2

我一直在根据一个粗略的经验法则进行操作,如果您有足够的数据进行操作,Q-form ASIMD 指令与 D-form 一样好或更好。因此,在阅读Cortex-A72 软件优化指南的第 3.15 节时,我很惊讶地看到FADDP,D 型的吞吐量为 2,Q 型的吞吐量为 2/3(作为参考,延迟分别为 4 和 7)。对于 D 和 Q 形式具有不同性能的所有其他指令在最坏的情况下只有很小的延迟差异(例如 3 对 4 FRINTX),并且具有相同或正好一半的吞吐量。 Cortex-A72 ASIMD 浮点指令特性

有什么特别之处FADDP在于它的吞吐量对于 Q-form 减少了三分之一,并且(如果你有前端带宽)你真的可以通过用两个 D-form 指令替换 Q-form 来增加吞吐量吗?

测试和基准测试:

我编写了几个 c++ 函数来尝试以两种方式锻炼 cortex-a72:

void q(float *i) {
  auto x = vld1q_f32_x4(i);
  auto y = vld1q_f32_x4(i + 16);
  for (int i = 0; i < 8192; ++i) {
    x.val[0] = vpaddq_f32(x.val[0], y.val[0]);
    x.val[1] = vpaddq_f32(x.val[1], y.val[1]);
    x.val[2] = vpaddq_f32(x.val[2], y.val[2]);
    x.val[3] = vpaddq_f32(x.val[3], y.val[3]);
    y.val[0] = vpaddq_f32(x.val[0], y.val[0]);
    y.val[1] = vpaddq_f32(x.val[1], y.val[1]);
    y.val[2] = vpaddq_f32(x.val[2], y.val[2]);
    y.val[3] = vpaddq_f32(x.val[3], y.val[3]);
  }
  vst1q_f32_x4(i, x);
}

void d(float *i) {
  auto x0 = vld1_f32_x4(i);
  auto x1 = vld1_f32_x4(i + 8);
  auto y0 = vld1_f32_x4(i + 16);
  auto y1 = vld1_f32_x4(i + 24);
  for (int i = 0; i < 8192; ++i) {
    x0.val[0] = vpadd_f32(x0.val[0], x0.val[1]);
    x0.val[1] = vpadd_f32(y0.val[0], y0.val[1]);
    x0.val[2] = vpadd_f32(x0.val[2], x0.val[3]);
    x0.val[3] = vpadd_f32(y0.val[2], y0.val[3]);
    x1.val[0] = vpadd_f32(x1.val[0], x1.val[1]);
    x1.val[1] = vpadd_f32(y1.val[0], y1.val[1]);
    x1.val[2] = vpadd_f32(x1.val[2], x1.val[3]);
    x1.val[3] = vpadd_f32(y1.val[2], y1.val[3]);
    y0.val[0] = vpadd_f32(x0.val[0], x0.val[1]);
    y0.val[1] = vpadd_f32(y0.val[0], y0.val[1]);
    y0.val[2] = vpadd_f32(x0.val[2], x0.val[3]);
    y0.val[3] = vpadd_f32(y0.val[2], y0.val[3]);
    y1.val[0] = vpadd_f32(x1.val[0], x1.val[1]);
    y1.val[1] = vpadd_f32(y1.val[0], y1.val[1]);
    y1.val[2] = vpadd_f32(x1.val[2], x1.val[3]);
    y1.val[3] = vpadd_f32(y1.val[2], y1.val[3]);
  }
  vst1_f32_x4(i, x0);
  vst1_f32_x4(i + 8, x1);
}

当使用 clang 和 -O3 编译时,它们会产生以下结果:

0000000000400a84 <_Z1qPf>:
  400a84:       aa0003e8        mov     x8, x0
  400a88:       4cdf2900        ld1     {v0.4s-v3.4s}, [x8], #64
  400a8c:       4c402904        ld1     {v4.4s-v7.4s}, [x8]
  400a90:       52840008        mov     w8, #0x2000                     // #8192
  400a94:       4ea21c54        mov     v20.16b, v2.16b
  400a98:       4ea11c35        mov     v21.16b, v1.16b
  400a9c:       4ea01c10        mov     v16.16b, v0.16b
  400aa0:       4ea61cd6        mov     v22.16b, v6.16b
  400aa4:       4ea51cb7        mov     v23.16b, v5.16b
  400aa8:       4ea41c98        mov     v24.16b, v4.16b
  400aac:       6e38d610        faddp   v16.4s, v16.4s, v24.4s
  400ab0:       6e37d6b5        faddp   v21.4s, v21.4s, v23.4s
  400ab4:       6e36d694        faddp   v20.4s, v20.4s, v22.4s
  400ab8:       6e27d463        faddp   v3.4s, v3.4s, v7.4s
  400abc:       71000508        subs    w8, w8, #0x1
  400ac0:       6e38d618        faddp   v24.4s, v16.4s, v24.4s
  400ac4:       6e37d6b7        faddp   v23.4s, v21.4s, v23.4s
  400ac8:       6e36d696        faddp   v22.4s, v20.4s, v22.4s
  400acc:       6e27d467        faddp   v7.4s, v3.4s, v7.4s
  400ad0:       54fffee1        b.ne    400aac <_Z1qPf+0x28>  // b.any
  400ad4:       4eb51eb1        mov     v17.16b, v21.16b
  400ad8:       4eb41e92        mov     v18.16b, v20.16b
  400adc:       4ea31c73        mov     v19.16b, v3.16b
  400ae0:       4c002810        st1     {v16.4s-v19.4s}, [x0]
  400ae4:       d65f03c0        ret

0000000000400ae8 <_Z1dPf>:
  400ae8:       fc1c0fee        str     d14, [sp, #-64]!
  400aec:       6d0133ed        stp     d13, d12, [sp, #16]
  400af0:       6d022beb        stp     d11, d10, [sp, #32]
  400af4:       6d0323e9        stp     d9, d8, [sp, #48]
  400af8:       aa0003e8        mov     x8, x0
  400afc:       0cdf2900        ld1     {v0.2s-v3.2s}, [x8], #32
  400b00:       91010009        add     x9, x0, #0x40
  400b04:       0c402930        ld1     {v16.2s-v19.2s}, [x9]
  400b08:       91018009        add     x9, x0, #0x60
  400b0c:       0c402904        ld1     {v4.2s-v7.2s}, [x8]
  400b10:       0c402934        ld1     {v20.2s-v23.2s}, [x9]
  400b14:       52840009        mov     w9, #0x2000                     // #8192
  400b18:       4ea11c29        mov     v9.16b, v1.16b
  400b1c:       4ea01c18        mov     v24.16b, v0.16b
  400b20:       4ea51ca8        mov     v8.16b, v5.16b
  400b24:       4ea41c9c        mov     v28.16b, v4.16b
  400b28:       4eb21e4b        mov     v11.16b, v18.16b
  400b2c:       4eb11e2a        mov     v10.16b, v17.16b
  400b30:       4eb01e0e        mov     v14.16b, v16.16b
  400b34:       4eb61ecd        mov     v13.16b, v22.16b
  400b38:       4eb71eec        mov     v12.16b, v23.16b
  400b3c:       2e23d442        faddp   v2.2s, v2.2s, v3.2s
  400b40:       2e27d4c6        faddp   v6.2s, v6.2s, v7.2s
  400b44:       2e29d718        faddp   v24.2s, v24.2s, v9.2s
  400b48:       2e2ad5c9        faddp   v9.2s, v14.2s, v10.2s
  400b4c:       2e28d79c        faddp   v28.2s, v28.2s, v8.2s
  400b50:       2e35d688        faddp   v8.2s, v20.2s, v21.2s
  400b54:       2e33d563        faddp   v3.2s, v11.2s, v19.2s
  400b58:       2e2cd5a7        faddp   v7.2s, v13.2s, v12.2s
  400b5c:       2e29d70e        faddp   v14.2s, v24.2s, v9.2s
  400b60:       2e28d794        faddp   v20.2s, v28.2s, v8.2s
  400b64:       2e23d44b        faddp   v11.2s, v2.2s, v3.2s
  400b68:       2e27d4cd        faddp   v13.2s, v6.2s, v7.2s
  400b6c:       71000529        subs    w9, w9, #0x1
  400b70:       2e2ad5ca        faddp   v10.2s, v14.2s, v10.2s
  400b74:       2e35d695        faddp   v21.2s, v20.2s, v21.2s
  400b78:       2e33d573        faddp   v19.2s, v11.2s, v19.2s
  400b7c:       2e2cd5ac        faddp   v12.2s, v13.2s, v12.2s
  400b80:       54fffde1        b.ne    400b3c <_Z1dPf+0x54>  // b.any
  400b84:       4ea91d39        mov     v25.16b, v9.16b
  400b88:       4ea81d1d        mov     v29.16b, v8.16b
  400b8c:       4ea21c5a        mov     v26.16b, v2.16b
  400b90:       4ea61cde        mov     v30.16b, v6.16b
  400b94:       4ea31c7b        mov     v27.16b, v3.16b
  400b98:       4ea71cff        mov     v31.16b, v7.16b
  400b9c:       0c002818        st1     {v24.2s-v27.2s}, [x0]
  400ba0:       0c00291c        st1     {v28.2s-v31.2s}, [x8]
  400ba4:       6d4323e9        ldp     d9, d8, [sp, #48]
  400ba8:       6d422beb        ldp     d11, d10, [sp, #32]
  400bac:       6d4133ed        ldp     d13, d12, [sp, #16]
  400bb0:       fc4407ee        ldr     d14, [sp], #64
  400bb4:       d65f03c0        ret

在我看来,那些主循环似乎没有找到任何技巧来避免计算,而且它只是一条直线 8 q-form faddp's vs 16 d-form。

使用 perf 进行基准测试时的结果如下:

Clocks per call
==============================
q       d
98631   90285

这并没有完全达到文档建议的收益(q 实际上非常接近文档建议的 8192 * 8 faddp 应该采用的理论 98304 周期,d 必须遇到延迟问题,这并不令人惊讶,因为有0x400b4c 和 0x400b60 之间的依赖关系,它们之间只有 4 条指令)。但是,这些收益似乎暗示着 d-form 有一些优势。

4

0 回答 0