ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

SYCL: Refactor ggml_sycl_compute_forward (#11121)

Browse source 
* SYCL: refactor ggml_sycl_compute_forward

* SYCL: add back GGML_USED(dst) to ggml_sycl_cpy

* SYCL: add function name to noop debug

* SYCL: Some device info print refactoring and add details of XMX availability
This commit is contained in:
Akarshan Biswas 2025-01-10 05:43:03 +05:30 • committed by GitHub
parent 1204f97270
commit c6860cc734
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 223 additions and 230 deletions
Download patch file Download diff file Expand all files Collapse all files

96
ggml/src/ggml-sycl/element_wise.cpp
View file

@ -882,149 +882,149 @@ inline void ggml_sycl_op_div(ggml_backend_sycl_context & ctx, const ggml_tensor
}
void ggml_sycl_sqrt(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_sqrt(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_sqrt);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_sqrt);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_sin(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_sin(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_sin);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_sin);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_cos(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_cos(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_cos);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_cos);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_acc(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_acc(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_acc);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_acc);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_gelu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_gelu(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_gelu);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_gelu);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_silu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_silu(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_silu);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_silu);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_gelu_quick(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_gelu_quick(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_gelu_quick);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_gelu_quick);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_tanh(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_tanh(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_tanh);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_tanh);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_relu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_relu(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_relu);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_relu);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_sigmoid(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_sigmoid(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_sigmoid);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_sigmoid);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_hardsigmoid(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_hardsigmoid(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_hardsigmoid);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_hardsigmoid);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_hardswish(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_hardswish(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_hardswish);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_hardswish);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_exp(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_exp(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_exp);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_exp);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_log(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_log(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_log);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_log);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_neg(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_neg(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_neg);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_neg);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_step(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_step(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_step);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_step);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_leaky_relu(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_leaky_relu(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_leaky_relu);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_leaky_relu);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_sqr(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_sqr(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_sqr);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_sqr);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_upscale(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_upscale(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_upscale);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_upscale);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_pad(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_pad(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_pad);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_pad);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_add(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_add(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_add);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_add);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_sub(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_sub(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_sub);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_sub);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_mul(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_mul(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_mul);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_mul);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}
void ggml_sycl_div(ggml_backend_sycl_context & ctx, const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) {
void ggml_sycl_div(ggml_backend_sycl_context & ctx, ggml_tensor * dst) {
GGML_SYCL_DEBUG("call %s\n", __func__);
ggml_sycl_op_flatten(ctx, src0, src1, dst, ggml_sycl_op_div);
ggml_sycl_op_flatten(ctx, dst->src[0], dst->src[1], dst, ggml_sycl_op_div);
GGML_SYCL_DEBUG("call %s done\n", __func__);
}