fix vulkan ggml_acc only works in 3d but not 4d (#19426)
* fix vulkan ggml_acc only works in 3d but not 4d * removed clamp in test_acc_block * use the correct stride and its test case * cuda : fix "supports op" condition * change src0 to src1 in ggml_vk_acc. Update acc.comp with jeffbolznv\'s suggestion except to keep the boundary check * version without boundary check * revert back to boundary check version --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
@@ -13,17 +13,18 @@ void main() {
|
||||
|
||||
const uint offset = p.param3;
|
||||
const uint src1_i = idx - offset;
|
||||
const uint oz = src1_i / p.nb02;
|
||||
const uint oy = (src1_i - (oz * p.nb02)) / p.nb01;
|
||||
const uint ox = src1_i % p.nb01;
|
||||
const uint i3 = src1_i / p.nb03;
|
||||
const uint rem2 = src1_i - i3 * p.nb03;
|
||||
const uint i2 = rem2 / p.nb02;
|
||||
const uint rem1 = rem2 - i2 * p.nb02;
|
||||
const uint i1 = rem1 / p.nb01;
|
||||
const uint i0 = rem1 % p.nb01;
|
||||
|
||||
uint i00, i01, i02, i03;
|
||||
get_indices(idx, i00, i01, i02, i03);
|
||||
|
||||
if (ox < p.ne10 && oy < p.ne11 && oz < p.ne12) {
|
||||
data_d[get_doffset() + dst_idx(i00, i01, i02, i03)] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + src0_idx(i00, i01, i02, i03)]) + FLOAT_TYPE(data_b[get_boffset() + ox + oy * p.ne10 + oz * p.ne10 * p.ne11]));
|
||||
if (i0 < p.ne10 && i1 < p.ne11 && i2 < p.ne12 && i3 < p.ne13) {
|
||||
data_d[get_doffset() + idx] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + idx]) + FLOAT_TYPE(data_b[get_boffset() + src1_idx(i0, i1, i2, i3)]));
|
||||
} else {
|
||||
data_d[get_doffset() + dst_idx(i00, i01, i02, i03)] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + src0_idx(i00, i01, i02, i03)]));
|
||||
data_d[get_doffset() + idx] = D_TYPE(FLOAT_TYPE(data_a[get_aoffset() + idx]));
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user