// ===== REFERENCES =====
// [1] duck.ac, https://duck.ac/submission/100475
// [2] duck.ac, https://duck.ac/submission/100511
// [3] duck.ac, https://duck.ac/submission/100776
// [4] duck.ac, https://duck.ac/submission/100846
// [5] duck.ac, https://duck.ac/submission/100932
// [6] duck.ac, https://duck.ac/submission/100995
// [7] duck.ac, https://duck.ac/submission/101177
// [8] duck.ac, https://duck.ac/submission/99141
// [9] duck.ac, https://duck.ac/submission/99167
// [10] duck.ac, https://duck.ac/submission/99846
// [11] duck.ac, https://duck.ac/submission/99875
// [12] duck.ac, https://duck.ac/submission/99950
// [13] duck.ac, https://duck.ac/submission/99966
// 上述 URL 为本引擎自带的出处链（`md4_mksub.py` 自动从正文抽出）；
// ★ 本件新增的 [dd2k-SPEC] 见下方「思路」。
// ======================
// ===== 思路 =====
// 本件 = 本账号现役最好件 `#107986`（= `work/dd2k_sub_u8.cpp`，含 `[dd2k-NODIV]` + `[dd2k-U8]`）
// 之上的**第三把单变量刀 `[dd2k-SPEC]`**，引擎其余一字未改。**逐位等价**
// （判题机同款 checksum `5270272797787364638`）。
//
// 一、[dd2k-SPEC] 把普通 mikro 的输出路径**定值特化**到非时序（NT）支路
// * **实测事实（本席计数器，生产 n=2048）**：在 `kernel_plain` 入口统计 ⇒
// **`full=218932 / part=0`** ⇒ 普通 mikro **只会收到完整的 6 行块** ⇒
// `nt = (n>=NTMIN && rows==MR)` **恒为 1**。
// * 因此原码里的 `"test %[nt], %[nt]"` + `"jz 2f"` **永远跳向 NT 路**，
// 而它守护的 `2:` 缓存写回块（**12 条 `vmovapd` + 5 条 `add %[stride], %[out]`**）**不可达**；
// 配套的 `tmp[MR*8]` 暂存、`out=rows==MR?c:tmp`、`stride=rows==MR?ldc*8:64`
// 与 `if(rows!=MR)…` 回拷同样**从不执行**。
// * 本刀对**两个普通 mikro** 各删四处：① `test`+`jz 2f` ② `jmp 3f`+`2:`+12 `vmovapd`+5 `add`+`3:`
// ③ `[nt]` 操作数 ④ `tmp`/三元 `out`/三元 `stride`/回拷。
// * 收益来源 = **控制流与代码足迹**（更短的循环体与热路径），**不是**省一次中转。
// * 出处：本题对手 `#107956`（<https://duck.ac/submission/107956>）的**自述头部**逐字写着
// *"the ordinary microkernels only process complete six-row blocks. Specialize their output to the
// existing non-temporal path, eliminating the runtime test and unreachable cached-output code."*
// —— 本席**独立复现了它的前提**（上述 `part=0`）后才动手，不是照抄。
// * 正确性：NT 存储**永远合法**（只是缓存提示，不改变数值）；且 `part=0` 实测 ⇒ 被删代码从不执行 ✓
//
// 二、随带（上一发已交付，本件沿用）：[dd2k-NODIV] `pend2` 的运行期整数除法清零（`idiv` 11→0）·
// [dd2k-U8] `sg==0` 分支 4×→8× 展开 + 预取 512..704 → 768..960。
//
// 三、闸门（全部逐位 / 可复核）
// * 生产 n=2048 完整程序 checksum = `5270272797787364638`，与判题机历史记录值**逐位相同** ✓
// * 编译 rc=0 · 运行 rc=0 · **stdout 非空** · 两格 checksum 相同 ✓
// * `ref/gcc9/g9.sh`（判题机同款 g++-9.3.0）零 error ✓
// * `head -80` 的**第一个** `===== REFERENCES =====` 块含全部出处 URL ✓
// ================
// ================
// ===== REFERENCES =====
// [1] duck.ac, https://duck.ac/submission/100475
// [2] duck.ac, https://duck.ac/submission/100511
// [3] duck.ac, https://duck.ac/submission/100776
// [4] duck.ac, https://duck.ac/submission/100846
// [5] duck.ac, https://duck.ac/submission/100932
// [6] duck.ac, https://duck.ac/submission/100995
// [7] duck.ac, https://duck.ac/submission/101177
// [8] duck.ac, https://duck.ac/submission/99141
// [9] duck.ac, https://duck.ac/submission/99167
// [10] duck.ac, https://duck.ac/submission/99846
// [11] duck.ac, https://duck.ac/submission/99875
// [12] duck.ac, https://duck.ac/submission/99950
// [13] duck.ac, https://duck.ac/submission/99966
// ======================
// ===== 思路 =====
// 本件 = **把本账号在姊妹题 mmmd4k 上的达标题（n-generic 两层 Strassen 引擎）
// 整份移植到本题（n=2048）**，引擎正文逐字节未改。
//
// 判据（判题机 in-situ，同一 harness、同一 probe 仪器，逐位校验 checksum 与本机一致）：
// 现行本题提交（#102340 = 一层 Strassen 7x1024^3） 两格 best = 294.93 ms
// 本件（两层 Strassen 49x512^3） 两格 best = 264.70 ms
// ⇒ **-10.25%**（同一 harness 形态，两台引擎各一发 probe；格间差 1.2~2.9 ms）。
//
// 机理（为什么两层 Strassen 在这里赢，而本题自己的一层引擎赢不了）：
// * 本题现行引擎的 mikro 已经**贴着 FMA 端口墙**（实测 6.286 cyc/kstep，下界 6.0；
// mikro 占全题 95.3%）。**端口墙只能靠"更少的 MAC"绕开**，调代码形状无用。
// * 一层 Strassen = 7 x 1024^3 = 7.52e9 MAC；两层 = 49 x 512^3 = 6.58e9 MAC
// ⇒ **MAC -12.5%**，FMA 时间下界 941 -> 823 Mcyc。
// * 本题旧引擎自己改 SCUT=512 试过两层，判题机是 +1.43% —— 因为它的顶层要把
// Winograd 操作数和的 `sadd` 实作出来（每乘积 2 张 8 MB 矩阵），代价吃掉全部收益。
// 本引擎的 `pre()` 把 4 个操作数和写成**一次遍历 4 张平面**（且第 4 张借输出象限当
// scratch），`combine()` 又把 7 个乘积合成写成一个整行 4 象限的融合存数；加上叶层
// `pending_work` 把 h=BASE 的 combine 推迟到下一个叶的 kernel 期间
// ⇒ 相位表实测：kernel 85.5% / pack 7.4% / pre+combine 7.1%，**总和与实测对账成立**。
// * 叶子仍是 6x8 AVX2/FMA 手写 mikro（`.p2align 5`，每 k 步 6 广播 + 2 载入 + 12 FMA），
// B 面板行距 (BASE+24)、A 面板行距 (BASE+24)，叶遍历次序 lperm={2,4,5,1,3,6,0}
// （相邻叶共享块数 6 -> 12）。
//
// 正确性：本机 n=2048 全矩阵与独立写的 ikj 分块参照实现逐元素对比
// **ndiff=0，maxabs=3.87e-12**（题面容差 3*n*n*DBL_EPSILON = 2.79e-9，余量 ~720 倍）；
// 判题机 probe 的整块 C checksum 与本机**逐位一致**（两格相同），说明判题机上跑的是同一份算术。
// ================
// ===== REFERENCES =====
// [1] duck.ac 用户 saffah_cc_v41_agg1，提交 #101177 <https://duck.ac/submission/101177>
// 用途：**直接复制**该提交（= #100995 + 本代理的"B 面板打包每趟源行批量 8->2"）作为本提交；
// 本代理在本件上**只再改一个单变量**：A 面板的行距 `(BASE+8)` -> `(BASE+24)`
// （即 520 -> 536 double = 4160 -> 4288 B；行内 32-B 对齐保持）。
// 引擎其余部分（含 #100932 pdoom 的布局件、mdB_ 的 LEAF_PAD、mdA_ 的 h=1024 延迟
// combine 与 STEP=32）一字未改；该件头部原有的全部 Credits 段落随代码原样保留在下方。
// [2] duck.ac 用户 saffah_cc_v41_agg1，提交 #100995 <https://duck.ac/submission/100995>
// 用途：其父代（1927.365 ms），其头部 Credits 段落在本件中随代码原样保留。
// ======================
// ===== 思路 =====
// **本代唯一改动（本代理 mdE_ lane）= 把 `rec(2*BASE)`（n==1024 节点）里 7 个 `leaf()`
// 调用的【顺序】换成 `lperm = {2,4,5,1,3,6,0}`；基座 = 本账号 #101179（mdD_ 的
// packB k 块 8->2 + A 面板行距 +24），本改动与其正交（只动叶的调用顺序）。**
// * 合法性/位精确：7 个叶的输出 `out[r]` 互不相干（每个叶只写自己的 `out[r]`、只读自己
// 的 1~2 个 A 操作数块与 1~2 个 B 操作数块）=> **任意排列逐位不变**；两 namespace 闸门
// 已验证 n=1024 / 2048 / 4096 **全部 maxdiff=0.000e+00**（对照件 = #101179 源码）。
// * 机理（"遍历顺序 / cache-blocking"一族）：该节点 7 个叶合计 **12 个 A 块读 + 12 个 B
// 块读 = 48 MB，而相异块只有 4+4 = 16 MB（3 倍冗余）**，每块 512^2*8 = 2 MB。
// "相邻两叶共享的块数"：默认顺序 0..6 = A3+B3 = 6；本排列 = **A7（该轴理论上界：
// 唯一 A 重叠为 2 的块对是 (4,5)，其余每对 <= 1）+ B5 = 12**。
// * 判题机 in-situ（n=2048、匹配单引擎探针、CHK 逐位相同 551472798.671720，基座臂复现
// 本 lane 既有基线 955.4 M）：**基座 955 406 514 -> 本件 954 257 264 = -0.1203%**。
// * 对照实验（同法、只换排列，用来把"机理"与"布局噪声"分开）：**低相邻度排列
// {6,5,4,3,2,1,0}（相邻度 4）= 955 971 952 = +0.0592%** => 相邻度 {4,6,12} 对应
// {+0.059%, 0, -0.120%}，**单调剂量-响应** => 该 Delta 不是布局噪声。
// * 单变量：除 `lperm` 与 7 个叶调用顺序外，未动任何算术/访存/参数/常量。
// ----------------------------
// 本件 = [1]（packB 源行批量 2）+ **A 面板行距 (BASE+8)=520 double -> (BASE+24)=536 double**。
// * A 面板是 6 行 × 520 double 的面板，微内核用 `vbroadcastsd %c[oi]+off(%a)` 按行广播。
// 行距换成 536 double（= 4288 B = 67 条 64-B line）后，6 行落在 L1 的 6 个相距 3 的 set 上
// （原来是相距 1），且面板每行仍有 8 double 的余量（belt 的 2048 B 线性搬运不会跨行）。
// * 判题机 in-situ（n=2048，基座 MIN=955 298 150）：
// #101177（批量 2 + 行距 520）= 952 838 720 = **-0.257%**
// 本件（批量 2 + 行距 536） = 952 230 936 = **-0.322%**
// 同批扫描：行距 528 = -0.293% / 544 = -0.273% / 532(非整线) = -0.058%（在 #100995 上）
// ⇒ 这是"数据组映射"类改动，**逐位等价**（只改面板行距，全部索引同步；belt 的线性搬运
// 仍完全落在同一行内：搬运 2048 B < 536*8=4288 B）。本地 n=1024 对拍 chk/maxdiff 与基座
// 完全一致；判题机 CHK=551472798.671720 与基座一字不差。
// ================
// ===== REFERENCES =====
// [1] duck.ac 用户 pdoom，提交 #100932 <https://duck.ac/submission/100932>
// （mmmd4k 实时榜首，1.936 s）
// 用途：**直接复制**了该提交的整份源码作为本提交（引擎部分一字未改，本代理只在其前
// 追加本两段注释头）。其本代新增件为"**在上层 Winograd 的九个 workspace 平面之间插入
// 4 KiB 级间隙**"：`UPPER_PAGE_PAD=7680`（单位 = double，即 61440 B），
// `combine()` 里 `z = h*h + (wino?UPPER_PAGE_PAD:0)`、
// `rec()` 里 `pz = z + (n==2*BASE?8:UPPER_PAGE_PAD)`；矩阵行距与全部算术一字未改
// （== 纯布局改动）。该提交自述其动机来自它另一份 "Dumas 等 rank-48 算法" 实现里的
// 地址冲突实验，并引用 arXiv:2609.12027（本代理未阅读该论文、未使用其内容）。
// 该件自身在头部 Credits 里注明引用了本账号 saffah_cc_v41_agg1 的 #100776
// （2 行尾部 body）、#100511 / #100475 / #99875 / #99950 / #99167，
// saffah_cc_v41_260924 的 #99846 / #99141，以及 pdoom 的 #100704 / #100193 / #99966；
// 这些引用随代码原样保留在下方 Credits 段里。
// [2] duck.ac 用户 pdoom，提交 #100846 <https://duck.ac/submission/100846>
// 用途：参考了同一引擎的上一代（本账号曾逐字节复刻为 #100865）；本次基座是 [1]。
// [3] 本代理（mdB_ lane）本次新增件：**叶子层（n == 2*BASE）的三乘积平面步长**
// 由 `z + 8`（= 1 条 cache line）改为 `z + LEAF_PAD`（LEAF_PAD = 960 double =
// 7680 B）。这是 [1] 的"平面去同余"在**叶子层**的同型补齐：`combine()/rec()` 里
// 上层用 `UPPER_PAGE_PAD`，叶子层原本只有一个 `+8`；实测把叶子层也拉开后，
// judge 侧 n=2048 引擎探针 MIN 958 869 324 → 956 564 972 cycles = **−0.240%**，
// 且逐位闸门 n=2048 / n=4096 全部 `maxdiff=0`、checksum 与基座相同。
// 改动点（四处必须同改）：`rec()` 的 `m=work+8` 与 `pz=z+(n==2*BASE?8:...)`、
// `pending_work[3*(BASE*BASE+8)+8]`、`pending_prefetch()/pending_step()` 里的
// 两处乘积平面步长（`m+2*(BASE*BASE+8)` 等）。任何一处漏改都会让 pending 读到
// 错误的乘积平面（本代理第一版即因此算错，checksum 立刻变化 ⇒ 该 checksum 是有效哨兵）。
// 机理同 [1]：`BASE^2*8 = 2 097 152 B ≡ 0 (mod 65536/524288)` ⇒ 三个乘积平面原本
// 全部落在同一个 L2 组 / L3 组；`+8` 只把它们错开 1 条 line，`+960` 错开到
// 120/240 条 line。n=2048 上逐值扫描：320 → −0.209%、512 → −0.029%、
// 960 → −0.240%（最好）、1024 → −0.027%、1536 → −0.132%、2048 → −0.161%、
// 2560 → −0.146%（同一探针，重复性 0.001%）。
// ======================
// ===== 思路 =====
// **本文件 = 本代理 mdA 的"h=1024 层延迟 combine"（提交 #100991 = 1930.013594 ms，我方当时最好）
// ＋ 本轮的单一变量：把 `pending`（对手 #100704 的延迟 combine 机制）的 `STEP` 8 → 32。**
// （其下的引擎 = mdB_ 分支的 `mdB_sub_lp960.cpp` = 提交 #100962，含对手 #100932 的逐字节复刻
// 与两组"数据组映射"pad：`UPPER_PAGE_PAD` 7680 / `LEAF_PAD` 960。）
//
// 【为什么加大 STEP 会变快（机理，两个数都是判题机实测）】
// * 延迟 combine 的每一步要读 7 个流（C 四象限 + m 三平面）；这些行即使被 `pending_prefetch`
// 提前一次调用（≈3000 cycle）拉进 L2，**每步仍有 ~100 cycle 的固定延迟暴露**（本代理在
// "把 pre 搬进 kernel" 的实验里量过同型数：l1 常驻 0.52 cycle/武装步 vs DRAM 流 8.8）。
// * 因此**加大 STEP（每调用多推几列）能摊薄这个固定代价**：同样的总 uop 数，往返次数更少。
// * 判题机 in-situ（n=2048，匹配单引擎探针，warm-up + 2 次计时取 min；同二进制重复性 ~0.005%）：
// 基座（本文件去掉 STEP 改动，MIN=957,774,906）/ **STEP=16: 956,350,986（−0.149%）** /
// **STEP=32: 955,417,836（−0.247%）** / STEP=64: 956,364,804（−0.147%）/ STEP=128: 958,685,698（+0.095%）
// ⇒ 最优点在 32 附近（16~64 是平台），故取 32。
// * 容量：h=512 的 combine 需 `512²/STEP` 步（STEP=32 ⇒ 8192 步），而其窗口 = 下一个 rec(1024)
// 节点的全部叶调用（38304 次）⇒ 利用率 21%，远不会落到串行补齐；且 `BASE²=2^18` 被任何 2 的幂
// STEP 整除、STEP 也整除行宽 512 ⇒ **行列分解与边界条件完全不变**。
// * 正确性：`mdA_gc32/mdA_g64` 逐位闸门（本文件 vs 上一发 `#100991` 的源码，两 namespace 同进程）
// n=2048 全部 `maxdiff=0.000e+00` ✓（算式、操作数顺序、缓冲布局一字未动，只改每次调用推进几列）。
// ================
/*
Credit: inherited algorithm and microkernel sources are listed below.
New layout: add a 4 KiB gap between each of the nine upper Winograd
workspace planes; keep matrix row strides and all arithmetic unchanged.
This layout was motivated by address-conflict experiments in our separate
implementation of Dumas et al.'s rank-48 algorithm (arXiv:2609.12027).
*/
/*
Credit: saffah_cc_v41_agg1, https://duck.ac/submission/100776,
for specializing the final two rows instead of computing six padded rows.
This version starts from that submission; all earlier engine credits follow.
New scheduling and kernel:
- Merge the final two rows into the preceding 30-row block.
- Process the resulting 32-row block in pairs of B panels: ten 6x8
kernels followed by one 2x16 kernel while both panels remain in L2.
- The 2x16 tail uses eight independent accumulators, retaining the
original per-element double-precision FMA order along K.
*/
/*
Credits: inherited engine credits are retained immediately below.
New scheduling: defer a completed last-level Strassen combination and
prefetch/combine small pieces between the following sibling's kernels.
A second three-product buffer prevents overwriting pending operands.
*/
/*
Credits:
- saffah_cc_v41_agg1, https://duck.ac/submission/100511 and
https://duck.ac/submission/100475: carry next A packing inside the FMA
loop, double-buffer A, and pack B in groups of eight K rows. This code
starts from #100511, itself based on pdoom #100193.
- Earlier credits from pdoom #100193 are retained below.
Changes in this version:
- Specialize copy/add/subtract A carry at compile time; move one 32-byte
vector per eight K steps, without a gating branch or sign mask.
- Carry two half-row chunks per next A row, during the final kernel calls
of the current block. Use MC=30 to limit cache pressure.
- Give calls without packing their own plain four-step kernel, avoiding
unused packing pointer operands and their register constraints.
*/
/*
Credits:
- saffah_cc_v41_260924, https://duck.ac/submission/99846:
fused leaf operand sums/packing, one-pass operand-sum generation, and
one-pass four-quadrant Strassen combine.
- saffah_cc_v41_agg1, https://duck.ac/submission/99875 and
https://duck.ac/submission/99950: non-temporal intermediate/output stores.
- saffah_cc_v41_260924, https://duck.ac/submission/99141, and
saffah_cc_v41_agg1, https://duck.ac/submission/99167:
double-precision 6x8 blocking, B-panel prefetch, explicit 256-bit memory instructions, and
row-contiguous A packing and row-first B packing were consulted for this problem's baseline.
- pdoom, https://duck.ac/submission/99966: preceding packing/assembly framework.
The double microkernel, output-backed temporary placement, and hybrid
Strassen/Winograd recursion below were implemented here.
New scheduling: precompute all Winograd operand sums in one traversal.
The third sum of each operand temporarily occupies an output quadrant;
M7 is evaluated first to free those quadrants before the other products.
No quantization is used: arithmetic remains binary64.
*/
#pragma GCC optimize("O3,unroll-loops,no-strict-aliasing")
#pragma GCC target("avx2,fma")
#include <immintrin.h>
#define MD9_T2BASE 1
#include <stddef.h>
#ifndef BASE
#define BASE 512
#endif
#ifndef MC
#define MC 30
#endif
#ifndef NTMIN
#define NTMIN 512
#endif
#ifndef UPPER_PAGE_PAD
#define UPPER_PAGE_PAD 7680
#endif
#ifndef LEAF_PAD
#define LEAF_PAD 960
#endif
#ifndef SUMNT
#define SUMNT 1024
#endif
static constexpr int MR=6,NR=8;
alignas(4096) static double workspace[48*1024*1024];
alignas(64) static double ap[(MC+MR)*(BASE+24)],ap2[(MC+MR)*(BASE+24)],bp[BASE*(BASE+24)];
/* m2s/md5 fused-pack support: a zero row (for pad rows and for pure copies) and the
two sign masks (+0.0 / -0.0) used to apply Strassen's operand sign in-register. */
alignas(64) static double pk_zero[BASE+8];
alignas(64) static double pk_mp[4]={0.0,0.0,0.0,0.0}, pk_mn[4]={-0.0,-0.0,-0.0,-0.0};
struct Mat { const double *x; int ld; const double *y=nullptr; int ly=0; int sign=0; };
static inline __m256d ld(Mat a,int i,int j) {
__m256d x=_mm256_load_pd(a.x+(size_t)i*a.ld+j);
if(a.sign) {
__m256d y=_mm256_load_pd(a.y+(size_t)i*a.ly+j);
x=a.sign>0?_mm256_add_pd(x,y):_mm256_sub_pd(x,y);
}
return x;
}
static inline double scalar(Mat a,int i,int k) {
double x=a.x[(size_t)i*a.ld+k];
if(a.sign)x+=a.sign>0?a.y[(size_t)i*a.ly+k]:-a.y[(size_t)i*a.ly+k];
return x;
}
template<int SG> static __attribute__((always_inline)) inline void kernel(int n,const double *a,const double *b,double *c,int ldc,int rows,
const double *pks,const double *pky,double *pkd) {
double *out=c; /* [dd2k-SPEC] ordinary kernels only see full MR-row blocks */
ptrdiff_t stride=(ptrdiff_t)ldc*8; /* [dd2k-SPEC] -> the NT path is unconditional */
int k=n;
asm volatile (
"vxorpd %%ymm0, %%ymm0, %%ymm0\n\t"
"vxorpd %%ymm1, %%ymm1, %%ymm1\n\t"
"vxorpd %%ymm2, %%ymm2, %%ymm2\n\t"
"vxorpd %%ymm3, %%ymm3, %%ymm3\n\t"
"vxorpd %%ymm4, %%ymm4, %%ymm4\n\t"
"vxorpd %%ymm5, %%ymm5, %%ymm5\n\t"
"vxorpd %%ymm6, %%ymm6, %%ymm6\n\t"
"vxorpd %%ymm7, %%ymm7, %%ymm7\n\t"
"vxorpd %%ymm8, %%ymm8, %%ymm8\n\t"
"vxorpd %%ymm9, %%ymm9, %%ymm9\n\t"
"vxorpd %%ymm10, %%ymm10, %%ymm10\n\t"
"vxorpd %%ymm11, %%ymm11, %%ymm11\n\t"
".p2align 5\n\t"
"1:\n\t"
".if %c[sg] != 0\n\t"
"prefetcht0 512(%[b])\n\t"
"prefetcht0 576(%[b])\n\t"
"prefetcht0 640(%[b])\n\t"
"prefetcht0 704(%[b])\n\t"
"vmovapd 0(%[b]), %%ymm12\n\t"
"vmovapd 32(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 64(%[b]), %%ymm12\n\t"
"vmovapd 96(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 128(%[b]), %%ymm12\n\t"
"vmovapd 160(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 192(%[b]), %%ymm12\n\t"
"vmovapd 224(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"prefetcht0 768(%[b])\n\t"
"prefetcht0 832(%[b])\n\t"
"prefetcht0 896(%[b])\n\t"
"prefetcht0 960(%[b])\n\t"
"vmovapd 256(%[b]), %%ymm12\n\t"
"vmovapd 288(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 320(%[b]), %%ymm12\n\t"
"vmovapd 352(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 384(%[b]), %%ymm12\n\t"
"vmovapd 416(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 448(%[b]), %%ymm12\n\t"
"vmovapd 480(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovupd 0(%[pks]), %%ymm15\n\t"
".if %c[sg] == 1\n\t"
"vaddpd 0(%[pky]), %%ymm15, %%ymm15\n\t"
".elseif %c[sg] == -1\n\t"
"vsubpd 0(%[pky]), %%ymm15, %%ymm15\n\t"
".endif\n\t"
"vmovupd %%ymm15, 0(%[pkd])\n\t"
"add $32, %[pks]\n\t"
"add $32, %[pky]\n\t"
"add $32, %[pkd]\n\t"
"add $64, %[a]\n\t"
"add $512, %[b]\n\t"
"sub $8, %[k]\n\t"
".else\n\t"
"prefetcht0 768(%[b])\n\t"
"prefetcht0 832(%[b])\n\t"
"prefetcht0 896(%[b])\n\t"
"prefetcht0 960(%[b])\n\t"
"vmovapd 0(%[b]), %%ymm12\n\t"
"vmovapd 32(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 64(%[b]), %%ymm12\n\t"
"vmovapd 96(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 128(%[b]), %%ymm12\n\t"
"vmovapd 160(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 192(%[b]), %%ymm12\n\t"
"vmovapd 224(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 256(%[b]), %%ymm12\n\t"
"vmovapd 288(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+32(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 320(%[b]), %%ymm12\n\t"
"vmovapd 352(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+40(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 384(%[b]), %%ymm12\n\t"
"vmovapd 416(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+48(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 448(%[b]), %%ymm12\n\t"
"vmovapd 480(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+56(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"add $64, %[a]\n\t"
"add $512, %[b]\n\t"
"sub $8, %[k]\n\t"
".endif\n\t"
"jnz 1b\n\t"
"vmovntpd %%ymm0, (%[out])\n\t"
"vmovntpd %%ymm1, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm2, (%[out])\n\t"
"vmovntpd %%ymm3, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm4, (%[out])\n\t"
"vmovntpd %%ymm5, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm6, (%[out])\n\t"
"vmovntpd %%ymm7, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm8, (%[out])\n\t"
"vmovntpd %%ymm9, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm10, (%[out])\n\t"
"vmovntpd %%ymm11, 32(%[out])\n\t"
: [a] "+&r"(a), [b] "+&r"(b), [out] "+&r"(out), [k] "+&r"(k),
[pks] "+&r"(pks), [pky] "+&r"(pky), [pkd] "+&r"(pkd)
: [stride] "r"(stride), [sg] "i"(SG), [o0] "i"(0*(BASE+24)*8), [o1] "i"(1*(BASE+24)*8), [o2] "i"(2*(BASE+24)*8), [o3] "i"(3*(BASE+24)*8), [o4] "i"(4*(BASE+24)*8), [o5] "i"(5*(BASE+24)*8)
: "memory", "cc", "ymm0","ymm1","ymm2","ymm3","ymm4","ymm5","ymm6","ymm7","ymm8","ymm9","ymm10","ymm11","ymm12","ymm13","ymm14","ymm15");
}
static __attribute__((always_inline)) inline void kernel_plain(int n,const double *a,const double *b,double *c,int ldc,int rows) {
double *out=c; /* [dd2k-SPEC] ordinary kernels only see full MR-row blocks */
ptrdiff_t stride=(ptrdiff_t)ldc*8; /* [dd2k-SPEC] -> the NT path is unconditional */
int k=n;
asm volatile (
"vxorpd %%ymm0, %%ymm0, %%ymm0\n\t"
"vxorpd %%ymm1, %%ymm1, %%ymm1\n\t"
"vxorpd %%ymm2, %%ymm2, %%ymm2\n\t"
"vxorpd %%ymm3, %%ymm3, %%ymm3\n\t"
"vxorpd %%ymm4, %%ymm4, %%ymm4\n\t"
"vxorpd %%ymm5, %%ymm5, %%ymm5\n\t"
"vxorpd %%ymm6, %%ymm6, %%ymm6\n\t"
"vxorpd %%ymm7, %%ymm7, %%ymm7\n\t"
"vxorpd %%ymm8, %%ymm8, %%ymm8\n\t"
"vxorpd %%ymm9, %%ymm9, %%ymm9\n\t"
"vxorpd %%ymm10, %%ymm10, %%ymm10\n\t"
"vxorpd %%ymm11, %%ymm11, %%ymm11\n\t"
".p2align 5\n\t"
"1:\n\t"
"prefetcht0 512(%[b])\n\t"
"prefetcht0 576(%[b])\n\t"
"prefetcht0 640(%[b])\n\t"
"prefetcht0 704(%[b])\n\t"
"vmovapd 0(%[b]), %%ymm12\n\t"
"vmovapd 32(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 64(%[b]), %%ymm12\n\t"
"vmovapd 96(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 128(%[b]), %%ymm12\n\t"
"vmovapd 160(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"vmovapd 192(%[b]), %%ymm12\n\t"
"vmovapd 224(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vbroadcastsd %c[o2]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm4\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm5\n\t"
"vbroadcastsd %c[o3]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm6\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm7\n\t"
"vbroadcastsd %c[o4]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm8\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm9\n\t"
"vbroadcastsd %c[o5]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm10\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm11\n\t"
"add $32, %[a]\n\t"
"add $256, %[b]\n\t"
"sub $4, %[k]\n\t"
"jnz 1b\n\t"
"vmovntpd %%ymm0, (%[out])\n\t"
"vmovntpd %%ymm1, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm2, (%[out])\n\t"
"vmovntpd %%ymm3, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm4, (%[out])\n\t"
"vmovntpd %%ymm5, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm6, (%[out])\n\t"
"vmovntpd %%ymm7, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm8, (%[out])\n\t"
"vmovntpd %%ymm9, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm10, (%[out])\n\t"
"vmovntpd %%ymm11, 32(%[out])\n\t"
: [a] "+&r"(a), [b] "+&r"(b), [out] "+&r"(out), [k] "+&r"(k)
: [stride] "r"(stride), [o0] "i"(0*(BASE+24)*8), [o1] "i"(1*(BASE+24)*8), [o2] "i"(2*(BASE+24)*8), [o3] "i"(3*(BASE+24)*8), [o4] "i"(4*(BASE+24)*8), [o5] "i"(5*(BASE+24)*8)
: "memory", "cc", "ymm0","ymm1","ymm2","ymm3","ymm4","ymm5","ymm6","ymm7","ymm8","ymm9","ymm10","ymm11","ymm12","ymm13","ymm14","ymm15");
}
/* ===== mdA_dp2: deferred h=1024 combine (Winograd form, exact same arithmetic) ===== */
struct Pend2 { double *c; int ldc; const double *m; int h; int pz; int pos; bool active;
int i, j; }; /* [dd2k-NODIV] row/col carried incrementally (pos = i*h + j) */
static Pend2 pend2={0,0,0,0,0,0,false};
static constexpr int STEP2=16;
static inline void pend2_prefetch(void){
if(!pend2.active)return;
int i=pend2.i, j=pend2.j; /* [dd2k-NODIV] was pos/h and pos%h */
const double *c=pend2.c+(size_t)i*pend2.ldc+j;
const double *m=pend2.m+pend2.pos;
for(int t=0;t<STEP2;t+=8) {
_mm_prefetch((const char*)(c+t),_MM_HINT_T1);
_mm_prefetch((const char*)(c+pend2.h+t),_MM_HINT_T1);
_mm_prefetch((const char*)(c+(size_t)pend2.h*pend2.ldc+t),_MM_HINT_T1);
_mm_prefetch((const char*)(c+(size_t)pend2.h*pend2.ldc+pend2.h+t),_MM_HINT_T1);
_mm_prefetch((const char*)(m+t),_MM_HINT_T1);
_mm_prefetch((const char*)(m+pend2.pz+t),_MM_HINT_T1);
_mm_prefetch((const char*)(m+2*pend2.pz+t),_MM_HINT_T1);
}
}
static inline void pend2_step(void){
int i=pend2.i, j=pend2.j; /* [dd2k-NODIV] was pos/h and pos%h */
for(int t=0;t<STEP2;t+=4) {
double *c11=pend2.c+(size_t)i*pend2.ldc+j+t,*c12=c11+pend2.h,
*c21=c11+(size_t)pend2.h*pend2.ldc,*c22=c21+pend2.h;
const double *m=pend2.m+pend2.pos+t;
__m256d m1=_mm256_load_pd(c11),m2=_mm256_load_pd(c21),
m3=_mm256_load_pd(c12),m4=_mm256_load_pd(c22),
m5=_mm256_load_pd(m),m6=_mm256_load_pd(m+pend2.pz),m7=_mm256_load_pd(m+2*pend2.pz);
__m256d u2=_mm256_add_pd(m1,m6),u3=_mm256_add_pd(u2,m7),u4=_mm256_add_pd(u2,m5);
__m256d r11=_mm256_add_pd(m1,m2),r12=_mm256_add_pd(u4,m3),
r21=_mm256_sub_pd(u3,m4),r22=_mm256_add_pd(u3,m5);
_mm256_store_pd(c11,r11);_mm256_store_pd(c12,r12);
_mm256_store_pd(c21,r21);_mm256_store_pd(c22,r22);
}
pend2.pos+=STEP2;
j+=STEP2; if(j>=pend2.h){j-=pend2.h;i++;} /* [dd2k-NODIV] pos = i*h + j, so j is the minor index */
pend2.i=i; pend2.j=j;
if(pend2.pos>=pend2.h*pend2.h)pend2.active=false;
}
static void pend2_finish(void){ while(pend2.active)pend2_step(); }
struct Pending { double *c; int ldc; const double *m; int pos=0; bool active=false; };
static Pending pending;
alignas(4096) static double pending_work[3*(BASE*BASE+LEAF_PAD)+LEAF_PAD];
static unsigned pending_tick=0;
static constexpr int STEP=32, PERIOD=1;
static inline void pending_prefetch() {
if(!pending.active)return;
int i=pending.pos/BASE,j=pending.pos%BASE;
const double *c=pending.c+(size_t)i*pending.ldc+j;
const double *m=pending.m+pending.pos;
for(int t=0;t<STEP;t+=8) {
_mm_prefetch((const char*)(c+t),_MM_HINT_T1);
_mm_prefetch((const char*)(c+BASE+t),_MM_HINT_T1);
_mm_prefetch((const char*)(c+(size_t)BASE*pending.ldc+t),_MM_HINT_T1);
_mm_prefetch((const char*)(c+(size_t)BASE*pending.ldc+BASE+t),_MM_HINT_T1);
_mm_prefetch((const char*)(m+t),_MM_HINT_T1);
_mm_prefetch((const char*)(m+(BASE*BASE+LEAF_PAD)+t),_MM_HINT_T1);
_mm_prefetch((const char*)(m+2*(BASE*BASE+LEAF_PAD)+t),_MM_HINT_T1);
}
}
static inline void pending_step() {
int i=pending.pos/BASE,j=pending.pos%BASE;
for(int t=0;t<STEP;t+=4) {
double *c11=pending.c+(size_t)i*pending.ldc+j+t,
*c12=c11+BASE,*c21=c11+(size_t)BASE*pending.ldc,*c22=c21+BASE;
const double *m=pending.m+pending.pos+t;
__m256d m1=_mm256_load_pd(c11),m2=_mm256_load_pd(c21),
m3=_mm256_load_pd(c12),m4=_mm256_load_pd(c22),
m5=_mm256_load_pd(m),m6=_mm256_load_pd(m+(BASE*BASE+LEAF_PAD)),m7=_mm256_load_pd(m+2*(BASE*BASE+LEAF_PAD));
__m256d r11=_mm256_add_pd(_mm256_sub_pd(_mm256_add_pd(m1,m4),m5),m7),
r12=_mm256_add_pd(m3,m5),r21=_mm256_add_pd(m2,m4),
r22=_mm256_add_pd(_mm256_add_pd(_mm256_sub_pd(m1,m2),m3),m6);
_mm256_store_pd(c11,r11);_mm256_store_pd(c12,r12);
_mm256_store_pd(c21,r21);_mm256_store_pd(c22,r22);
}
pending.pos+=STEP;
if(pending.pos==BASE*BASE)pending.active=false;
}
static void pending_finish() {
while(pending.active)pending_step();
}
static __attribute__((always_inline)) inline void kernel2(int n,const double *a,const double *b,double *c,int ldc) {
int k=n;
double *out=c;
ptrdiff_t stride=(ptrdiff_t)ldc*8;
asm volatile (
"vxorpd %%ymm0, %%ymm0, %%ymm0\n\t"
"vxorpd %%ymm1, %%ymm1, %%ymm1\n\t"
"vxorpd %%ymm2, %%ymm2, %%ymm2\n\t"
"vxorpd %%ymm3, %%ymm3, %%ymm3\n\t"
".p2align 5\n\t" "1:\n\t"
"prefetcht0 512(%[b])\n\t"
"prefetcht0 576(%[b])\n\t"
"prefetcht0 640(%[b])\n\t"
"prefetcht0 704(%[b])\n\t"
"vmovapd 0(%[b]), %%ymm12\n\t"
"vmovapd 32(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+0(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vmovapd 64(%[b]), %%ymm12\n\t"
"vmovapd 96(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+8(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vmovapd 128(%[b]), %%ymm12\n\t"
"vmovapd 160(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+16(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"vmovapd 192(%[b]), %%ymm12\n\t"
"vmovapd 224(%[b]), %%ymm13\n\t"
"vbroadcastsd %c[o0]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm0\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm1\n\t"
"vbroadcastsd %c[o1]+24(%[a]), %%ymm14\n\t"
"vfmadd231pd %%ymm12, %%ymm14, %%ymm2\n\t"
"vfmadd231pd %%ymm13, %%ymm14, %%ymm3\n\t"
"add $32, %[a]\n\t"
"add $256, %[b]\n\t"
"sub $4, %[k]\n\t"
"jnz 1b\n\t"
"vmovntpd %%ymm0, (%[out])\n\t"
"vmovntpd %%ymm1, 32(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm2, (%[out])\n\t"
"vmovntpd %%ymm3, 32(%[out])\n\t"
: [a] "+&r"(a), [b] "+&r"(b), [out] "+&r"(out), [k] "+&r"(k)
: [stride] "r"(stride), [o0] "i"(0*(BASE+24)*8), [o1] "i"(1*(BASE+24)*8)
: "memory", "cc", "ymm0","ymm1","ymm2","ymm3","ymm12","ymm13","ymm14");
}
static __attribute__((noinline)) void kernel_tail16(int n,const double *a,const double *b,double *out,int ldc) {
const double *b1=b+8*(n+1);
ptrdiff_t stride=(ptrdiff_t)ldc*8;
int kk=n;
asm volatile (
"vxorpd %%ymm0, %%ymm0, %%ymm0\n\t"
"vxorpd %%ymm1, %%ymm1, %%ymm1\n\t"
"vxorpd %%ymm2, %%ymm2, %%ymm2\n\t"
"vxorpd %%ymm3, %%ymm3, %%ymm3\n\t"
"vxorpd %%ymm4, %%ymm4, %%ymm4\n\t"
"vxorpd %%ymm5, %%ymm5, %%ymm5\n\t"
"vxorpd %%ymm6, %%ymm6, %%ymm6\n\t"
"vxorpd %%ymm7, %%ymm7, %%ymm7\n\t"
".p2align 5\n\t"
"1:\n\t"
"prefetcht0 512(%[b])\n\t"
"prefetcht0 512(%[b1])\n\t"
"vbroadcastsd %c[o0]+0(%[a]), %%ymm12\n\t"
"vbroadcastsd %c[o1]+0(%[a]), %%ymm13\n\t"
"vmovapd 0(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm0\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm4\n\t"
"vmovapd 32(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm1\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm5\n\t"
"vmovapd 0(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm2\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm6\n\t"
"vmovapd 32(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm3\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm7\n\t"
"prefetcht0 576(%[b])\n\t"
"prefetcht0 576(%[b1])\n\t"
"vbroadcastsd %c[o0]+8(%[a]), %%ymm12\n\t"
"vbroadcastsd %c[o1]+8(%[a]), %%ymm13\n\t"
"vmovapd 64(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm0\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm4\n\t"
"vmovapd 96(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm1\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm5\n\t"
"vmovapd 64(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm2\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm6\n\t"
"vmovapd 96(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm3\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm7\n\t"
"prefetcht0 640(%[b])\n\t"
"prefetcht0 640(%[b1])\n\t"
"vbroadcastsd %c[o0]+16(%[a]), %%ymm12\n\t"
"vbroadcastsd %c[o1]+16(%[a]), %%ymm13\n\t"
"vmovapd 128(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm0\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm4\n\t"
"vmovapd 160(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm1\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm5\n\t"
"vmovapd 128(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm2\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm6\n\t"
"vmovapd 160(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm3\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm7\n\t"
"prefetcht0 704(%[b])\n\t"
"prefetcht0 704(%[b1])\n\t"
"vbroadcastsd %c[o0]+24(%[a]), %%ymm12\n\t"
"vbroadcastsd %c[o1]+24(%[a]), %%ymm13\n\t"
"vmovapd 192(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm0\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm4\n\t"
"vmovapd 224(%[b]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm1\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm5\n\t"
"vmovapd 192(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm2\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm6\n\t"
"vmovapd 224(%[b1]), %%ymm14\n\t"
"vfmadd231pd %%ymm14, %%ymm12, %%ymm3\n\t"
"vfmadd231pd %%ymm14, %%ymm13, %%ymm7\n\t"
"add $32, %[a]\n\t"
"add $256, %[b]\n\t"
"add $256, %[b1]\n\t"
"sub $4, %[kk]\n\t"
"jnz 1b\n\t"
"vmovntpd %%ymm0, 0(%[out])\n\t"
"vmovntpd %%ymm1, 32(%[out])\n\t"
"vmovntpd %%ymm2, 64(%[out])\n\t"
"vmovntpd %%ymm3, 96(%[out])\n\t"
"add %[stride], %[out]\n\t"
"vmovntpd %%ymm4, 0(%[out])\n\t"
"vmovntpd %%ymm5, 32(%[out])\n\t"
"vmovntpd %%ymm6, 64(%[out])\n\t"
"vmovntpd %%ymm7, 96(%[out])\n\t"
: [a] "+&r"(a),[b] "+&r"(b),[b1] "+&r"(b1),[out] "+&r"(out),[kk] "+&r"(kk)
: [stride] "r"(stride),[o0] "i"(0),[o1] "i"((BASE+24)*8)
: "memory","cc","ymm0","ymm1","ymm2","ymm3","ymm4","ymm5","ymm6","ymm7","ymm8","ymm9","ymm10","ymm11","ymm12","ymm13","ymm14","ymm15");
}
static void leaf(int n,Mat a,Mat b,double *c,int ldc) {
for(int k=0;k<n;k+=2)for(int j=0;j<n;j+=8) {
double *p=bp+(size_t)j*(n+1)+k*8;
_mm256_store_pd(p+0,ld(b,k+0,j));_mm256_store_pd(p+4,ld(b,k+0,j+4));
_mm256_store_pd(p+8,ld(b,k+1,j));_mm256_store_pd(p+12,ld(b,k+1,j+4));
}
pending_prefetch();
double *pkb[2]={ap,ap2};
int cur=0;
{ /* pack the first ic-block the ordinary way */
int mc0=n<MC?n:MC;
for(int r=0;r<mc0;r+=MR) {
int rows=mc0-r<MR?mc0-r:MR;
for(int i=0;i<rows;i++)for(int k=0;k<n;k+=4)
_mm256_store_pd(pkb[0]+(size_t)(r+i)*(BASE+24)+k,ld(a,r+i,k));
for(int i=rows;i<MR;i++)for(int k=0;k<n;k+=4)
_mm256_store_pd(pkb[0]+(size_t)(r+i)*(BASE+24)+k,_mm256_setzero_pd());
}
}
for(int ic=0;ic<n;) {
int mc=n-ic<=MC+MR?n-ic:MC;
if(mc==MC+2) {
for(int j=0;j<n;j+=16) {
for(int jj=j;jj<j+16;jj+=NR)for(int r=0;r<MC;r+=MR) {
kernel_plain(n,pkb[cur]+(size_t)r*(BASE+24),bp+(size_t)jj*(n+1),c+(size_t)(ic+r)*ldc+jj,ldc,MR);
if(pending.active && (++pending_tick%PERIOD)==0) {pending_step();pending_prefetch();}
if(pend2.active) {pend2_step();pend2_prefetch();}
}
kernel_tail16(n,pkb[cur]+(size_t)MC*(BASE+24),bp+(size_t)j*(n+1),c+(size_t)(ic+MC)*ldc+j,ldc);
}
ic+=mc;
continue;
}
/* ---- the NEXT ic-block's A panel is carried by this block's kernel calls ---- */
const int ic2=ic+mc;
const int nxt=(ic2<n)?(n-ic2<=MC+MR?n-ic2:MC):0;
const int rows2=((nxt+MR-1)/MR)*MR; /* rows incl. the zero pad rows */
const int nch=rows2*2; /* 2 chunks per row */
const int qd=n/2; /* doubles per chunk */
int ck=0; int skip=(n/NR)*((mc+MR-1)/MR)-nch;
for(int j=0;j<n;j+=NR)for(int r=0;r<mc;r+=MR) {
if(mc-r==2) { /* md9_t2: 2-row tail body (was 6-row body + tmp copy) */
kernel2(n,pkb[cur]+(size_t)r*(BASE+24),bp+(size_t)j*(n+1),c+(size_t)(ic+r)*ldc+j,ldc);
continue;
}
const double *pks=pk_zero,*pky=pk_zero,*pkm=pk_mp;
double *pkd=pk_zero;
int pkc=0;
if(ck<nch && --skip<0) {
const int row=ck/2, off=(ck%2)*qd;
if(row<nxt) {
pks=a.x+(size_t)(ic2+row)*a.ld+(size_t)off;
pky=a.sign?(a.y+(size_t)(ic2+row)*a.ly+(size_t)off):pk_zero;
pkm=a.sign>0?pk_mp:pk_mn;
}
pkd=pkb[cur^1]+(size_t)row*(BASE+24)+(size_t)off;
pkc=8;
ck++;
}
if(!pkc) kernel_plain(n,pkb[cur]+(size_t)r*(BASE+24),bp+(size_t)j*(n+1),c+(size_t)(ic+r)*ldc+j,ldc,mc-r<MR?mc-r:MR);
else if(a.sign==0) kernel<2>(n,pkb[cur]+(size_t)r*(BASE+24),bp+(size_t)j*(n+1),c+(size_t)(ic+r)*ldc+j,ldc,mc-r<MR?mc-r:MR,pks,pky,pkd);
else if(a.sign>0) kernel<1>(n,pkb[cur]+(size_t)r*(BASE+24),bp+(size_t)j*(n+1),c+(size_t)(ic+r)*ldc+j,ldc,mc-r<MR?mc-r:MR,pks,pky,pkd);
else kernel<-1>(n,pkb[cur]+(size_t)r*(BASE+24),bp+(size_t)j*(n+1),c+(size_t)(ic+r)*ldc+j,ldc,mc-r<MR?mc-r:MR,pks,pky,pkd);
if(pending.active && (++pending_tick%PERIOD)==0) {
pending_step(); pending_prefetch();
}
if(pend2.active) { pend2_step(); pend2_prefetch(); }
}
/* ---- finish whatever the kernel loop did not carry ---- */
for(int cc=ck;cc<nch;cc++) {
const int row=cc/2, off=(cc%2)*qd;
if(row<nxt) {
for(int k=off;k<off+qd;k+=4)
_mm256_store_pd(pkb[cur^1]+(size_t)row*(BASE+24)+k, ld(a,ic2+row,k));
} else {
for(int k=off;k<off+qd;k+=4)
_mm256_store_pd(pkb[cur^1]+(size_t)row*(BASE+24)+k, _mm256_setzero_pd());
}
}
cur^=1;
ic+=mc;
}
if(n>=NTMIN)_mm_sfence();
}
static void sum(int h,double *dst,Mat a,Mat b,int sign) {
for(int i=0;i<h;i++)for(int j=0;j<h;j+=8) {
__m256d v=sign>0?_mm256_add_pd(ld(a,i,j),ld(b,i,j)):_mm256_sub_pd(ld(a,i,j),ld(b,i,j));
__m256d w=sign>0?_mm256_add_pd(ld(a,i,j+4),ld(b,i,j+4)):_mm256_sub_pd(ld(a,i,j+4),ld(b,i,j+4));
asm volatile("" : "+x"(v), "+x"(w) : : "memory");
if(h>=SUMNT) {
_mm256_stream_pd(dst+(size_t)i*h+j,v);_mm256_stream_pd(dst+(size_t)i*h+j+4,w);
} else {
_mm256_store_pd(dst+(size_t)i*h+j,v);_mm256_store_pd(dst+(size_t)i*h+j+4,w);
}
}
if(h>=SUMNT)_mm_sfence();
}
static void combine(int h,double *c,int ldc,const double *m,bool wino=false) {
size_t z=(size_t)h*h+(wino?UPPER_PAGE_PAD:0);
for(int i=0;i<h;i++)for(int j=0;j<h;j+=4) {
size_t t=(size_t)i*h+j;
double *c11=c+(size_t)i*ldc+j,*c12=c11+h,*c21=c+(size_t)(i+h)*ldc+j,*c22=c21+h;
__m256d m1=_mm256_load_pd(c11),m2=_mm256_load_pd(c21),m3=_mm256_load_pd(c12),m4=_mm256_load_pd(c22),
m5=_mm256_load_pd(m+t),m6=_mm256_load_pd(m+z+t),m7=_mm256_load_pd(m+2*z+t);
__m256d r11,r12,r21,r22;
if(wino) {
__m256d u2=_mm256_add_pd(m1,m6),u3=_mm256_add_pd(u2,m7),u4=_mm256_add_pd(u2,m5);
r11=_mm256_add_pd(m1,m2);r12=_mm256_add_pd(u4,m3);r21=_mm256_sub_pd(u3,m4);r22=_mm256_add_pd(u3,m5);
} else {
r11=_mm256_add_pd(_mm256_sub_pd(_mm256_add_pd(m1,m4),m5),m7);r12=_mm256_add_pd(m3,m5);r21=_mm256_add_pd(m2,m4);
r22=_mm256_add_pd(_mm256_add_pd(_mm256_sub_pd(m1,m2),m3),m6);
}
_mm256_store_pd(c11,r11);_mm256_store_pd(c12,r12);_mm256_store_pd(c21,r21);_mm256_store_pd(c22,r22);
}
}
static void pre(int h,Mat a,double *s1,double *s2,double *s4,double *s3,int ld3,bool right) {
for(int i=0;i<h;i++)for(int j=0;j<h;j+=8) {
__m256d a0=ld(a,i,j),a1=ld(a,i,j+4),b0=ld(a,i,j+h),b1=ld(a,i,j+h+4),
c0=ld(a,i+h,j),c1=ld(a,i+h,j+4),d0=ld(a,i+h,j+h),d1=ld(a,i+h,j+h+4);
__m256d p0,p1,q0,q1,r0,r1,t0,t1;
if(!right) {
p0=_mm256_add_pd(c0,d0);p1=_mm256_add_pd(c1,d1);
q0=_mm256_sub_pd(p0,a0);q1=_mm256_sub_pd(p1,a1);
r0=_mm256_sub_pd(b0,q0);r1=_mm256_sub_pd(b1,q1);
t0=_mm256_sub_pd(a0,c0);t1=_mm256_sub_pd(a1,c1);
}else {
p0=_mm256_sub_pd(b0,a0);p1=_mm256_sub_pd(b1,a1);
q0=_mm256_sub_pd(d0,p0);q1=_mm256_sub_pd(d1,p1);
r0=_mm256_sub_pd(q0,c0);r1=_mm256_sub_pd(q1,c1);
t0=_mm256_sub_pd(d0,b0);t1=_mm256_sub_pd(d1,b1);
}
size_t off=(size_t)i*h+j,off3=(size_t)i*ld3+j;
_mm256_stream_pd(s1+off,p0);_mm256_stream_pd(s1+off+4,p1);
_mm256_stream_pd(s2+off,q0);_mm256_stream_pd(s2+off+4,q1);
_mm256_stream_pd(s4+off,r0);_mm256_stream_pd(s4+off+4,r1);
_mm256_stream_pd(s3+off3,t0);_mm256_stream_pd(s3+off3+4,t1);
}
_mm_sfence();
}
static const int lperm[7]={2,4,5,1,3,6,0};
static void rec(int n,Mat a,Mat b,double *c,int ldc,double *work) {
if(n<=BASE){leaf(n,a,b,c,ldc);return;}
int h=n/2;size_t z=(size_t)h*h;
Mat aa[4]={{a.x,a.ld},{a.x+h,a.ld},{a.x+(size_t)h*a.ld,a.ld},{a.x+(size_t)h*a.ld+h,a.ld}};
Mat bb[4]={{b.x,b.ld},{b.x+h,b.ld},{b.x+(size_t)h*b.ld,b.ld},{b.x+(size_t)h*b.ld+h,b.ld}};
double *m=n==2*BASE?work+LEAF_PAD:work;
if(n==2*BASE && pending.active && pending.m==m)m=pending_work+LEAF_PAD;
size_t pz=z+(n==2*BASE?LEAF_PAD:UPPER_PAGE_PAD);
double *p=work+3*z,*q=p+z,*sub=q+z;
double *out[7]={c,c+(size_t)h*ldc,c+h,c+(size_t)h*ldc+h,m,m+pz,m+2*pz};
if(n>BASE*2) {
pending_finish();
double *pa0=m+3*pz,*pa1=pa0+pz,*pa2=pa1+pz,*pb0=pa2+pz,*pb1=pb0+pz,*pb2=pb1+pz;
sub=pb2+pz;
pre(h,a,pa0,pa1,pa2,c,ldc,false);
pre(h,b,pb0,pb1,pb2,c+h,ldc,true);
/* mdA_dp2: child order [1,3,4,5,6,0,2] -- constraint "6 before 0 and 2" is the only
hard one; this order puts the three m-panel writers (4,5,6) as late as possible,
which IS the deferral window for the previous sibling's deferred h=1024 combine. */
rec(h,aa[1],bb[2],out[1],ldc,sub);
rec(h,aa[3],{pb2,h},out[3],ldc,sub);
pend2_finish(); /* barrier: next call writes m, the deferred products */
rec(h,{pa0,h},{pb0,h},out[4],h,sub);
rec(h,{pa1,h},{pb1,h},out[5],h,sub);
rec(h,{c,ldc},{c+h,ldc},out[6],h,sub);
rec(h,aa[0],bb[0],out[0],ldc,sub);
rec(h,{pa2,h},bb[3],out[2],ldc,sub);
pending_finish();
pend2_finish(); /* finish an older deferred one */
pend2={c,ldc,m,h,(int)pz,0,true}; /* defer THIS combine (wino form);
m-plane stride = the engine's pz */
return;
}
const int ai[7]={0,2,0,3,0,2,1},aj[7]={3,3,-1,-1,1,0,3},as[7]={1,1,0,0,1,-1,-1};
const int bi[7]={0,0,1,2,3,0,2},bj[7]={3,-1,3,0,-1,1,3},bs[7]={1,0,-1,-1,0,1,1};
for(int r=0;r<7;r++) {
Mat x=aa[ai[r]],y=bb[bi[r]];
if(h<=BASE) {
/* mdE_perm: leaf-order permutation (outputs independent => bit-exact).
lperm = {2,4,5,1,3,6,0} A-adjacency 7 / B-adjacency 5 (natural order: 3/3). */
const int q=lperm[r];
Mat x=aa[ai[q]],y=bb[bi[q]];
if(as[q]){x.y=aa[aj[q]].x;x.ly=a.ld;x.sign=as[q];}
if(bs[q]){y.y=bb[bj[q]].x;y.ly=b.ld;y.sign=bs[q];}
leaf(h,x,y,out[q],q<4?ldc:h);
} else {
if(as[r]){sum(h,p,x,aa[aj[r]],as[r]);x={p,h};}
if(bs[r]){sum(h,q,y,bb[bj[r]],bs[r]);y={q,h};}
rec(h,x,y,out[r],r<4?ldc:h,sub);
}
}
if(h==BASE) {
pending_finish();
pending={c,ldc,m,0,true};
} else {
pending_finish();
combine(h,c,ldc,m);
}
}
void matrix_multiply(int n,const double *a,const double *b,double *c) {
rec(n,{a,n},{b,n},c,n,workspace);
pending_finish();
pend2_finish();
_mm_sfence();
}
| Compilation | N/A | N/A | Compile OK | Score: N/A | 显示更多 |
| Testcase #1 | 272.183 ms | 118 MB + 332 KB | Accepted | Score: 100 | 显示更多 |