Fix OpenCL kernels for the new formats
This commit is contained in:
Henri Vasserman
parent
fb62f92433
commit
3243b9943a
1 changed files with 93 additions and 73 deletions
166
ggml-opencl.c
166
ggml-opencl.c
|
|
@ -12,109 +12,129 @@
|
|||
#define MULTILINE_QUOTE(...) #__VA_ARGS__
|
||||
const char * clblast_dequant = MULTILINE_QUOTE(
|
||||
|
||||
typedef uchar uint8_t;
|
||||
typedef int int32_t;
|
||||
typedef uint uint32_t;
|
||||
|
||||
constant uint QK4_0 = 32;
|
||||
struct block_q4_0
|
||||
{
|
||||
float d;
|
||||
uchar qs[16];
|
||||
uchar qs[QK4_0 / 2];
|
||||
};
|
||||
|
||||
__kernel void dequantize_row_q4_0(__global struct block_q4_0* blocks, __global float* result) {
|
||||
const uint i = get_global_id(0) / 32;
|
||||
const uint l = get_local_id(0);
|
||||
|
||||
const float d = blocks[i].d;
|
||||
|
||||
const uchar vi = blocks[i].qs[l];
|
||||
|
||||
const uint index = i*32 + l*2;
|
||||
result[index + 0] = ((vi & 0xf) - 8)*d;
|
||||
result[index + 1] = ((vi >> 4) - 8)*d;
|
||||
}
|
||||
|
||||
constant uint QK4_1 = 32;
|
||||
struct block_q4_1
|
||||
{
|
||||
float d;
|
||||
float m;
|
||||
uchar qs[16];
|
||||
uchar qs[QK4_1 / 2];
|
||||
};
|
||||
|
||||
__kernel void dequantize_row_q4_1(__global struct block_q4_1* blocks, __global float* result) {
|
||||
const uint i = get_global_id(0) / 32;
|
||||
const uint l = get_local_id(0);
|
||||
|
||||
const float d = blocks[i].d;
|
||||
const float m = blocks[i].m;
|
||||
|
||||
const uchar vi = blocks[i].qs[l];
|
||||
|
||||
const uint index = i*32 + l*2;
|
||||
result[index + 0] = (vi & 0xf) * d + m;
|
||||
result[index + 1] = (vi >> 4) * d + m;
|
||||
}
|
||||
|
||||
constant uint QK5_0 = 32;
|
||||
struct block_q5_0
|
||||
{
|
||||
float d;
|
||||
uint qh;
|
||||
uchar qs[16];
|
||||
uchar qs[QK5_0 / 2];
|
||||
};
|
||||
|
||||
__kernel void dequantize_row_q5_0(__global struct block_q5_0* blocks, __global float* result) {
|
||||
const uint i = get_global_id(0) / 32;
|
||||
const uint l = get_local_id(0);
|
||||
|
||||
const float d = blocks[i].d;
|
||||
|
||||
const uchar vi = blocks[i].qs[l];
|
||||
|
||||
const uint l2 = l * 2;
|
||||
|
||||
const uchar vh0 = ((blocks[i].qh & (1 << (l2 + 0))) >> (l2 + 0)) << 4;
|
||||
const uchar vh1 = ((blocks[i].qh & (1 << (l2 + 1))) >> (l2 + 1)) << 4;
|
||||
|
||||
const uint index = i*32 + l2;
|
||||
result[index + 0] = (((vi & 0xf) | vh0) - 16)*d;
|
||||
result[index + 1] = (((vi >> 4) | vh1) - 16)*d;
|
||||
}
|
||||
|
||||
constant uint QK5_1 = 32;
|
||||
struct block_q5_1
|
||||
{
|
||||
ushort d;
|
||||
ushort m;
|
||||
uint qh;
|
||||
uchar qs[16];
|
||||
uchar qs[QK5_1 / 2];
|
||||
};
|
||||
|
||||
__kernel void dequantize_row_q5_1(__global struct block_q5_1* blocks, __global float* result) {
|
||||
const uint i = get_global_id(0) / 32;
|
||||
const uint l = get_local_id(0);
|
||||
|
||||
const float d = vload_half(0, (__global half*) &blocks[i].d);
|
||||
const float m = vload_half(0, (__global half*) &blocks[i].m);
|
||||
|
||||
const uchar vi = blocks[i].qs[l];
|
||||
|
||||
const uint l2 = l * 2;
|
||||
|
||||
const uchar vh0 = ((blocks[i].qh & (1 << (l2 + 0))) >> (l2 + 0)) << 4;
|
||||
const uchar vh1 = ((blocks[i].qh & (1 << (l2 + 1))) >> (l2 + 1)) << 4;
|
||||
|
||||
const uint index = i*32 + l2;
|
||||
result[index + 0] = ((vi & 0xf) | vh0)*d + m;
|
||||
result[index + 1] = ((vi >> 4) | vh1)*d + m;
|
||||
}
|
||||
|
||||
constant uint QK8_0 = 32;
|
||||
struct block_q8_0
|
||||
{
|
||||
float d;
|
||||
char qs[32];
|
||||
char qs[QK8_0];
|
||||
};
|
||||
|
||||
__kernel void dequantize_row_q8_0(__global struct block_q8_0* blocks, __global float* result) {
|
||||
const uint i = get_global_id(0) / 32;
|
||||
const uint l = get_local_id(0);
|
||||
|
||||
result[i*32 + l] = blocks[i].qs[l] * blocks[i].d;
|
||||
__kernel void dequantize_row_q4_0(__global struct block_q4_0* x, __global float* y) {
|
||||
constant uint qk = QK4_0;
|
||||
|
||||
const uint i = get_global_id(0) / qk;
|
||||
const uint j = get_local_id(0);
|
||||
|
||||
const float d = x[i].d;
|
||||
|
||||
const int x0 = (x[i].qs[j] & 0xf) - 8;
|
||||
const int x1 = (x[i].qs[j] >> 4) - 8;
|
||||
|
||||
y[i*qk + j + 0 ] = x0*d;
|
||||
y[i*qk + j + qk/2] = x1*d;
|
||||
}
|
||||
|
||||
__kernel void dequantize_row_q4_1(__global struct block_q4_1* x, __global float* y) {
|
||||
constant uint qk = QK4_1;
|
||||
|
||||
const uint i = get_global_id(0) / qk;
|
||||
const uint j = get_local_id(0);
|
||||
|
||||
const float d = x[i].d;
|
||||
const float m = x[i].m;
|
||||
|
||||
const int x0 = (x[i].qs[j] & 0xf);
|
||||
const int x1 = (x[i].qs[j] >> 4);
|
||||
|
||||
y[i*qk + j + 0 ] = x0*d + m;
|
||||
y[i*qk + j + qk/2] = x1*d + m;
|
||||
}
|
||||
|
||||
__kernel void dequantize_row_q5_0(__global struct block_q5_0* x, __global float* y) {
|
||||
constant uint qk = QK5_0;
|
||||
|
||||
const uint i = get_global_id(0) / qk;
|
||||
const uint j = get_local_id(0);
|
||||
|
||||
const float d = x[i].d;
|
||||
|
||||
uint32_t qh = x[i].qh;
|
||||
|
||||
const uint8_t xh_0 = ((qh >> (j + 0)) << 4) & 0x10;
|
||||
const uint8_t xh_1 = ((qh >> (j + 12)) ) & 0x10;
|
||||
|
||||
const int32_t x0 = ((x[i].qs[j] & 0xf) | xh_0) - 16;
|
||||
const int32_t x1 = ((x[i].qs[j] >> 4) | xh_1) - 16;
|
||||
|
||||
y[i*qk + j + 0 ] = x0*d;
|
||||
y[i*qk + j + qk/2] = x1*d;
|
||||
}
|
||||
|
||||
__kernel void dequantize_row_q5_1(__global struct block_q5_1* x, __global float* y) {
|
||||
constant uint qk = QK5_1;
|
||||
|
||||
const uint i = get_global_id(0) / qk;
|
||||
const uint j = get_local_id(0);
|
||||
|
||||
const float d = vload_half(0, (__global half*) &x[i].d);
|
||||
const float m = vload_half(0, (__global half*) &x[i].m);
|
||||
|
||||
uint32_t qh = x[i].qh;
|
||||
|
||||
const uint8_t xh_0 = ((qh >> (j + 0)) << 4) & 0x10;
|
||||
const uint8_t xh_1 = ((qh >> (j + 12)) ) & 0x10;
|
||||
|
||||
const int x0 = (x[i].qs[j] & 0xf) | xh_0;
|
||||
const int x1 = (x[i].qs[j] >> 4) | xh_1;
|
||||
|
||||
y[i*qk + j + 0 ] = x0*d + m;
|
||||
y[i*qk + j + qk/2] = x1*d + m;
|
||||
}
|
||||
|
||||
__kernel void dequantize_row_q8_0(__global struct block_q8_0* x, __global float* y) {
|
||||
constant uint qk = QK8_0;
|
||||
const uint i = get_global_id(0) / qk;
|
||||
const uint j = get_local_id(0);
|
||||
|
||||
const float d = x[i].d;
|
||||
y[i*qk + j] = x[i].qs[j]*d;
|
||||
}
|
||||
|
||||
);
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue