/8, 8), ceil_div(k, 16), 16, 8]。
- weightInt4Pack的数据类型为INT4时：输入weight的shape为[dim0, dim1]，按int4Pack打包后输出weightInt4Pack的shape为[dim0, dim1], 当weightInt4Pack的format为FRACTAL_NZ时，接口内部会将输出数据的数据格式转为FRACTAL_NZ，weightInt4Pack storage shape为[ceil_div(dim1, 64), ceil_div(k, 16), 16, 64]。
aclnnConvertWeightToINT4PackGetWorkspaceSize
参数说明
weight(aclTensor*, 计算输入)：输入的weight，数据类型支持INT32，数据格式支持ND，维度支持2维，shape支持[k, n]、[n, k]。 当输出weightInt4Pack数据类型为INT4时，要求最后一维度为2对齐。当输出weightInt4Pack数据类型为INT32时，要求最后一维度为8对齐。 输入weight中元素的值需要在int4的表示范围内，即[-8, 7]。不支持非连续Tensor。
weightInt4Pack(aclTensor*, 计算输出)：INT4打包后的输出，数据类型为INT4或INT32（用1个INT32数据承载8个INT4数据）。数据格式支持ND、FRACTAL_NZ。不支持非连续Tensor。
对于weightInt4Pack不同的数据格式，weightInt4Pack的shape要求如下：
- 数据格式为ND时：
- weightInt4Pack数据类型为INT4时，shape需要和输入weight保持一致为(dim0, dim1)。
- weightInt4Pack数据类型为INT32时，shape的最后一维度为weight最后一维度的1/8为(dim0, dim1/8);
- 数据格式为FRACTAL_NZ时：
- weightInt4Pack数据类型为INT4时，shape需要和输入weight保持一致为(dim0, dim1)，storage shape为(ceil_div(dim1, 64), ceil_div(dim0, 16), 16, 64)。
- weightInt4Pack数据类型为INT32时，view shape的最后一维度为weight最后一维度的1/8为(dim0, dim1/8)，storage shape为(ceil_div(n, 64), ceil_div(k, 16), 16, 8)。
- 数据格式为ND时：
workspaceSize(uint64_t*, 出参)：返回需要在Device侧申请的workspace大小。
executor(aclOpExecutor**, 出参)：返回op执行器，包含了算子计算流程。
返回值：
aclnnStatus：返回状态码，具体参见aclnn返回码。
161001 (ACLNN_ERR_PARAM_NULLPTR)：如果传入的必选输入、输出、属性是空指针。 161002 (ACLNN_ERR_PARAM_INVALID)： - 传入weight、weightInt4Pack的shape维度不符合要求。 - 传入weight、weightInt4Pack的数据类型不在支持的范围之内。 - 传入weight、weightInt4Pack的shape大小不符合约束要求。 - 传入空tensor场景。 - 输入tensor的Format不是ND。 361001 (ACLNN_ERR_RUNTIME_ERROR)： - 数据从host侧拷贝到device侧异常。 - 数据从device侧拷贝到host侧异常。
aclnnConvertWeightToINT4Pack
参数说明
- workspace(void*, 入参)：在Device侧申请的workspace内存地址。
- workspaceSize(uint64_t, 入参)：在Device侧申请的workspace大小，由第一段接口aclnnConvertWeightToINT4PackGetWorkspaceSize获取。
- executor(aclOpExecutor*, 入参)：op执行器，包含了算子计算流程。
- stream(aclrtStream, 入参)：指定执行任务的AscendCL Stream流。
返回值：
aclnnStatus：返回状态码，具体参见aclnn返回码。
约束与限制
无
调用示例
示例代码如下，仅供参考，具体编译和执行过程请参考编译与运行样例。 伪量化有aclnnWeightQuantBatchMatmulV2和aclnnWeightQuantBatchMatmulV3接口， 这里以aclnnWeightQuantBatchMatmulV2为例
#include <iostream>
#include <vector>
#include "acl/acl.h"
#include "aclnnop/aclnn_cast.h"
#include "aclnnop/aclnn_weight_quant_batch_matmul_v2.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)
#define CEIL_DIV(x, y) ((((x) + (y)) - 1) / (y))
#define CEIL_ALIGN(x, y) ((((x) + (y)) - 1) / (y) * (y))
int64_t GetShapeSize(const std::vector<int64_t>& shape) {
int64_t shapeSize = 1;
for (auto i : shape) {
shapeSize *= i;
}
return shapeSize;
}
extern "C" aclnnStatus aclnnConvertWeightToINT4PackGetWorkspaceSize(const aclTensor *weight, const aclTensor *weightInt4Pack,
uint64_t *workspaceSize, aclOpExecutor **executor);
extern "C" aclnnStatus aclnnConvertWeightToINT4Pack(void *workspace, uint64_t workspaceSize, aclOpExecutor *executor,
aclrtStream stream);
int Init(int32_t deviceId, aclrtStream* stream) {
// 固定写法，AscendCL初始化
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 = 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);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
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);
// 计算连续tensor的strides
std::vector<int64_t> strides(shape.size(), 1);
for (int64_t i = shape.size() - 2; i >= 0; i--) {
strides[i] = shape[i + 1] * strides[i + 1];
}
// 调用aclCreateTensor接口创建aclTensor
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
shape.data(), shape.size(), *deviceAddr);
return 0;
}
template <typename T>
int CreateAclTensorInt4(const std::vector<T>& hostData, const std::vector<int64_t>& shape, void** deviceAddr,
aclDataType dataType, aclTensor** tensor, aclFormat format) {
auto size = hostData.size() * sizeof(T);
// 调用aclrtMalloc申请device侧内存
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);
// 调用aclrtMemcpy将host侧数据拷贝到device侧内存上
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);
// 计算连续tensor的strides
std::vector<int64_t> strides(shape.size(), 1);
for (int64_t i = shape.size() - 2; i >= 0; i--) {
strides[i] = shape[i + 1] * strides[i + 1];
}
// 调用aclCreateTensor接口创建aclTensor
if (format == aclFormat::ACL_FORMAT_ND) {
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0, aclFormat::ACL_FORMAT_ND,
shape.data(), shape.size(), *deviceAddr);
} else {
std::vector<int64_t> nzShape;
if (dataType == aclDataType::ACL_INT4) {
nzShape = {CEIL_DIV(shape[1], 64), CEIL_DIV(shape[0], 16), 16, 64};
} else {
nzShape = {CEIL_DIV(shape[1], 8), CEIL_DIV(shape[0], 16), 16, 8};
}
*tensor = aclCreateTensor(shape.data(), shape.size(), dataType, strides.data(), 0,
aclFormat::ACL_FORMAT_FRACTAL_NZ, nzShape.data(), nzShape.size(), *deviceAddr);
}
return 0;
}
int main() {
// 1. （固定写法）device/stream初始化，参考AscendCL对外接口列表
// 根据自己的实际device填写deviceId
int32_t deviceId = 0;
aclrtStream stream;
auto ret = Init(deviceId, &stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("Init acl failed. ERROR: %d\n", ret); return ret);
aclDataType weightInt4PackDtype = aclDataType::ACL_INT4;
aclFormat weightFormat = aclFormat::ACL_FORMAT_FRACTAL_NZ;
bool isWeightTransposed = true;
// 2. 构造输入与输出，需要根据API的接口自定义构造
int64_t m = 16;
int64_t k = 72;
int64_t n = 17;
int64_t weightDim0 = k;
int64_t weightDim1 = n;
if (isWeightTransposed) {
weightDim0 = n;
weightDim1 = k;
}
std::vector<int64_t> xShape = {m, k};
std::vector<int64_t> weightShape = {weightDim0, weightDim1};
std::vector<int64_t> weightInt4PackShape;
if (weightInt4PackDtype == aclDataType::ACL_INT4) {
weightInt4PackShape = {weightDim0, weightDim1};
} else {
weightInt4PackShape = {weightDim0, weightDim1/8};
}
std::vector<int64_t> yShape = {m, n};
void* xDeviceAddr = nullptr;
void* weightDeviceAddr = nullptr;
void* weightInt4PackDeviceAddr = nullptr;
void* yDeviceAddr = nullptr;
aclTensor* x = nullptr;
aclTensor* weight = nullptr;
aclTensor* weightInt4Pack = nullptr;
aclTensor* y = nullptr;
std::vector<float> xHostData(m * k, 1);
std::vector<int32_t> weightHostData(k * n, 1);
std::vector<float> yHostData(m * n, 0);
std::vector<int64_t> antiquantScaleShape = {n};
void* antiquantScaleDeviceAddr = nullptr;
aclTensor* antiquantScale = nullptr;
std::vector<float> antiquantScaleHostData(n, 1);
// 创建x aclTensor
ret = CreateAclTensor(xHostData, xShape, &xDeviceAddr, aclDataType::ACL_FLOAT, &x);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建weight aclTensor
ret = CreateAclTensor(weightHostData, weightShape, &weightDeviceAddr, aclDataType::ACL_INT32, &weight);
CHECK_RET(ret == ACL_SUCCESS, return ret);
if (weightInt4PackDtype == aclDataType::ACL_INT4) {
std::vector<int8_t> weightInt4PackHostData(n * k / 2, 0); //一个int8数据存放2个int4数据，所以这里除以2
if (weightFormat == aclFormat::ACL_FORMAT_FRACTAL_NZ) {
weightInt4PackHostData.resize(CEIL_ALIGN(weightDim1/2, 32) * CEIL_ALIGN(weightDim0, 16), 0);
}
// 创建weightInt4Pack aclTensor
ret = CreateAclTensorInt4(weightInt4PackHostData, weightInt4PackShape, &weightInt4PackDeviceAddr,
weightInt4PackDtype, &weightInt4Pack, weightFormat);
CHECK_RET(ret == ACL_SUCCESS, return ret);
} else {
std::vector<int32_t> weightInt4PackHostData(n * k / 8, 1); //一个int32数据存放8个int4数据，所以这里除以8
if (weightFormat == aclFormat::ACL_FORMAT_FRACTAL_NZ) {
weightInt4PackHostData.resize(CEIL_ALIGN(weightDim1/8, 8) * CEIL_ALIGN(weightDim0, 16), 0);
ret = CreateAclTensorInt4(weightInt4PackHostData, weightInt4PackShape, &weightInt4PackDeviceAddr,
weightInt4PackDtype, &weightInt4Pack, weightFormat);
} else {
// 创建weightInt4Pack aclTensor
ret = CreateAclTensor(weightInt4PackHostData, weightInt4PackShape, &weightInt4PackDeviceAddr,
weightInt4PackDtype, &weightInt4Pack);
}
CHECK_RET(ret == ACL_SUCCESS, return ret);
}
// 创建y aclTensor
ret = CreateAclTensor(yHostData, yShape, &yDeviceAddr, aclDataType::ACL_FLOAT, &y);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建antiquantScale aclTensor
ret = CreateAclTensor(antiquantScaleHostData, antiquantScaleShape, &antiquantScaleDeviceAddr, aclDataType::ACL_FLOAT, &antiquantScale);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建xFp16 aclTensor
void* xFp16DeviceAddr = nullptr;
aclTensor* xFp16 = nullptr;
ret = CreateAclTensor(xHostData, xShape, &xFp16DeviceAddr, aclDataType::ACL_FLOAT16, &xFp16);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建antiquantScale aclTensor
void* antiquantScaleFp16DeviceAddr = nullptr;
aclTensor* antiquantScaleFp16 = nullptr;
ret = CreateAclTensor(antiquantScaleHostData, antiquantScaleShape, &antiquantScaleFp16DeviceAddr, aclDataType::ACL_FLOAT16, &antiquantScaleFp16);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 创建yFp16 aclTensor
void* yFp16DeviceAddr = nullptr;
aclTensor* yFp16 = nullptr;
ret = CreateAclTensor(yHostData, yShape, &yFp16DeviceAddr, aclDataType::ACL_FLOAT16, &yFp16);
CHECK_RET(ret == ACL_SUCCESS, return ret);
// 3. 调用CANN算子库API，需要修改为具体的Api名称
uint64_t workspaceSize = 0;
aclOpExecutor* executor;
void* workspaceAddr = nullptr;
// 对weight做int32转int4pack
ret = aclnnConvertWeightToINT4PackGetWorkspaceSize(weight, weightInt4Pack, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvertWeightToINT4PackGetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
ret = aclnnConvertWeightToINT4Pack(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnConvertWeightToINT4Pack failed. ERROR: %d\n", ret); return ret);
// weight为转置场景，且weightInt4Pack shape为NZ时，需要调用aclInitTensor转换为非连续tensor
if (isWeightTransposed && weightFormat == aclFormat::ACL_FORMAT_FRACTAL_NZ) {
std::vector<int64_t> strides(weightInt4PackShape.size(), 1);
for (int64_t i = weightInt4PackShape.size() - 2; i >= 0; i--) {
strides[i] = weightInt4PackShape[i + 1] * strides[i + 1];
}
std::swap(strides[0], strides[1]);
std::swap(weightInt4PackShape[0], weightInt4PackShape[1]);
std::vector<int64_t> nzShape = {CEIL_DIV(k, 64), CEIL_DIV(n, 16), 16, 8};
if (weightInt4PackDtype == aclDataType::ACL_INT4) {
nzShape[3] = 64;
}
aclInitTensor(weightInt4Pack, weightInt4PackShape.data(), weightInt4PackShape.size(), weightInt4PackDtype, strides.data(), 0,
weightFormat, nzShape.data(), nzShape.size(), weightInt4PackDeviceAddr);
}
// 调用cast生成FP16的输入
ret = aclnnCastGetWorkspaceSize(x, aclDataType::ACL_FLOAT16, xFp16, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCastGetWorkspaceSize0 failed. ERROR: %d\n", ret); return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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 = aclnnCast(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCast0 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);
ret = aclnnCastGetWorkspaceSize(antiquantScale, aclDataType::ACL_FLOAT16, antiquantScaleFp16, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCastGetWorkspaceSize1 failed. ERROR: %d\n", ret); return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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 = aclnnCast(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCast1 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);
// 调用aclnnWeightQuantBatchMatmulV2第一段接口
ret = aclnnWeightQuantBatchMatmulV2GetWorkspaceSize(xFp16, weightInt4Pack, antiquantScaleFp16, nullptr, nullptr, nullptr, nullptr, 0, yFp16, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnWeightQuantBatchMatmulV2GetWorkspaceSize failed. ERROR: %d\n", ret); return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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);
}
// 调用aclnnWeightQuantBatchMatmulV2第二段接口
ret = aclnnWeightQuantBatchMatmulV2(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnWeightQuantBatchMatmulV2 failed. ERROR: %d\n", ret); return ret);
// 4. （固定写法）同步等待任务执行结束
ret = aclrtSynchronizeStream(stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclrtSynchronizeStream failed. ERROR: %d\n", ret); return ret);
// 将输出转为FP32
ret = aclnnCastGetWorkspaceSize(yFp16, aclDataType::ACL_FLOAT, y, &workspaceSize, &executor);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCastGetWorkspaceSize2 failed. ERROR: %d\n", ret); return ret);
// 根据第一段接口计算出的workspaceSize申请device内存
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 = aclnnCast(workspaceAddr, workspaceSize, executor, stream);
CHECK_RET(ret == ACL_SUCCESS, LOG_PRINT("aclnnCast2 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);
// 5. 获取输出的值，将device侧内存上的结果拷贝至host侧，需要根据具体API的接口定义修改
auto size = GetShapeSize(yShape);
std::vector<float> resultData(size, 0);
ret = aclrtMemcpy(resultData.data(), resultData.size() * sizeof(resultData[0]), yDeviceAddr,
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 ret);
for (int64_t i = 0; i < size; i++) {
LOG_PRINT("result[%ld] is: %f\n", i, resultData[i]);
}
// 6. 释放aclTensor和aclScalar，需要根据具体API的接口定义修改
aclDestroyTensor(x);
aclDestroyTensor(weight);
aclDestroyTensor(weightInt4Pack);
aclDestroyTensor(antiquantScale);
aclDestroyTensor(y);
aclDestroyTensor(xFp16);
aclDestroyTensor(antiquantScaleFp16);
aclDestroyTensor(yFp16);
// 7. 释放device资源
aclrtFree(xDeviceAddr);
aclrtFree(weightDeviceAddr);
aclrtFree(weightInt4PackDeviceAddr);
aclrtFree(antiquantScaleDeviceAddr);
aclrtFree(yDeviceAddr);
aclrtFree(xFp16DeviceAddr);
aclrtFree(antiquantScaleFp16DeviceAddr);
aclrtFree(yFp16DeviceAddr);
if (workspaceSize > 0) {
aclrtFree(workspaceAddr);
}
aclrtDestroyStream(stream);
aclrtResetDevice(deviceId);
aclFinalize();
return 0;
}