mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

SYCL: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators (#16613)

Browse Source 
* SYCL: Add support for FLOOR,CEIL,ROUND and TRUNC unary operators

Clean up unrelated changes from previous commit

* Chore: remove empty lines and fix indentation

* Clean up: remove leftover blank lines and fix spacing

* chore: fix trailing whitespace and ensure final newline

* Cleanup: remove redundant declarations already defined in header

* Sync docs/ops.md with updated backend operation support

* docs: update ops.md after rebase

* docs: update ops.md - Vulkan supports SSM_CONV and SSM_SCAN
This commit is contained in:
safranowith
2025-10-20 11:08:32 +03:00
committed by GitHub
parent 7062dd8460
commit 2330de7b84
7 changed files with 313 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-sycl/element_wise.cpp
+120
View File
@@ -150,6 +150,26 @@ static __dpct_inline__ T op_clamp(T x, float min_val, float max_val) {
return x < static_cast<T>(min_val) ? static_cast<T>(min_val) : (x > static_cast<T>(max_val) ? static_cast<T>(max_val) : x);
}
template<typename T>
static __dpct_inline__ T op_floor(T x) {
return sycl::floor(x);
}
template<typename T>
static __dpct_inline__ T op_ceil(T x) {
return sycl::ceil(x);
}
template<typename T>
static __dpct_inline__ T op_round(T x) {
return sycl::round(x);
}
template<typename T>
static __dpct_inline__ T op_trunc(T x) {
return sycl::trunc(x);
}
template<typename T>
static void unary_op_sgn_kernel(const T * x, T * dst, const int k, const sycl::nd_item<1> &item_ct1) {
SYCL_GLOBAL_ID_LOOP(k, item_ct1) {
@@ -304,6 +324,34 @@ static void unary_op_clamp_kernel(const T * x, T * dst, const int k, const sycl:
}
}
template<typename T>
static void unary_op_floor_kernel(const T * x, T * dst, const int k, const sycl::nd_item<1> &item_ct1) {
SYCL_GLOBAL_ID_LOOP(k, item_ct1) {
dst[i] = op_floor(x[i]);
}
}
template<typename T>
static void unary_op_ceil_kernel(const T * x, T * dst, const int k, const sycl::nd_item<1> &item_ct1) {
SYCL_GLOBAL_ID_LOOP(k, item_ct1) {
dst[i] = op_ceil(x[i]);
}
}
template<typename T>
static void unary_op_round_kernel(const T * x, T * dst, const int k, const sycl::nd_item<1> &item_ct1) {
SYCL_GLOBAL_ID_LOOP(k, item_ct1) {
dst[i] = op_round(x[i]);
}
}
template<typename T>
static void unary_op_trunc_kernel(const T * x, T * dst, const int k, const sycl::nd_item<1> &item_ct1) {
SYCL_GLOBAL_ID_LOOP(k, item_ct1) {
dst[i] = op_trunc(x[i]);
}
}
template<typename T>
static void upscale(const T *x, T *dst, const int nb00, const int nb01,
const int nb02, const int nb03, const int ne10, const int ne11,
@@ -897,6 +945,58 @@ static inline void ggml_sycl_op_clamp(ggml_backend_sycl_context & ctx, ggml_tens
}, min_val, max_val);
}
static inline void ggml_sycl_op_floor(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
ggml_sycl_detail::dispatch_ggml_sycl_op_unary(ctx, dst,
[](const auto* src, auto* dst_ptr, int k_elements, queue_ptr stream) {
const int num_blocks = ceil_div(k_elements, 256);
stream->parallel_for(
sycl::nd_range<1>(sycl::range<1>(num_blocks) * sycl::range<1>(256),
sycl::range<1>(256)),
[=](sycl::nd_item<1> item_ct1) {
unary_op_floor_kernel(src, dst_ptr, k_elements, item_ct1);
});
});
}
static inline void ggml_sycl_op_ceil(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
ggml_sycl_detail::dispatch_ggml_sycl_op_unary(ctx, dst,
[](const auto* src, auto* dst_ptr, int k_elements, queue_ptr stream) {
const int num_blocks = ceil_div(k_elements, 256);
stream->parallel_for(
sycl::nd_range<1>(sycl::range<1>(num_blocks) * sycl::range<1>(256),
sycl::range<1>(256)),
[=](sycl::nd_item<1> item_ct1) {
unary_op_ceil_kernel(src, dst_ptr, k_elements, item_ct1);
});
});
}
static inline void ggml_sycl_op_round(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
ggml_sycl_detail::dispatch_ggml_sycl_op_unary(ctx, dst,
[](const auto* src, auto* dst_ptr, int k_elements, queue_ptr stream) {
const int num_blocks = ceil_div(k_elements, 256);
stream->parallel_for(
sycl::nd_range<1>(sycl::range<1>(num_blocks) * sycl::range<1>(256),
sycl::range<1>(256)),
[=](sycl::nd_item<1> item_ct1) {
unary_op_round_kernel(src, dst_ptr, k_elements, item_ct1);
});
});
}
static inline void ggml_sycl_op_trunc(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
ggml_sycl_detail::dispatch_ggml_sycl_op_unary(ctx, dst,
[](const auto* src, auto* dst_ptr, int k_elements, queue_ptr stream) {
const int num_blocks = ceil_div(k_elements, 256);
stream->parallel_for(
sycl::nd_range<1>(sycl::range<1>(num_blocks) * sycl::range<1>(256),
sycl::range<1>(256)),
[=](sycl::nd_item<1> item_ct1) {
unary_op_trunc_kernel(src, dst_ptr, k_elements, item_ct1);
});
});
}
static inline void ggml_sycl_op_acc(ggml_backend_sycl_context & ctx, ggml_tensor *dst) {
GGML_ASSERT(dst->src[0]->type == GGML_TYPE_F32);
GGML_ASSERT(dst->src[1]->type == GGML_TYPE_F32);
@@ -1122,3 +1222,23 @@ void ggml_sycl_arange(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/0);
ggml_sycl_detail::ggml_sycl_op_arange(ctx, dst);
}
void ggml_sycl_floor(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/1);
ggml_sycl_op_floor(ctx, dst);
}
void ggml_sycl_ceil(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/1);
ggml_sycl_op_ceil(ctx, dst);
}
void ggml_sycl_round(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/1);
ggml_sycl_op_round(ctx, dst);
}
void ggml_sycl_trunc(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
scope_op_debug_print scope_dbg_print(__func__, dst, /*num_src=*/1);
ggml_sycl_op_trunc(ctx, dst);
}