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

opencl: Noncontiguous norm, rms_norm, disable fp16 for some ops (#12217)

Browse source 
* opencl: support noncontiguous `norm`

* opencl: support noncontiguous `rms_norm`

* opencl: disable fp16 for `ADD`, `MUL`, `SCALE`, `RELU`, `GELU`, `SILU`, `CLAMP`
This commit is contained in:
lhez 2025-03-06 16:20:35 -08:00 • committed by GitHub
parent 776f9e59cc
commit d76a86d967
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 65 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

70
ggml/src/ggml-opencl/ggml-opencl.cpp
View file

@ -1007,17 +1007,18 @@ static bool ggml_opencl_supports_op(ggml_backend_dev_t dev, const struct ggml_te
case GGML_OP_ADD:
case GGML_OP_SCALE:
case GGML_OP_MUL:
return true;
return op->src[0]->type == GGML_TYPE_F32;
case GGML_OP_UNARY:
switch (ggml_get_unary_op(op)) {
case GGML_UNARY_OP_GELU:
case GGML_UNARY_OP_SILU:
case GGML_UNARY_OP_RELU:
return ggml_is_contiguous(op->src[0]);
return ggml_is_contiguous(op->src[0]) && op->src[0]->type == GGML_TYPE_F32;
default:
return false;
}
case GGML_OP_CLAMP:
return op->src[0]->type == GGML_TYPE_F32;
case GGML_OP_SOFT_MAX:
case GGML_OP_NORM:
case GGML_OP_RMS_NORM:
@ -2573,26 +2574,33 @@ static void ggml_cl_norm(ggml_backend_t backend, const ggml_tensor * src0, const
memcpy(&eps, dst->op_params, sizeof(float));
const int ne00 = src0 ? src0->ne[0] : 0;
const cl_ulong nb01 = src0 ? src0->nb[1] : 0;
const int ne01 = src0 ? src0->ne[1] : 0;
const int ne02 = src0 ? src0->ne[2] : 0;
const int ne03 = src0 ? src0->ne[3] : 0;
GGML_ASSERT(ggml_is_contiguous_1(src0));
const cl_ulong nb01 = src0 ? src0->nb[1] : 0;
const cl_ulong nb02 = src0 ? src0->nb[2] : 0;
const cl_ulong nb03 = src0 ? src0->nb[3] : 0;
const int nth = MIN(64, ne00);
cl_kernel kernel = backend_ctx->kernel_norm;
CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), &extra0->data_device));
CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_ulong), &offset0));
CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), &extrad->data_device));
CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_ulong), &offsetd));
CL_CHECK(clSetKernelArg(kernel, 4, sizeof(int), &ne00));
CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_ulong), &nb01));
CL_CHECK(clSetKernelArg(kernel, 6, sizeof(float), &eps));
CL_CHECK(clSetKernelArg(kernel, 7, sizeof(float)*nth, NULL));
CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), &extra0->data_device));
CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_ulong), &offset0));
CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), &extrad->data_device));
CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_ulong), &offsetd));
CL_CHECK(clSetKernelArg(kernel, 4, sizeof(int), &ne00));
CL_CHECK(clSetKernelArg(kernel, 5, sizeof(int), &ne01));
CL_CHECK(clSetKernelArg(kernel, 6, sizeof(int), &ne02));
CL_CHECK(clSetKernelArg(kernel, 7, sizeof(int), &ne03));
CL_CHECK(clSetKernelArg(kernel, 8, sizeof(cl_ulong), &nb01));
CL_CHECK(clSetKernelArg(kernel, 9, sizeof(cl_ulong), &nb02));
CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_ulong), &nb03));
CL_CHECK(clSetKernelArg(kernel, 11, sizeof(float), &eps));
CL_CHECK(clSetKernelArg(kernel, 12, sizeof(float)*nth, NULL));
const int64_t nrows = ggml_nrows(src0);
size_t global_work_size[] = {(size_t)nrows*nth, 1, 1};
size_t global_work_size[] = {(size_t)ne01*nth, (size_t)ne02, (size_t)ne03};
size_t local_work_size[] = {(size_t)nth, 1, 1};
#ifdef GGML_OPENCL_PROFILING
@ -2630,16 +2638,19 @@ static void ggml_cl_rms_norm(ggml_backend_t backend, const ggml_tensor * src0, c
memcpy(&eps, dst->op_params, sizeof(float));
const int ne00 = src0 ? src0->ne[0] : 0;
const int ne01 = src0 ? src0->ne[1] : 0;
const int ne02 = src0 ? src0->ne[2] : 0;
const int ne03 = src0 ? src0->ne[3] : 0;
const cl_ulong nb01 = src0 ? src0->nb[1] : 0;
const cl_ulong nb02 = src0 ? src0->nb[2] : 0;
const cl_ulong nb03 = src0 ? src0->nb[3] : 0;
GGML_ASSERT(ne00 % 4 == 0);
GGML_ASSERT(ggml_is_contiguous_1(src0));
const int nth = MIN(64, ne00);
const int64_t nrows = ggml_nrows(src0);
size_t global_work_size[] = {(size_t)nrows*nth, 1, 1};
size_t global_work_size[] = {(size_t)ne01*nth, (size_t)ne02, (size_t)ne03};
size_t local_work_size[] = {(size_t)nth, 1, 1};
cl_kernel kernel = backend_ctx->kernel_rms_norm;
@ -2654,15 +2665,20 @@ static void ggml_cl_rms_norm(ggml_backend_t backend, const ggml_tensor * src0, c
sizeof(local_work_size), local_work_size,
sizeof(size_t), &sgs, NULL));
CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), &extra0->data_device));
CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_ulong), &offset0));
CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), &extrad->data_device));
CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_ulong), &offsetd));
CL_CHECK(clSetKernelArg(kernel, 4, sizeof(int), &ne00));
CL_CHECK(clSetKernelArg(kernel, 5, sizeof(cl_ulong), &nb01));
CL_CHECK(clSetKernelArg(kernel, 6, sizeof(float), &eps));
CL_CHECK(clSetKernelArg(kernel, 0, sizeof(cl_mem), &extra0->data_device));
CL_CHECK(clSetKernelArg(kernel, 1, sizeof(cl_ulong), &offset0));
CL_CHECK(clSetKernelArg(kernel, 2, sizeof(cl_mem), &extrad->data_device));
CL_CHECK(clSetKernelArg(kernel, 3, sizeof(cl_ulong), &offsetd));
CL_CHECK(clSetKernelArg(kernel, 4, sizeof(int), &ne00));
CL_CHECK(clSetKernelArg(kernel, 5, sizeof(int), &ne01));
CL_CHECK(clSetKernelArg(kernel, 6, sizeof(int), &ne02));
CL_CHECK(clSetKernelArg(kernel, 7, sizeof(int), &ne03));
CL_CHECK(clSetKernelArg(kernel, 8, sizeof(cl_ulong), &nb01));
CL_CHECK(clSetKernelArg(kernel, 9, sizeof(cl_ulong), &nb02));
CL_CHECK(clSetKernelArg(kernel, 10, sizeof(cl_ulong), &nb03));
CL_CHECK(clSetKernelArg(kernel, 11, sizeof(float), &eps));
// This is local memory - the size depends on subgroup size.
CL_CHECK(clSetKernelArg(kernel, 7, sizeof(float)*nth/sgs, NULL));
CL_CHECK(clSetKernelArg(kernel, 12, sizeof(float)*nth/sgs, NULL));
#ifdef GGML_OPENCL_PROFILING
cl_event evt;