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

metal : add count_equal op (#18314)

Browse Source 
* add count equal for metal

* remove trailing whitespace

* updated doc ops table

* changed shmem to i32

* added multi tg and templating

* removed BLAS support from Metal docs

* Apply suggestions from code review

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* add memset to set dst to 0

* metal : cleanup

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
gatbontonpc
2025-12-31 10:39:48 +02:00
committed by GitHub
co-authored by Georgi Gerganov
parent ecc343de63
commit 9a6369bb60
9 changed files with 585 additions and 324 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-metal/ggml-metal.metal
+73
View File
@@ -1790,6 +1790,7 @@ kernel void kernel_op_sum_f32(
return;
}
// TODO: become function constant
const uint nsg = (ntg.x + 31) / 32;
float sumf = 0;
@@ -9914,3 +9915,75 @@ kernel void kernel_opt_step_sgd_f32(
x[gid] = x[gid] * (1.0f - pars[0] * pars[1]) - pars[0] * g[gid];
}
template<typename T>
kernel void kernel_memset(
constant ggml_metal_kargs_fill & args,
device T * dst,
uint tpig[[thread_position_in_grid]]) {
dst[tpig] = args.val;
}
typedef decltype(kernel_memset<int64_t>) kernel_memset_t;
template [[host_name("kernel_memset_i64")]] kernel kernel_memset_t kernel_memset<int64_t>;
constant short FC_count_equal_nsg [[function_constant(FC_COUNT_EQUAL + 0)]];
template<typename T>
kernel void kernel_count_equal(
constant ggml_metal_kargs_count_equal & args,
device const char * src0,
device const char * src1,
device atomic_int * dst,
threadgroup int32_t * shmem_i32 [[threadgroup(0)]],
uint3 tgpig[[threadgroup_position_in_grid]],
ushort3 tpitg[[thread_position_in_threadgroup]],
ushort sgitg[[simdgroup_index_in_threadgroup]],
ushort tiisg[[thread_index_in_simdgroup]],
ushort3 ntg[[threads_per_threadgroup]]) {
const short NSG = FC_count_equal_nsg;
const int i3 = tgpig.z;
const int i2 = tgpig.y;
const int i1 = tgpig.x;
if (i3 >= args.ne03 || i2 >= args.ne02 || i1 >= args.ne01) {
return;
}
int sum = 0;
device const char * base0 = src0 + i1*args.nb01 + i2*args.nb02 + i3*args.nb03;
device const char * base1 = src1 + i1*args.nb11 + i2*args.nb12 + i3*args.nb13;
for (int64_t i0 = tpitg.x; i0 < args.ne00; i0 += ntg.x) {
const T v0 = *(device const T *)(base0 + i0*args.nb00);
const T v1 = *(device const T *)(base1 + i0*args.nb10);
sum += (v0 == v1);
}
sum = simd_sum(sum);
if (tiisg == 0) {
shmem_i32[sgitg] = sum;
}
threadgroup_barrier(mem_flags::mem_threadgroup);
if (sgitg == 0) {
float v = 0.0f;
if (tpitg.x < NSG) {
v = shmem_i32[tpitg.x];
}
float total = simd_sum(v);
if (tpitg.x == 0) {
atomic_fetch_add_explicit(dst, (int32_t) total, memory_order_relaxed);
}
}
}
typedef decltype(kernel_count_equal<int32_t>) kernel_count_equal_t;
template [[host_name("kernel_count_equal_i32")]] kernel kernel_count_equal_t kernel_count_equal<int32_t>;