M-Labs/nac3
M-Labs
/
nac3
8
0
Fork 10
Code Issues 100 Pull Requests 20 Releases Wiki Activity

tmp: reformat nac3core/irrt

This commit is contained in:
lyken 2024-08-26 19:19:39 +08:00
parent ff6fed6d45
commit 6a35203101
No known key found for this signature in database
GPG Key ID: 3BD5FC6AC8325DD8
8 changed files with 117 additions and 127 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
nac3core/irrt/irrt/cslice.hpp
View File

@ -2,7 +2,8 @@
#include <irrt/int_types.hpp>
template <typename SizeT> struct CSlice {
uint8_t *base;
template<typename SizeT>
struct CSlice {
uint8_t* base;
SizeT len;
};

5
nac3core/irrt/irrt/debug.hpp
View File

@ -7,9 +7,8 @@
#define IRRT_DEBUG_ASSERT_BOOL false
#endif
#define raise_debug_assert(SizeT, msg, param1, param2, param3) \
raise_exception(SizeT, EXN_ASSERTION_ERROR, \
"IRRT debug assert failed: " msg, param1, param2, param3);
#define raise_debug_assert(SizeT, msg, param1, param2, param3) \
raise_exception(SizeT, EXN_ASSERTION_ERROR, "IRRT debug assert failed: " msg, param1, param2, param3);
#define debug_assert_eq(SizeT, lhs, rhs) if constexpr (IRRT_DEBUG_ASSERT_BOOL)
{

36
nac3core/irrt/irrt/exception.hpp
View File

@ -25,13 +25,14 @@ ExceptionId EXN_TYPE_ERROR;
* The parameter `err` could be `Exception<int32_t>` or `Exception<int64_t>`. The caller
* must make sure to pass `Exception`s with the correct `SizeT` depending on the `size_t` of the runtime.
*/
extern "C" void __nac3_raise(void *err);
extern "C" void __nac3_raise(void* err);
namespace {
/**
* @brief NAC3's Exception struct
*/
template <typename SizeT> struct Exception {
template<typename SizeT>
struct Exception {
ExceptionId id;
CSlice<SizeT> filename;
int32_t line;
@ -43,25 +44,27 @@ template <typename SizeT> struct Exception {
constexpr int64_t NO_PARAM = 0;
template <typename SizeT>
void _raise_exception_helper(ExceptionId id, const char *filename, int32_t line,
const char *function, const char *msg,
int64_t param0, int64_t param1, int64_t param2) {
template<typename SizeT>
void _raise_exception_helper(ExceptionId id,
const char* filename,
int32_t line,
const char* function,
const char* msg,
int64_t param0,
int64_t param1,
int64_t param2) {
Exception<SizeT> e = {
.id = id,
.filename = {.base = reinterpret_cast<const uint8_t *>(filename),
.len = __builtin_strlen(filename)},
.filename = {.base = reinterpret_cast<const uint8_t*>(filename), .len = __builtin_strlen(filename)},
.line = line,
.column = 0,
.function = {.base = reinterpret_cast<const uint8_t *>(function),
.len = __builtin_strlen(function)},
.msg = {.base = reinterpret_cast<const uint8_t *>(msg),
.len = __builtin_strlen(msg)},
.function = {.base = reinterpret_cast<const uint8_t*>(function), .len = __builtin_strlen(function)},
.msg = {.base = reinterpret_cast<const uint8_t*>(msg), .len = __builtin_strlen(msg)},
};
e.params[0] = param0;
e.params[1] = param1;
e.params[2] = param2;
__nac3_raise(reinterpret_cast<void *>(&e));
__nac3_raise(reinterpret_cast<void*>(&e));
__builtin_unreachable();
}
@ -74,7 +77,6 @@ void _raise_exception_helper(ExceptionId id, const char *filename, int32_t line,
* `param0` to `param2` are optional format arguments of `msg`. They should be set to
* `NO_PARAM` to indicate they are unused.
*/
#define raise_exception(SizeT, id, msg, param0, param1, param2) \
_raise_exception_helper<SizeT>(id, __FILE__, __LINE__, __FUNCTION__, msg, \
param0, param1, param2)
} // namespace
#define raise_exception(SizeT, id, msg, param0, param1, param2) \
_raise_exception_helper<SizeT>(id, __FILE__, __LINE__, __FUNCTION__, msg, param0, param1, param2)
} // namespace

49
nac3core/irrt/irrt/list.hpp
View File

@ -10,48 +10,47 @@ extern "C" {
// - The end index is *inclusive*,
// - The length of src and dest slice size should already
// be checked: if dest.step == 1 then len(src) <= len(dest) else len(src) == len(dest)
SliceIndex __nac3_list_slice_assign_var_size(
SliceIndex dest_start, SliceIndex dest_end, SliceIndex dest_step,
uint8_t *dest_arr, SliceIndex dest_arr_len, SliceIndex src_start,
SliceIndex src_end, SliceIndex src_step, uint8_t *src_arr,
SliceIndex src_arr_len, const SliceIndex size) {
SliceIndex __nac3_list_slice_assign_var_size(SliceIndex dest_start,
SliceIndex dest_end,
SliceIndex dest_step,
uint8_t* dest_arr,
SliceIndex dest_arr_len,
SliceIndex src_start,
SliceIndex src_end,
SliceIndex src_step,
uint8_t* src_arr,
SliceIndex src_arr_len,
const SliceIndex size) {
/* if dest_arr_len == 0, do nothing since we do not support extending list */
if (dest_arr_len == 0)
return dest_arr_len;
/* if both step is 1, memmove directly, handle the dropping of the list, and shrink size */
if (src_step == dest_step && dest_step == 1) {
const SliceIndex src_len =
(src_end >= src_start) ? (src_end - src_start + 1) : 0;
const SliceIndex dest_len =
(dest_end >= dest_start) ? (dest_end - dest_start + 1) : 0;
const SliceIndex src_len = (src_end >= src_start) ? (src_end - src_start + 1) : 0;
const SliceIndex dest_len = (dest_end >= dest_start) ? (dest_end - dest_start + 1) : 0;
if (src_len > 0) {
__builtin_memmove(dest_arr + dest_start * size,
src_arr + src_start * size, src_len * size);
__builtin_memmove(dest_arr + dest_start * size, src_arr + src_start * size, src_len * size);
}
if (dest_len > 0) {
/* dropping */
__builtin_memmove(dest_arr + (dest_start + src_len) * size,
dest_arr + (dest_end + 1) * size,
__builtin_memmove(dest_arr + (dest_start + src_len) * size, dest_arr + (dest_end + 1) * size,
(dest_arr_len - dest_end - 1) * size);
}
/* shrink size */
return dest_arr_len - (dest_len - src_len);
}
/* if two range overlaps, need alloca */
uint8_t need_alloca =
(dest_arr == src_arr) &&
!(max(dest_start, dest_end) < min(src_start, src_end) ||
max(src_start, src_end) < min(dest_start, dest_end));
uint8_t need_alloca = (dest_arr == src_arr)
&& !(max(dest_start, dest_end) < min(src_start, src_end)
|| max(src_start, src_end) < min(dest_start, dest_end));
if (need_alloca) {
uint8_t *tmp =
reinterpret_cast<uint8_t *>(__builtin_alloca(src_arr_len * size));
uint8_t* tmp = reinterpret_cast<uint8_t*>(__builtin_alloca(src_arr_len * size));
__builtin_memcpy(tmp, src_arr, src_arr_len * size);
src_arr = tmp;
}
SliceIndex src_ind = src_start;
SliceIndex dest_ind = dest_start;
for (; (src_step > 0) ? (src_ind <= src_end) : (src_ind >= src_end);
src_ind += src_step, dest_ind += dest_step) {
for (; (src_step > 0) ? (src_ind <= src_end) : (src_ind >= src_end); src_ind += src_step, dest_ind += dest_step) {
/* for constant optimization */
if (size == 1) {
__builtin_memcpy(dest_arr + dest_ind, src_arr + src_ind, 1);
@ -61,18 +60,16 @@ SliceIndex __nac3_list_slice_assign_var_size(
__builtin_memcpy(dest_arr + dest_ind * 8, src_arr + src_ind * 8, 8);
} else {
/* memcpy for var size, cannot overlap after previous alloca */
__builtin_memcpy(dest_arr + dest_ind * size,
src_arr + src_ind * size, size);
__builtin_memcpy(dest_arr + dest_ind * size, src_arr + src_ind * size, size);
}
}
/* only dest_step == 1 can we shrink the dest list. */
/* size should be ensured prior to calling this function */
if (dest_step == 1 && dest_end >= dest_start) {
__builtin_memmove(dest_arr + dest_ind * size,
dest_arr + (dest_end + 1) * size,
__builtin_memmove(dest_arr + dest_ind * size, dest_arr + (dest_end + 1) * size,
(dest_arr_len - dest_end - 1) * size);
return dest_arr_len - (dest_end - dest_ind) - 1;
}
return dest_arr_len;
}
} // extern "C"
} // extern "C"

19
nac3core/irrt/irrt/math.hpp
View File

@ -3,7 +3,8 @@
namespace {
// adapted from GNU Scientific Library: https://git.savannah.gnu.org/cgit/gsl.git/tree/sys/pow_int.c
// need to make sure `exp >= 0` before calling this function
template <typename T> T __nac3_int_exp_impl(T base, T exp) {
template<typename T>
T __nac3_int_exp_impl(T base, T exp) {
T res = 1;
/* repeated squaring method */
do {
@ -15,11 +16,11 @@ template <typename T> T __nac3_int_exp_impl(T base, T exp) {
} while (exp);
return res;
}
} // namespace
} // namespace
#define DEF_nac3_int_exp_(T) \
T __nac3_int_exp_##T(T base, T exp) { \
return __nac3_int_exp_impl(base, exp); \
#define DEF_nac3_int_exp_(T) \
T __nac3_int_exp_##T(T base, T exp) { \
return __nac3_int_exp_impl(base, exp); \
}
extern "C" {
@ -31,9 +32,13 @@ DEF_nac3_int_exp_(int64_t);
DEF_nac3_int_exp_(uint32_t);
DEF_nac3_int_exp_(uint64_t);
int32_t __nac3_isinf(double x) { return __builtin_isinf(x); }
int32_t __nac3_isinf(double x) {
return __builtin_isinf(x);
}
int32_t __nac3_isnan(double x) { return __builtin_isnan(x); }
int32_t __nac3_isnan(double x) {
return __builtin_isnan(x);
}
double tgamma(double arg);

8
nac3core/irrt/irrt/math_util.hpp
View File

@ -1,11 +1,13 @@
#pragma once
namespace {
template <typename T> const T &max(const T &a, const T &b) {
template<typename T>
const T& max(const T& a, const T& b) {
return a > b ? a : b;
}
template <typename T> const T &min(const T &a, const T &b) {
template<typename T>
const T& min(const T& a, const T& b) {
return a > b ? b : a;
}
} // namespace
} // namespace

119
nac3core/irrt/irrt/ndarray.hpp
View File

@ -3,9 +3,8 @@
#include <irrt/int_types.hpp>
namespace {
template <typename SizeT>
SizeT __nac3_ndarray_calc_size_impl(const SizeT *list_data, SizeT list_len,
SizeT begin_idx, SizeT end_idx) {
template<typename SizeT>
SizeT __nac3_ndarray_calc_size_impl(const SizeT* list_data, SizeT list_len, SizeT begin_idx, SizeT end_idx) {
__builtin_assume(end_idx <= list_len);
SizeT num_elems = 1;
@ -17,9 +16,8 @@ SizeT __nac3_ndarray_calc_size_impl(const SizeT *list_data, SizeT list_len,
return num_elems;
}
template <typename SizeT>
void __nac3_ndarray_calc_nd_indices_impl(SizeT index, const SizeT *dims,
SizeT num_dims, NDIndex *idxs) {
template<typename SizeT>
void __nac3_ndarray_calc_nd_indices_impl(SizeT index, const SizeT* dims, SizeT num_dims, NDIndex* idxs) {
SizeT stride = 1;
for (SizeT dim = 0; dim < num_dims; dim++) {
SizeT i = num_dims - dim - 1;
@ -29,10 +27,8 @@ void __nac3_ndarray_calc_nd_indices_impl(SizeT index, const SizeT *dims,
}
}
template <typename SizeT>
SizeT __nac3_ndarray_flatten_index_impl(const SizeT *dims, SizeT num_dims,
const NDIndex *indices,
SizeT num_indices) {
template<typename SizeT>
SizeT __nac3_ndarray_flatten_index_impl(const SizeT* dims, SizeT num_dims, const NDIndex* indices, SizeT num_indices) {
SizeT idx = 0;
SizeT stride = 1;
for (SizeT i = 0; i < num_dims; ++i) {
@ -47,18 +43,18 @@ SizeT __nac3_ndarray_flatten_index_impl(const SizeT *dims, SizeT num_dims,
return idx;
}
template <typename SizeT>
void __nac3_ndarray_calc_broadcast_impl(const SizeT *lhs_dims, SizeT lhs_ndims,
const SizeT *rhs_dims, SizeT rhs_ndims,
SizeT *out_dims) {
template<typename SizeT>
void __nac3_ndarray_calc_broadcast_impl(const SizeT* lhs_dims,
SizeT lhs_ndims,
const SizeT* rhs_dims,
SizeT rhs_ndims,
SizeT* out_dims) {
SizeT max_ndims = lhs_ndims > rhs_ndims ? lhs_ndims : rhs_ndims;
for (SizeT i = 0; i < max_ndims; ++i) {
const SizeT *lhs_dim_sz =
i < lhs_ndims ? &lhs_dims[lhs_ndims - i - 1] : nullptr;
const SizeT *rhs_dim_sz =
i < rhs_ndims ? &rhs_dims[rhs_ndims - i - 1] : nullptr;
SizeT *out_dim = &out_dims[max_ndims - i - 1];
const SizeT* lhs_dim_sz = i < lhs_ndims ? &lhs_dims[lhs_ndims - i - 1] : nullptr;
const SizeT* rhs_dim_sz = i < rhs_ndims ? &rhs_dims[rhs_ndims - i - 1] : nullptr;
SizeT* out_dim = &out_dims[max_ndims - i - 1];
if (lhs_dim_sz == nullptr) {
*out_dim = *rhs_dim_sz;
@ -76,84 +72,73 @@ void __nac3_ndarray_calc_broadcast_impl(const SizeT *lhs_dims, SizeT lhs_ndims,
}
}
template <typename SizeT>
void __nac3_ndarray_calc_broadcast_idx_impl(const SizeT *src_dims,
template<typename SizeT>
void __nac3_ndarray_calc_broadcast_idx_impl(const SizeT* src_dims,
SizeT src_ndims,
const NDIndex *in_idx,
NDIndex *out_idx) {
const NDIndex* in_idx,
NDIndex* out_idx) {
for (SizeT i = 0; i < src_ndims; ++i) {
SizeT src_i = src_ndims - i - 1;
out_idx[src_i] = src_dims[src_i] == 1 ? 0 : in_idx[src_i];
}
}
} // namespace
} // namespace
extern "C" {
uint32_t __nac3_ndarray_calc_size(const uint32_t *list_data, uint32_t list_len,
uint32_t begin_idx, uint32_t end_idx) {
return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx,
end_idx);
uint32_t __nac3_ndarray_calc_size(const uint32_t* list_data, uint32_t list_len, uint32_t begin_idx, uint32_t end_idx) {
return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx, end_idx);
}
uint64_t __nac3_ndarray_calc_size64(const uint64_t *list_data,
uint64_t list_len, uint64_t begin_idx,
uint64_t end_idx) {
return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx,
end_idx);
uint64_t
__nac3_ndarray_calc_size64(const uint64_t* list_data, uint64_t list_len, uint64_t begin_idx, uint64_t end_idx) {
return __nac3_ndarray_calc_size_impl(list_data, list_len, begin_idx, end_idx);
}
void __nac3_ndarray_calc_nd_indices(uint32_t index, const uint32_t *dims,
uint32_t num_dims, NDIndex *idxs) {
void __nac3_ndarray_calc_nd_indices(uint32_t index, const uint32_t* dims, uint32_t num_dims, NDIndex* idxs) {
__nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
}
void __nac3_ndarray_calc_nd_indices64(uint64_t index, const uint64_t *dims,
uint64_t num_dims, NDIndex *idxs) {
void __nac3_ndarray_calc_nd_indices64(uint64_t index, const uint64_t* dims, uint64_t num_dims, NDIndex* idxs) {
__nac3_ndarray_calc_nd_indices_impl(index, dims, num_dims, idxs);
}
uint32_t __nac3_ndarray_flatten_index(const uint32_t *dims, uint32_t num_dims,
const NDIndex *indices,
uint32_t num_indices) {
return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices,
num_indices);
uint32_t
__nac3_ndarray_flatten_index(const uint32_t* dims, uint32_t num_dims, const NDIndex* indices, uint32_t num_indices) {
return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices, num_indices);
}
uint64_t __nac3_ndarray_flatten_index64(const uint64_t *dims, uint64_t num_dims,
const NDIndex *indices,
uint64_t num_indices) {
return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices,
num_indices);
uint64_t
__nac3_ndarray_flatten_index64(const uint64_t* dims, uint64_t num_dims, const NDIndex* indices, uint64_t num_indices) {
return __nac3_ndarray_flatten_index_impl(dims, num_dims, indices, num_indices);
}
void __nac3_ndarray_calc_broadcast(const uint32_t *lhs_dims, uint32_t lhs_ndims,
const uint32_t *rhs_dims, uint32_t rhs_ndims,
uint32_t *out_dims) {
return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims,
rhs_ndims, out_dims);
void __nac3_ndarray_calc_broadcast(const uint32_t* lhs_dims,
uint32_t lhs_ndims,
const uint32_t* rhs_dims,
uint32_t rhs_ndims,
uint32_t* out_dims) {
return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims, rhs_ndims, out_dims);
}
void __nac3_ndarray_calc_broadcast64(const uint64_t *lhs_dims,
void __nac3_ndarray_calc_broadcast64(const uint64_t* lhs_dims,
uint64_t lhs_ndims,
const uint64_t *rhs_dims,
uint64_t rhs_ndims, uint64_t *out_dims) {
return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims,
rhs_ndims, out_dims);
const uint64_t* rhs_dims,
uint64_t rhs_ndims,
uint64_t* out_dims) {
return __nac3_ndarray_calc_broadcast_impl(lhs_dims, lhs_ndims, rhs_dims, rhs_ndims, out_dims);
}
void __nac3_ndarray_calc_broadcast_idx(const uint32_t *src_dims,
void __nac3_ndarray_calc_broadcast_idx(const uint32_t* src_dims,
uint32_t src_ndims,
const NDIndex *in_idx,
NDIndex *out_idx) {
__nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx,
out_idx);
const NDIndex* in_idx,
NDIndex* out_idx) {
__nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx, out_idx);
}
void __nac3_ndarray_calc_broadcast_idx64(const uint64_t *src_dims,
void __nac3_ndarray_calc_broadcast_idx64(const uint64_t* src_dims,
uint64_t src_ndims,
const NDIndex *in_idx,
NDIndex *out_idx) {
__nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx,
out_idx);
const NDIndex* in_idx,
NDIndex* out_idx) {
__nac3_ndarray_calc_broadcast_idx_impl(src_dims, src_ndims, in_idx, out_idx);
}
}

3
nac3core/irrt/irrt/slice.hpp
View File

@ -15,8 +15,7 @@ SliceIndex __nac3_slice_index_bound(SliceIndex i, const SliceIndex len) {
return i;
}
SliceIndex __nac3_range_slice_len(const SliceIndex start, const SliceIndex end,
const SliceIndex step) {
SliceIndex __nac3_range_slice_len(const SliceIndex start, const SliceIndex end, const SliceIndex step) {
SliceIndex diff = end - start;
if (diff > 0 && step > 0) {
return ((diff - 1) / step) + 1;