Files
enginex-ascend-910-llama.cpp/ggml/src/ggml-cuda/unary.cuh

73 lines
2.6 KiB
Plaintext
Raw Normal View History

#include "common.cuh"
#define CUDA_NEG_BLOCK_SIZE 256
2024-09-20 19:04:44 +03:00
#define CUDA_STEP_BLOCK_SIZE 256
#define CUDA_GELU_BLOCK_SIZE 256
#define CUDA_SILU_BLOCK_SIZE 256
#define CUDA_SILU_BACK_BLOCK_SIZE 256
#define CUDA_TANH_BLOCK_SIZE 256
#define CUDA_RELU_BLOCK_SIZE 256
#define CUDA_SIGMOID_BLOCK_SIZE 256
#define CUDA_HARDSIGMOID_BLOCK_SIZE 256
#define CUDA_EXP_BLOCK_SIZE 256
#define CUDA_HARDSWISH_BLOCK_SIZE 256
#define CUDA_SQR_BLOCK_SIZE 256
#define CUDA_SQRT_BLOCK_SIZE 256
2024-08-27 22:01:45 +03:00
#define CUDA_SIN_BLOCK_SIZE 256
#define CUDA_COS_BLOCK_SIZE 256
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158) * implement unary REGLU/GEGLU/SWIGLU cpu ops * relax constraints * duplicate shape of source * fix ggml_vec_geglu_f16 * special case gated ops * implement unary REGLU/GEGLU/SWIGLU cuda ops * tighten constraints again * refactor into GGML_GLU_OP * metal : add glu kernels ggml-ci * add CUDA_GLU_BLOCK_SIZE [no ci] * more constraints and use 64bit ints ggml-ci * 64bit multiplication [no ci] * implement swapped variants (cpu/cuda) * update comment [no ci] ggml-ci * Vulkan: Add GLU ops and shaders * SYCL: Implement fused kernel GEGLU, SWIGLU and REGLU for single up+gate * ggml : implement GLU for split up/gate (#14181) * implement GLU for split up/gate * add tests for ggml_glu_split * Vulkan: Implement glu_split logic and shader support * add split to logging [no ci] * SYCL: refactor element_size ops and add split up and gate support to gated kernels * SYCL: switch GEGLU to use tanh approximation --------- Co-authored-by: 0cc4m <picard12@live.de> Co-authored-by: Akarshan <akarshan@menlo.ai> * GGML: increase OP count in assertion * Refactor: Optimize SYCL element-wise operations with unary function inlining This commit refactors the SYCL element-wise operations to improve performance by: - Inlining unary operations (sgn, abs, elu, gelu, silu, etc.) to reduce kernel launch overhead. - Introducing helper functions `op_xxx` for each unary operation to encapsulate the logic. - Replacing direct kernel calls with calls to these inlined functions. - Using `__dpct_inline__` to encourage compiler inlining. - Minor code cleanup and consistency improvements. The changes aim to reduce kernel launch overhead and improve the overall efficiency of element-wise operations on SYCL devices. * vulkan: Increase workgroup size for GLU, for performance (#14345) * vulkan: Increase workgroup size for GLU, for performance * vulkan: change GLU shaders to do one element per invocation rather than one row per workgroup * merge fix * metal : add support for split and swap ggml-ci --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: 0cc4m <picard12@live.de> Co-authored-by: Akarshan <akarshan@menlo.ai> Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
2025-06-29 11:04:10 +02:00
#define CUDA_GLU_BLOCK_SIZE 256
void ggml_cuda_op_abs(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_sgn(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_neg(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
2024-09-20 19:04:44 +03:00
void ggml_cuda_op_step(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_gelu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_silu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_silu_back(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_gelu_erf(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_gelu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_tanh(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_sigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_hardsigmoid(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_exp(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_hardswish(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_leaky_relu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_sqr(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_sqrt(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
2024-08-27 22:01:45 +03:00
void ggml_cuda_op_sin(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_cos(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_log(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158) * implement unary REGLU/GEGLU/SWIGLU cpu ops * relax constraints * duplicate shape of source * fix ggml_vec_geglu_f16 * special case gated ops * implement unary REGLU/GEGLU/SWIGLU cuda ops * tighten constraints again * refactor into GGML_GLU_OP * metal : add glu kernels ggml-ci * add CUDA_GLU_BLOCK_SIZE [no ci] * more constraints and use 64bit ints ggml-ci * 64bit multiplication [no ci] * implement swapped variants (cpu/cuda) * update comment [no ci] ggml-ci * Vulkan: Add GLU ops and shaders * SYCL: Implement fused kernel GEGLU, SWIGLU and REGLU for single up+gate * ggml : implement GLU for split up/gate (#14181) * implement GLU for split up/gate * add tests for ggml_glu_split * Vulkan: Implement glu_split logic and shader support * add split to logging [no ci] * SYCL: refactor element_size ops and add split up and gate support to gated kernels * SYCL: switch GEGLU to use tanh approximation --------- Co-authored-by: 0cc4m <picard12@live.de> Co-authored-by: Akarshan <akarshan@menlo.ai> * GGML: increase OP count in assertion * Refactor: Optimize SYCL element-wise operations with unary function inlining This commit refactors the SYCL element-wise operations to improve performance by: - Inlining unary operations (sgn, abs, elu, gelu, silu, etc.) to reduce kernel launch overhead. - Introducing helper functions `op_xxx` for each unary operation to encapsulate the logic. - Replacing direct kernel calls with calls to these inlined functions. - Using `__dpct_inline__` to encourage compiler inlining. - Minor code cleanup and consistency improvements. The changes aim to reduce kernel launch overhead and improve the overall efficiency of element-wise operations on SYCL devices. * vulkan: Increase workgroup size for GLU, for performance (#14345) * vulkan: Increase workgroup size for GLU, for performance * vulkan: change GLU shaders to do one element per invocation rather than one row per workgroup * merge fix * metal : add support for split and swap ggml-ci --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: 0cc4m <picard12@live.de> Co-authored-by: Akarshan <akarshan@menlo.ai> Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
2025-06-29 11:04:10 +02:00
2025-07-13 02:33:16 -07:00
void ggml_cuda_op_elu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
ggml : implement REGLU/GEGLU/SWIGLU ops (#14158) * implement unary REGLU/GEGLU/SWIGLU cpu ops * relax constraints * duplicate shape of source * fix ggml_vec_geglu_f16 * special case gated ops * implement unary REGLU/GEGLU/SWIGLU cuda ops * tighten constraints again * refactor into GGML_GLU_OP * metal : add glu kernels ggml-ci * add CUDA_GLU_BLOCK_SIZE [no ci] * more constraints and use 64bit ints ggml-ci * 64bit multiplication [no ci] * implement swapped variants (cpu/cuda) * update comment [no ci] ggml-ci * Vulkan: Add GLU ops and shaders * SYCL: Implement fused kernel GEGLU, SWIGLU and REGLU for single up+gate * ggml : implement GLU for split up/gate (#14181) * implement GLU for split up/gate * add tests for ggml_glu_split * Vulkan: Implement glu_split logic and shader support * add split to logging [no ci] * SYCL: refactor element_size ops and add split up and gate support to gated kernels * SYCL: switch GEGLU to use tanh approximation --------- Co-authored-by: 0cc4m <picard12@live.de> Co-authored-by: Akarshan <akarshan@menlo.ai> * GGML: increase OP count in assertion * Refactor: Optimize SYCL element-wise operations with unary function inlining This commit refactors the SYCL element-wise operations to improve performance by: - Inlining unary operations (sgn, abs, elu, gelu, silu, etc.) to reduce kernel launch overhead. - Introducing helper functions `op_xxx` for each unary operation to encapsulate the logic. - Replacing direct kernel calls with calls to these inlined functions. - Using `__dpct_inline__` to encourage compiler inlining. - Minor code cleanup and consistency improvements. The changes aim to reduce kernel launch overhead and improve the overall efficiency of element-wise operations on SYCL devices. * vulkan: Increase workgroup size for GLU, for performance (#14345) * vulkan: Increase workgroup size for GLU, for performance * vulkan: change GLU shaders to do one element per invocation rather than one row per workgroup * merge fix * metal : add support for split and swap ggml-ci --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> Co-authored-by: 0cc4m <picard12@live.de> Co-authored-by: Akarshan <akarshan@menlo.ai> Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
2025-06-29 11:04:10 +02:00
void ggml_cuda_op_reglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_geglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_swiglu(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_geglu_erf(ggml_backend_cuda_context & ctx, ggml_tensor * dst);
void ggml_cuda_op_geglu_quick(ggml_backend_cuda_context & ctx, ggml_tensor * dst);