diff --git a/ggml/src/ggml-cpu/arch/wasm/quants.c b/ggml/src/ggml-cpu/arch/wasm/quants.c index 0a7119b4e..ced2cf3b8 100644 --- a/ggml/src/ggml-cpu/arch/wasm/quants.c +++ b/ggml/src/ggml-cpu/arch/wasm/quants.c @@ -262,13 +262,22 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi v128_t v0_0 = wasm_v128_load(x0->qs); v128_t v0_0l = wasm_v128_and(v0_0, m4b); v128_t v0_0h = wasm_u8x16_shr(v0_0, 4); - v128_t v0_0ls = wasm_i8x16_sub(v0_0l, s8b); - v128_t v0_0hs = wasm_i8x16_sub(v0_0h, s8b); // Load y0 vectors v128_t y0_l = wasm_v128_load(y0->qs); v128_t y0_h = wasm_v128_load(y0->qs + 16); +# if defined(__wasm_relaxed_simd__) + // unsigned nibbles (0..15) in the 7-bit operand, then subtract 8*sum(y) + v128_t dp0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y0_l, v0_0l, wasm_i32x4_splat(0)); + dp0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y0_h, v0_0h, dp0); + v128_t ys0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y0_l, s8b, wasm_i32x4_splat(0)); + ys0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y0_h, s8b, ys0); + dp0 = wasm_i32x4_sub(dp0, ys0); +# else + v128_t v0_0ls = wasm_i8x16_sub(v0_0l, s8b); + v128_t v0_0hs = wasm_i8x16_sub(v0_0h, s8b); + // Extend to i16x8 and compute dot products v128_t dx0l = wasm_i16x8_extend_low_i8x16(v0_0ls); v128_t dx0h = wasm_i16x8_extend_high_i8x16(v0_0ls); @@ -290,18 +299,27 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i32x4_dot_i16x8(dx0hh, dy0hh) ) ); +# endif // Load and process x1 v128_t v0_1 = wasm_v128_load(x1->qs); v128_t v0_1l = wasm_v128_and(v0_1, m4b); v128_t v0_1h = wasm_u8x16_shr(v0_1, 4); - v128_t v0_1ls = wasm_i8x16_sub(v0_1l, s8b); - v128_t v0_1hs = wasm_i8x16_sub(v0_1h, s8b); // Load y1 vectors v128_t y1_l = wasm_v128_load(y1->qs); v128_t y1_h = wasm_v128_load(y1->qs + 16); +# if defined(__wasm_relaxed_simd__) + // unsigned nibbles (0..15) in the 7-bit operand, then subtract 8*sum(y) + v128_t dp1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y1_l, v0_1l, wasm_i32x4_splat(0)); + dp1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y1_h, v0_1h, dp1); + v128_t ys1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y1_l, s8b, wasm_i32x4_splat(0)); + ys1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(y1_h, s8b, ys1); + dp1 = wasm_i32x4_sub(dp1, ys1); +# else + v128_t v0_1ls = wasm_i8x16_sub(v0_1l, s8b); + v128_t v0_1hs = wasm_i8x16_sub(v0_1h, s8b); // Extend to i16x8 and compute dot products v128_t dx1l = wasm_i16x8_extend_low_i8x16(v0_1ls); v128_t dx1h = wasm_i16x8_extend_high_i8x16(v0_1ls); @@ -323,6 +341,7 @@ void ggml_vec_dot_q4_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i32x4_dot_i16x8(dx1hh, dy1hh) ) ); +# endif // Accumulate results with scaling float scale0 = GGML_CPU_FP16_TO_FP32(x0->d) * GGML_CPU_FP16_TO_FP32(y0->d); @@ -461,10 +480,18 @@ void ggml_vec_dot_q5_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi // extract the 5th bit memcpy(&qh_, x0->qh, sizeof(qh_)); +# if defined(__wasm_relaxed_simd__) + // the high bit as is: unsigned 5-bit quants for the 7-bit operand + tmp[0] = table_b2b_0[(qh_ >> 0) & 0xFF]; + tmp[1] = table_b2b_0[(qh_ >> 8) & 0xFF]; + tmp[2] = table_b2b_0[(qh_ >> 16) & 0xFF]; + tmp[3] = table_b2b_0[(qh_ >> 24) ]; +# else tmp[0] = table_b2b_1[(qh_ >> 0) & 0xFF]; tmp[1] = table_b2b_1[(qh_ >> 8) & 0xFF]; tmp[2] = table_b2b_1[(qh_ >> 16) & 0xFF]; tmp[3] = table_b2b_1[(qh_ >> 24) ]; +# endif const v128_t qhl = wasm_v128_load(tmp + 0); const v128_t qhh = wasm_v128_load(tmp + 2); @@ -475,14 +502,29 @@ void ggml_vec_dot_q5_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi const v128_t v0l = wasm_v128_and (v0, m4b); const v128_t v0h = wasm_u8x16_shr(v0, 4); - // add high bit and sub 16 (equivalent to sub 0x10 when bit is zero) - const v128_t v0lf = wasm_i8x16_sub(v0l, qhl); - const v128_t v0hf = wasm_i8x16_sub(v0h, qhh); - // load y const v128_t v1l = wasm_v128_load(y0->qs); const v128_t v1h = wasm_v128_load(y0->qs + 16); +# if defined(__wasm_relaxed_simd__) + // unsigned 5-bit quants (0..31) in the 7-bit operand, then subtract 16*sum(y) + const v128_t s16b = wasm_i8x16_splat(0x10); + const v128_t v0lu = wasm_v128_or(v0l, qhl); + const v128_t v0hu = wasm_v128_or(v0h, qhh); + + v128_t dp = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(v1l, v0lu, wasm_i32x4_splat(0)); + dp = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(v1h, v0hu, dp); + v128_t ys = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(v1l, s16b, wasm_i32x4_splat(0)); + ys = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(v1h, s16b, ys); + dp = wasm_i32x4_sub(dp, ys); + + sumv = wasm_f32x4_add(sumv, wasm_f32x4_mul(wasm_f32x4_convert_i32x4(dp), + wasm_f32x4_splat(GGML_CPU_FP16_TO_FP32(x0->d) * GGML_CPU_FP16_TO_FP32(y0->d)))); +# else + // add high bit and sub 16 (equivalent to sub 0x10 when bit is zero) + const v128_t v0lf = wasm_i8x16_sub(v0l, qhl); + const v128_t v0hf = wasm_i8x16_sub(v0h, qhh); + // int8x16 -> int16x8 const v128_t v0lfl = wasm_i16x8_extend_low_i8x16 (v0lf); const v128_t v0lfh = wasm_i16x8_extend_high_i8x16(v0lf); @@ -502,6 +544,7 @@ void ggml_vec_dot_q5_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i32x4_add(wasm_i32x4_dot_i16x8(v0hfl, v1hl), wasm_i32x4_dot_i16x8(v0hfh, v1hh)))), wasm_f32x4_splat(GGML_CPU_FP16_TO_FP32(x0->d) * GGML_CPU_FP16_TO_FP32(y0->d)))); +# endif } sumf = wasm_f32x4_extract_lane(sumv, 0) + wasm_f32x4_extract_lane(sumv, 1) + @@ -578,6 +621,13 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * GGML_RESTRICT s, size_t bs, const voi const v128_t v1l = wasm_v128_load(y0->qs); const v128_t v1h = wasm_v128_load(y0->qs + 16); +# if defined(__wasm_relaxed_simd__) + v128_t dp = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(v1l, v0lf, wasm_i32x4_splat(0)); + dp = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(v1h, v0hf, dp); + + sumv = wasm_f32x4_add(sumv, wasm_f32x4_mul(wasm_f32x4_convert_i32x4(dp), + wasm_f32x4_splat(GGML_CPU_FP16_TO_FP32(x0->d) * GGML_CPU_FP16_TO_FP32(y0->d)))); +# else // int8x16 -> int16x8 const v128_t v0lfl = wasm_i16x8_extend_low_i8x16 (v0lf); const v128_t v0lfh = wasm_i16x8_extend_high_i8x16(v0lf); @@ -597,6 +647,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i32x4_add(wasm_i32x4_dot_i16x8(v0hfl, v1hl), wasm_i32x4_dot_i16x8(v0hfh, v1hh)))), wasm_f32x4_splat(GGML_CPU_FP16_TO_FP32(x0->d) * GGML_CPU_FP16_TO_FP32(y0->d)))); +# endif } sumf = wasm_f32x4_extract_lane(sumv, 0) + wasm_f32x4_extract_lane(sumv, 1) + @@ -642,6 +693,17 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi const v128_t y0_0 = wasm_v128_load(y0->qs); const v128_t y0_1 = wasm_v128_load(y0->qs + 16); +# if defined(__wasm_relaxed_simd__) + // |x| (0..127) in the 7-bit operand and y*sign(x) in the other; relies on + // q8_0 values being in -127..127, as ggml's quantizers produce + const v128_t zero = wasm_i8x16_splat(0); + const v128_t sx0 = wasm_i8x16_lt(x0_0, zero); + const v128_t sx1 = wasm_i8x16_lt(x0_1, zero); + const v128_t ys0 = wasm_i8x16_sub(wasm_v128_xor(y0_0, sx0), sx0); + const v128_t ys1 = wasm_i8x16_sub(wasm_v128_xor(y0_1, sx1), sx1); + v128_t sum_dots = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(ys0, wasm_i8x16_abs(x0_0), wasm_i32x4_splat(0)); + sum_dots = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(ys1, wasm_i8x16_abs(x0_1), sum_dots); +# else // Extend 8-bit to 16-bit const v128_t x0_0l = wasm_i16x8_extend_low_i8x16(x0_0); const v128_t x0_0h = wasm_i16x8_extend_high_i8x16(x0_0); @@ -661,7 +723,7 @@ void ggml_vec_dot_q8_0_q8_0(int n, float * GGML_RESTRICT s, size_t bs, const voi // Sum all dot products const v128_t sum_dots = wasm_i32x4_add(wasm_i32x4_add(dx0_0, dx0_1), wasm_i32x4_add(dx1_0, dx1_1)); - +# endif // Convert to float and accumulate const float scale = GGML_CPU_FP16_TO_FP32(x0->d) * GGML_CPU_FP16_TO_FP32(y0->d); sumv = wasm_f32x4_add(sumv, wasm_f32x4_mul(wasm_f32x4_convert_i32x4(sum_dots), wasm_f32x4_splat(scale))); @@ -750,6 +812,10 @@ void ggml_vec_dot_q2_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi v128_t q2_shift_1 = wasm_u8x16_shr(q2_1, shift); v128_t q2_bits_1 = wasm_v128_and(q2_shift_1, wasm_i8x16_splat(0x03)); +# if defined(__wasm_relaxed_simd__) + v128_t p_sum0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(q8_0, q2_bits_0, wasm_i32x4_splat(0)); + v128_t p_sum1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(q8_1, q2_bits_1, wasm_i32x4_splat(0)); +# else // Calculate dot products v128_t p0 = wasm_i32x4_dot_i16x8( wasm_i16x8_extend_low_i8x16(q8_0), @@ -768,10 +834,14 @@ void ggml_vec_dot_q2_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i16x8_extend_high_i8x16(q2_bits_1) ); + v128_t p_sum0 = wasm_i32x4_add(p0, p1); + v128_t p_sum1 = wasm_i32x4_add(p2, p3); +# endif + // Accumulate scaled results v128_t scaled = wasm_i32x4_add( - wasm_i32x4_mul(wasm_i32x4_add(p0, p1), wasm_i32x4_splat(d0)), - wasm_i32x4_mul(wasm_i32x4_add(p2, p3), wasm_i32x4_splat(d1)) + wasm_i32x4_mul(p_sum0, wasm_i32x4_splat(d0)), + wasm_i32x4_mul(p_sum1, wasm_i32x4_splat(d1)) ); isum_vec = wasm_i32x4_add(isum_vec, scaled); @@ -817,7 +887,84 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi const int nb = n / QK_K; -#if defined __wasm_simd128__ +#if defined(__wasm_relaxed_simd__) + // Unsigned 3-bit quants (0..7) in the relaxed dot's 7-bit operand, q8 in + // the other; the -4 offset is taken off with the q8 block sums. + const v128_t m3 = wasm_i8x16_splat(0x03); + const v128_t m1 = wasm_i8x16_splat(0x01); + const v128_t zero = wasm_i32x4_splat(0); + uint32_t auxs[4]; + + float sumf = 0; + + for (int i = 0; i < nb; ++i) { + const float d = GGML_CPU_FP16_TO_FP32(x[i].d) * y[i].d; + + const uint8_t * GGML_RESTRICT q3 = x[i].qs; + const int8_t * GGML_RESTRICT q8 = y[i].qs; + + // Extract scales + memcpy(auxs, x[i].scales, 12); + uint32_t tmp = auxs[2]; + auxs[2] = ((auxs[0] >> 4) & kmask2) | (((tmp >> 4) & kmask1) << 4); + auxs[3] = ((auxs[1] >> 4) & kmask2) | (((tmp >> 6) & kmask1) << 4); + auxs[0] = (auxs[0] & kmask2) | (((tmp >> 0) & kmask1) << 4); + auxs[1] = (auxs[1] & kmask2) | (((tmp >> 2) & kmask1) << 4); + + const v128_t vsc = wasm_i8x16_sub(wasm_v128_load(auxs), wasm_i8x16_splat(32)); + const v128_t vsc_l = wasm_i16x8_extend_low_i8x16(vsc); + const v128_t vsc_h = wasm_i16x8_extend_high_i8x16(vsc); + + // sum(scale * bsum), for the -4 offset + const v128_t vmins = wasm_i32x4_add( + wasm_i32x4_dot_i16x8(wasm_v128_load(y[i].bsums), vsc_l), + wasm_i32x4_dot_i16x8(wasm_v128_load(y[i].bsums + 8), vsc_h)); + + const v128_t hm0 = wasm_v128_load(x[i].hmask); + const v128_t hm1 = wasm_v128_load(x[i].hmask + 16); + + v128_t acc = zero; + v128_t acc2 = zero; + + for (int j = 0; j < QK_K/128; ++j) { + const v128_t q3_0 = wasm_v128_load(q3); + const v128_t q3_1 = wasm_v128_load(q3 + 16); + q3 += 32; + + const v128_t s32a = wasm_i32x4_extend_low_i16x8(j == 0 ? vsc_l : vsc_h); + const v128_t s32b = wasm_i32x4_extend_high_i16x8(j == 0 ? vsc_l : vsc_h); + const v128_t s32[2] = { s32a, s32b }; + + for (int g = 0; g < 4; ++g) { + // 2 low bits at shift 2g, high bit 4j+g of hmask moved to bit 2 + // (16-bit shifts are safe on masked bytes) + const int hb = 4*j + g; + const v128_t u0 = wasm_v128_or(wasm_v128_and(wasm_u16x8_shr(q3_0, 2*g), m3), + wasm_i16x8_shl(wasm_v128_and(wasm_u16x8_shr(hm0, hb), m1), 2)); + const v128_t u1 = wasm_v128_or(wasm_v128_and(wasm_u16x8_shr(q3_1, 2*g), m3), + wasm_i16x8_shl(wasm_v128_and(wasm_u16x8_shr(hm1, hb), m1), 2)); + + const v128_t p0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8), u0, zero); + const v128_t p1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 16), u1, zero); + q8 += 32; + + const v128_t sv = s32[g >> 1]; + const v128_t sc0 = (g & 1) ? wasm_i32x4_shuffle(sv, sv, 2, 2, 2, 2) : wasm_i32x4_shuffle(sv, sv, 0, 0, 0, 0); + const v128_t sc1 = (g & 1) ? wasm_i32x4_shuffle(sv, sv, 3, 3, 3, 3) : wasm_i32x4_shuffle(sv, sv, 1, 1, 1, 1); + acc = wasm_i32x4_add(acc, wasm_i32x4_mul(p0, sc0)); + acc2 = wasm_i32x4_add(acc2, wasm_i32x4_mul(p1, sc1)); + } + } + + acc = wasm_i32x4_sub(wasm_i32x4_add(acc, acc2), wasm_i32x4_shl(vmins, 2)); + const int32_t isum = wasm_i32x4_extract_lane(acc, 0) + wasm_i32x4_extract_lane(acc, 1) + + wasm_i32x4_extract_lane(acc, 2) + wasm_i32x4_extract_lane(acc, 3); + sumf += d * isum; + } + + *s = sumf; + +#elif defined __wasm_simd128__ int8_t aux8[QK_K]; float sums[8] = {0}; uint32_t auxs[4]; @@ -986,6 +1133,14 @@ void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi q8 += 64; // Low nibble products +# if defined(__wasm_relaxed_simd__) + v128_t vacc1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add( + q8x0, q4l0, wasm_i32x4_splat(0) + ); + vacc1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add( + q8x1, q4l1, vacc1 + ); +# else v128_t vacc1 = wasm_i32x4_dot_i16x8( wasm_i16x8_extend_low_i8x16(q4l0), wasm_i16x8_extend_low_i8x16(q8x0) @@ -1002,8 +1157,17 @@ void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i16x8_extend_high_i8x16(q4l1), wasm_i16x8_extend_high_i8x16(q8x1) )); +# endif // High nibble products +# if defined(__wasm_relaxed_simd__) + v128_t vacc2 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add( + q8x2, q4h0, wasm_i32x4_splat(0) + ); + vacc2 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add( + q8x3, q4h1, vacc2 + ); +# else v128_t vacc2 = wasm_i32x4_dot_i16x8( wasm_i16x8_extend_low_i8x16(q4h0), wasm_i16x8_extend_low_i8x16(q8x2) @@ -1020,6 +1184,7 @@ void ggml_vec_dot_q4_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i16x8_extend_high_i8x16(q4h1), wasm_i16x8_extend_high_i8x16(q8x3) )); +# endif // Accumulate scaled results int32_t vacc1_sum = wasm_i32x4_extract_lane(vacc1, 0) + wasm_i32x4_extract_lane(vacc1, 1) + @@ -1127,6 +1292,11 @@ void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi v128_t q8_3 = wasm_v128_load(q8 + 48); q8 += 64; +# if defined(__wasm_relaxed_simd__) + // Process low quants using relaxed SIMD + v128_t sum_low = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(q8_0, q5l_0, wasm_i32x4_splat(0)); + sum_low = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(q8_1, q5l_1, sum_low); +# else // Process low quants v128_t pl0 = wasm_i32x4_dot_i16x8( wasm_i16x8_extend_low_i8x16(q5l_0), @@ -1145,7 +1315,13 @@ void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i16x8_extend_high_i8x16(q8_1) )); v128_t sum_low = wasm_i32x4_add(pl0, pl1); +# endif +# if defined(__wasm_relaxed_simd__) + // Process high quants using relaxed SIMD + v128_t sum_high = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(q8_2, q5h_0, wasm_i32x4_splat(0)); + sum_high = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(q8_3, q5h_1, sum_high); +# else // Process high quants v128_t ph0 = wasm_i32x4_dot_i16x8( wasm_i16x8_extend_low_i8x16(q5h_0), @@ -1164,6 +1340,7 @@ void ggml_vec_dot_q5_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi wasm_i16x8_extend_high_i8x16(q8_3) )); v128_t sum_high = wasm_i32x4_add(ph0, ph1); +# endif // Accumulate with scale factors int32_t sl = wasm_i32x4_extract_lane(sum_low, 0) + wasm_i32x4_extract_lane(sum_low, 1) + @@ -1204,7 +1381,78 @@ void ggml_vec_dot_q6_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi const int nb = n / QK_K; -#if defined __wasm_simd128__ +#if defined(__wasm_relaxed_simd__) + const v128_t m4 = wasm_i8x16_splat(0x0F); + const v128_t m2 = wasm_i8x16_splat(0x03); + const v128_t zero = wasm_i32x4_splat(0); + + float sumf = 0; + + for (int i = 0; i < nb; ++i) { + const float d = GGML_CPU_FP16_TO_FP32(x[i].d) * y[i].d; + const uint8_t * GGML_RESTRICT ql = x[i].ql; + const uint8_t * GGML_RESTRICT qh = x[i].qh; + const int8_t * GGML_RESTRICT q8 = y[i].qs; + + const v128_t vsc = wasm_v128_load(x[i].scales); + const v128_t vsc_l = wasm_i16x8_extend_low_i8x16(vsc); + const v128_t vsc_h = wasm_i16x8_extend_high_i8x16(vsc); + const v128_t vmins = wasm_i32x4_add( + wasm_i32x4_dot_i16x8(wasm_v128_load(y[i].bsums), vsc_l), + wasm_i32x4_dot_i16x8(wasm_v128_load(y[i].bsums + 8), vsc_h)); + + v128_t acc = zero; + v128_t acc2 = zero; + for (int j = 0; j < QK_K/128; ++j) { + const v128_t ql0 = wasm_v128_load(ql); + const v128_t ql1 = wasm_v128_load(ql + 16); + const v128_t ql2 = wasm_v128_load(ql + 32); + const v128_t ql3 = wasm_v128_load(ql + 48); + const v128_t qh0 = wasm_v128_load(qh); + const v128_t qh1 = wasm_v128_load(qh + 16); + ql += 64; + qh += 32; + + const v128_t q6_0 = wasm_v128_or(wasm_v128_and(ql0, m4), wasm_i16x8_shl(wasm_v128_and(qh0, m2), 4)); + const v128_t q6_1 = wasm_v128_or(wasm_v128_and(ql1, m4), wasm_i16x8_shl(wasm_v128_and(qh1, m2), 4)); + const v128_t q6_2 = wasm_v128_or(wasm_v128_and(ql2, m4), wasm_i16x8_shl(wasm_v128_and(qh0, wasm_i8x16_splat(0x0C)), 2)); + const v128_t q6_3 = wasm_v128_or(wasm_v128_and(ql3, m4), wasm_i16x8_shl(wasm_v128_and(qh1, wasm_i8x16_splat(0x0C)), 2)); + const v128_t q6_4 = wasm_v128_or(wasm_v128_and(wasm_u16x8_shr(ql0, 4), m4), wasm_v128_and(qh0, wasm_i8x16_splat(0x30))); + const v128_t q6_5 = wasm_v128_or(wasm_v128_and(wasm_u16x8_shr(ql1, 4), m4), wasm_v128_and(qh1, wasm_i8x16_splat(0x30))); + const v128_t q6_6 = wasm_v128_or(wasm_v128_and(wasm_u16x8_shr(ql2, 4), m4), wasm_u16x8_shr(wasm_v128_and(qh0, wasm_i8x16_splat((int8_t)0xC0)), 2)); + const v128_t q6_7 = wasm_v128_or(wasm_v128_and(wasm_u16x8_shr(ql3, 4), m4), wasm_u16x8_shr(wasm_v128_and(qh1, wasm_i8x16_splat((int8_t)0xC0)), 2)); + + const v128_t p0 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 0), q6_0, zero); + const v128_t p1 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 16), q6_1, zero); + const v128_t p2 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 32), q6_2, zero); + const v128_t p3 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 48), q6_3, zero); + const v128_t p4 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 64), q6_4, zero); + const v128_t p5 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 80), q6_5, zero); + const v128_t p6 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 96), q6_6, zero); + const v128_t p7 = wasm_i32x4_relaxed_dot_i8x16_i7x16_add(wasm_v128_load(q8 + 112), q6_7, zero); + q8 += 128; + + const v128_t s32a = wasm_i32x4_extend_low_i16x8(j == 0 ? vsc_l : vsc_h); + const v128_t s32b = wasm_i32x4_extend_high_i16x8(j == 0 ? vsc_l : vsc_h); + acc = wasm_i32x4_add(acc, wasm_i32x4_mul(p0, wasm_i32x4_shuffle(s32a, s32a, 0, 0, 0, 0))); + acc2 = wasm_i32x4_add(acc2, wasm_i32x4_mul(p1, wasm_i32x4_shuffle(s32a, s32a, 1, 1, 1, 1))); + acc = wasm_i32x4_add(acc, wasm_i32x4_mul(p2, wasm_i32x4_shuffle(s32a, s32a, 2, 2, 2, 2))); + acc2 = wasm_i32x4_add(acc2, wasm_i32x4_mul(p3, wasm_i32x4_shuffle(s32a, s32a, 3, 3, 3, 3))); + acc = wasm_i32x4_add(acc, wasm_i32x4_mul(p4, wasm_i32x4_shuffle(s32b, s32b, 0, 0, 0, 0))); + acc2 = wasm_i32x4_add(acc2, wasm_i32x4_mul(p5, wasm_i32x4_shuffle(s32b, s32b, 1, 1, 1, 1))); + acc = wasm_i32x4_add(acc, wasm_i32x4_mul(p6, wasm_i32x4_shuffle(s32b, s32b, 2, 2, 2, 2))); + acc2 = wasm_i32x4_add(acc2, wasm_i32x4_mul(p7, wasm_i32x4_shuffle(s32b, s32b, 3, 3, 3, 3))); + } + + acc = wasm_i32x4_sub(wasm_i32x4_add(acc, acc2), wasm_i32x4_shl(vmins, 5)); + const int32_t isum = wasm_i32x4_extract_lane(acc, 0) + wasm_i32x4_extract_lane(acc, 1) + + wasm_i32x4_extract_lane(acc, 2) + wasm_i32x4_extract_lane(acc, 3); + sumf += d * isum; + } + + *s = sumf; + +#elif defined __wasm_simd128__ int8_t aux8[QK_K] __attribute__((aligned(16))); int32_t aux32[8] __attribute__((aligned(16))) = {0}; float sums[8] __attribute__((aligned(16))) = {0};