Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions ggml/src/ggml-vulkan/vulkan-shaders/mul_mat_vec.comp
Original file line number Diff line number Diff line change
Expand Up @@ -105,6 +105,16 @@ void compute_outputs(const uint32_t first_row, const uint32_t num_rows) {
int unroll_count = 4;
uint unrolled_iters = num_iters & ~(unroll_count - 1);

#if K_PER_ITER == 2
// If the K dimension is odd, we need lastiter==true on the last iteration
// so OOB is computed correctly. Skip some unrolling to make that happen.
if ((p.ncols & 1) != 0 &&
unrolled_iters == num_iters &&
unrolled_iters > 0) {
unrolled_iters -= unroll_count;
}
#endif

uint i = 0;
while (i < unrolled_iters) {
// Manually partially unroll the loop
Expand All @@ -113,8 +123,18 @@ void compute_outputs(const uint32_t first_row, const uint32_t num_rows) {
i++;
}
}

unroll_count = 2;
unrolled_iters = num_iters & ~(unroll_count - 1);

#if K_PER_ITER == 2
if ((p.ncols & 1) != 0 &&
unrolled_iters == num_iters &&
unrolled_iters > 0) {
unrolled_iters -= unroll_count;
}
#endif

while (i < unrolled_iters) {
// Manually partially unroll the loop
[[unroll]] for (uint k = 0; k < unroll_count; ++k) {
Expand Down
2 changes: 2 additions & 0 deletions tests/test-backend-ops.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -4204,6 +4204,8 @@ static std::vector<std::unique_ptr<test_case>> make_test_cases_eval() {
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 83, 2, 64, { 8, 1}, {4, 1}));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 64, 45, 128, { 8, 1}, {4, 1}));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 128, 45, 64, { 8, 1}, {4, 1}));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 1056, 1, 193, {1, 1}, {4, 1}, {0, 2, 1, 3}));
test_cases.emplace_back(new test_mul_mat(GGML_TYPE_F16, GGML_TYPE_F32, 1056, 1, 67, {1, 1}, {4, 1}, {0, 2, 1, 3}));

for (auto bs : {1,2,4,8}) {
for (auto nr : {1,4}) {
Expand Down
Loading