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

ggml : add GGML_PAD_REFLECT_1D operation (ggml/1034)

Browse source 
* ggml_pad_reflect_1d defined in header

* implemented on CPU

* called the forward pass

* impl Metal kernel

* added Metal kernel

* added OP_PAD_REFLECT_1D in test-backend-ops.cpp

* add test-pad-reflect-1d test case

* test case support multiple backend
This commit is contained in:
PAB 2024-12-03 20:20:04 +01:00 • committed by Georgi Gerganov
parent d405804be8
commit c2082d93a8
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
6 changed files with 192 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

47
ggml/src/ggml-metal/ggml-metal.metal
View file

@ -2897,6 +2897,53 @@ kernel void kernel_pad_f32(
}
}
kernel void kernel_pad_reflect_1d_f32(
device const char * src0,
device char * dst,
constant int64_t & ne00,
constant int64_t & ne01,
constant int64_t & ne02,
constant int64_t & ne03,
constant int64_t & ne0,
constant uint64_t & nb00,
constant uint64_t & nb01,
constant uint64_t & nb02,
constant uint64_t & nb03,
constant uint64_t & nb0,
constant uint64_t & nb1,
constant uint64_t & nb2,
constant uint64_t & nb3,
constant int32_t & p0,
constant int32_t & p1,
uint3 tgpig[[threadgroup_position_in_grid]],
uint3 tgpg[[threadgroups_per_grid]],
uint3 tpitg[[thread_position_in_threadgroup]],
uint3 ntg[[threads_per_threadgroup]]) {
const int64_t i3 = tgpig.z;
const int64_t i2 = tgpig.y;
const int64_t i1 = tgpig.x;
const int64_t i03 = i3;
const int64_t i02 = i2;
const int64_t i01 = i1;
device const float * src0_ptr = (device const float *) (src0 + i03*nb03 + i02*nb02 + i01*nb01);
device float * dst_ptr = (device float *) (dst + i3*nb3 + i2*nb2 + i1*nb1);
if (i1 < ne01 && i2 < ne02 && i3 < ne03) {
for (int i0 = tpitg.x; i0 < ne0; i0 += ntg.x) {
if (i0 < p0) {
dst_ptr[i0] = src0_ptr[p0 - i0];
} else if (i0 < ne0 - p1) {
dst_ptr[i0] = src0_ptr[i0 - p0];
} else {
dst_ptr[i0] = src0_ptr[(ne0 - p1 - p0) - (p1 + 1 - (ne0 - i0)) - 1];
}
}
}
}
kernel void kernel_arange_f32(
device char * dst,
constant int64_t & ne0,