metal: Implement ROLL op (#21946)

* nix: support unified apple-sdk

* Impl roll op for Metal

* Revert "nix: support unified apple-sdk"

This reverts commit abfa473360471532c547de8b202c780507924d4b.

* update ops.md

* update op docs
This commit is contained in:
Kusha Gharahi
2026-04-16 11:54:37 +03:00
committed by GitHub
parent 1e796eb41f
commit ae2d34899e
9 changed files with 3072 additions and 856 deletions
+34
View File
@@ -5247,6 +5247,40 @@ kernel void kernel_upscale_bicubic_f32(
}
}
kernel void kernel_roll_f32(
constant ggml_metal_kargs_roll & args,
device const char * src0,
device char * dst,
uint3 tgpig[[threadgroup_position_in_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;
device const float * src0_ptr = (device const float *) src0;
device float * dst_ptr = (device float *) dst;
for (int i0 = tpitg.x; i0 < args.ne0; i0 += ntg.x) {
// apply shifts and wrap around
int64_t i00 = i0 - args.s0;
int64_t i01 = i1 - args.s1;
int64_t i02 = i2 - args.s2;
int64_t i03 = i3 - args.s3;
if (i00 < 0) { i00 += args.ne00; } else if (i00 >= args.ne00) { i00 -= args.ne00; }
if (i01 < 0) { i01 += args.ne01; } else if (i01 >= args.ne01) { i01 -= args.ne01; }
if (i02 < 0) { i02 += args.ne02; } else if (i02 >= args.ne02) { i02 -= args.ne02; }
if (i03 < 0) { i03 += args.ne03; } else if (i03 >= args.ne03) { i03 -= args.ne03; }
int64_t src_idx = i03*args.ne02*args.ne01*args.ne00 + i02*args.ne01*args.ne00 + i01*args.ne00 + i00;
int64_t dst_idx = i3 *args.ne2 *args.ne1 *args.ne0 + i2 *args.ne1 *args.ne0 + i1 *args.ne0 + i0;
dst_ptr[dst_idx] = src0_ptr[src_idx];
}
}
kernel void kernel_pad_f32(
constant ggml_metal_kargs_pad & args,
device const char * src0,