Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2024-12-25 13:58:46 +01:00
Code Issues Packages Projects Releases Wiki Activity

ggml : add ARM_NEON dequantize_row_q4_1()

Browse Source
This commit is contained in:
Georgi Gerganov 2023-03-29 22:10:01 +03:00
parent f202ada131
commit cea1c85948
No known key found for this signature in database
GPG Key ID: 449E073F9DC10735
1 changed files with 44 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

44
ggml.c
View File

@ -1016,6 +1016,50 @@ static void dequantize_row_q4_1(const void * restrict vx, float * restrict y, in
}
}
}
#elif defined(__ARM_NEON)
for (int i = 0; i < nb; i++) {
const float32x4_t vd = vdupq_n_f32(x[i].d);
const float32x4_t vm = vdupq_n_f32(x[i].m);
const uint8_t * restrict pp = x[i].qs;
for (int l = 0; l < QK; l += 16) {
// Load 16x4-bit integers into 8x8-bit integers
const uint8x8_t v8 = vld1_u8(pp + l/2);
// Expand 4-bit qs to 8-bit bytes
const uint8x8_t v0 = vand_u8(v8, vdup_n_u8(0x0f));
const uint8x8_t v1 = vshr_n_u8(v8, 4);
// Interleave and combine
const uint8x8_t vx_0 = vzip1_u8(v0, v1);
const uint8x8_t vx_1 = vzip2_u8(v0, v1);
const uint8x16_t vq = vcombine_u8(vx_0, vx_1);
// convert to 2x uint16x8_t
const uint16x8_t vi_0 = vmovl_s8(vget_low_u8 (vq));
const uint16x8_t vi_1 = vmovl_s8(vget_high_u8(vq));
// convert to 4x float32x4_t
const float32x4_t vf_0 = vcvtq_f32_u32(vmovl_u16(vget_low_u16 (vi_0)));
const float32x4_t vf_1 = vcvtq_f32_u32(vmovl_u16(vget_high_u16(vi_0)));
const float32x4_t vf_2 = vcvtq_f32_u32(vmovl_u16(vget_low_u16 (vi_1)));
const float32x4_t vf_3 = vcvtq_f32_u32(vmovl_u16(vget_high_u16(vi_1)));
// multiply by d and add m
const float32x4_t r0 = vmlaq_f32(vm, vf_0, vd);
const float32x4_t r1 = vmlaq_f32(vm, vf_1, vd);
const float32x4_t r2 = vmlaq_f32(vm, vf_2, vd);
const float32x4_t r3 = vmlaq_f32(vm, vf_3, vd);
// Store
vst1q_f32(y + i*QK + l + 0, r0);
vst1q_f32(y + i*QK + l + 4, r1);
vst1q_f32(y + i*QK + l + 8, r2);
vst1q_f32(y + i*QK + l + 12, r3);
}
}
#else
for (int i = 0; i < nb; i++) {
const float d = x[i].d;