diff options
| author | Michael Podvitskiy <podvitskiymichael@gmail.com> | 2024-03-11 10:28:51 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-03-11 11:28:51 +0200 |
| commit | 3202361c5b1ba15e695b31209567ef42c22c5c32 (patch) | |
| tree | ab87c2d33904eeb87c4832375fa9261fbf11e871 /ggml-quants.c | |
| parent | 332bdfd7980718abf664bfa5460f2288a3314984 (diff) | |
ggml, ci : Windows ARM runner and build fixes (#5979)
* windows arm ci
* fix `error C2078: too many initializers` with ggml_vld1q_u32 macro for MSVC ARM64
* fix `warning C4146: unary minus operator applied to unsigned type, result still unsigned`
* fix `error C2065: '__fp16': undeclared identifier`
Diffstat (limited to 'ggml-quants.c')
| -rw-r--r-- | ggml-quants.c | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/ggml-quants.c b/ggml-quants.c index f9a3d9fd..86b0764c 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -9374,15 +9374,15 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void * const uint8x16_t idx_l = vld1q_u8(qs); qs += 16; idx.vec_index = vorrq_u16(vmovl_u8(vget_low_u8 (idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+0]), hshift), m256)); - const uint32x4_t aux32x4_0 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], - iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]}; - const uint32x4_t aux32x4_1 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], - iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]}; + const uint32x4_t aux32x4_0 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], + iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]); + const uint32x4_t aux32x4_1 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], + iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]); idx.vec_index = vorrq_u16(vmovl_u8(vget_high_u8(idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+1]), hshift), m256)); - const uint32x4_t aux32x4_2 = {iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], - iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]}; - const uint32x4_t aux32x4_3 = {iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], - iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]}; + const uint32x4_t aux32x4_2 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]], + iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]); + const uint32x4_t aux32x4_3 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]], + iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]); vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16))); |