Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

metal: add col2im_1d op (f32/f16/bf16) (#25176)

Browse Source 
* metal: add col2im_1d op (f32/f16/bf16)

Gather kernel mirroring the CPU/CUDA path: each output (t_out, oc)
reads its ceil(K/s0) source columns with an F32 accumulator, a single
write and no atomics. One thread per output element, 256 per
threadgroup.

* metal: check dst contiguity and type match in supports_op for COL2IM_1D

Align the GGML_OP_COL2IM_1D predicate with the CPU, CUDA, and Vulkan
backends: the kernel writes dst with linear indexing and assumes the
same type as src0, so supports_op must also require a contiguous dst
and op->type == op->src[0]->type.

* Update ggml/src/ggml-metal/ggml-metal.metal

Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>

---------

Co-authored-by: YiChen Lv <63285796+forforever73@users.noreply.github.com>
This commit is contained in:
Pascal
2026-07-06 20:47:36 +02:00
committed by GitHub
co-authored by YiChen Lv
parent 74976e1aef
commit f36e5c348b
7 changed files with 125 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal.metal
+43
View File
@@ -4977,6 +4977,49 @@ kernel void kernel_conv_transpose_1d<half>(
uint3 tgpg[[threadgroups_per_grid]]);
template <typename T>
kernel void kernel_col2im_1d(
constant ggml_metal_kargs_col2im_1d & args,
device const T * col,
device T * dst,
uint tgpig [[threadgroup_position_in_grid]],
uint tpitg [[thread_position_in_threadgroup]],
uint ntg [[threads_per_threadgroup]]) {
const int idx = tgpig * ntg + tpitg;
if (idx >= args.T_out * args.OC) {
return;
}
const int t_out = idx % args.T_out;
const int oc = idx / args.T_out;
const int t_abs = t_out + args.p0; // absolute position in uncropped signal
int t_in_min = (t_abs - args.K + args.s0) / args.s0; // ceil((t_abs - K + 1) / s0)
if (t_in_min < 0) {
t_in_min = 0;
}
int t_in_max = t_abs / args.s0;
if (t_in_max >= args.T_in) {
t_in_max = args.T_in - 1;
}
float sum = 0.0f;
for (int t_in = t_in_min; t_in <= t_in_max; t_in++) {
const int k = t_abs - t_in * args.s0;
sum += float(col[(oc * args.K + k) + t_in * args.K_OC]);
}
dst[t_out + oc * args.T_out] = T(sum);
}
template [[host_name("kernel_col2im_1d_f32")]] kernel void kernel_col2im_1d<float>(constant ggml_metal_kargs_col2im_1d &, device const float *, device float *, uint, uint, uint);
template [[host_name("kernel_col2im_1d_f16")]] kernel void kernel_col2im_1d<half>(constant ggml_metal_kargs_col2im_1d &, device const half *, device half *, uint, uint, uint);
#if defined(GGML_METAL_HAS_BF16)
template [[host_name("kernel_col2im_1d_bf16")]] kernel void kernel_col2im_1d<bfloat>(constant ggml_metal_kargs_col2im_1d &, device const bfloat *, device bfloat *, uint, uint, uint);
#endif
typedef void (conv_transpose_2d_t)(
constant ggml_metal_kargs_conv_transpose_2d & args,
device const float * src0,