參考連結： 利用neon技術對矩陣旋轉進行加速

目標：將輸入矩陣順時針旋轉90度，如下圖所示：

   輸入矩陣                                      輸出矩陣

以 8x8x8bit 的矩陣（更大的矩陣可以分塊為 8x8x8bit）為例，基本的思路就是，逐漸擴大粒度（8bit 到 32bit）的 2x2 矩陣旋轉

vtrn 示意圖，可以看作是 2x2 矩陣的轉置

原始的資料的位元組表示形式 

以 8 bit 為單位進行旋轉：

temp1 = vtrn_u8(mat1.val[1], mat1.val[0]);
temp2 = vtrn_u8(mat1.val[3], mat1.val[2]);
temp3 = vtrn_u8(mat2.val[1], mat2.val[0]);
temp4 = vtrn_u8(mat2.val[3], mat2.val[2]);
 

 結果以 16 bit 看作一個數（大端儲存）

 再次進行旋轉得到

temp9 = vtrn_u16(temp6.val[0], temp5.val[0]);
temp10 = vtrn_u16(temp6.val[1], temp5.val[1]);
temp11 = vtrn_u16(temp8.val[0], temp7.val[0]);
temp12 = vtrn_u16(temp8.val[1], temp7.val[1]);

旋轉的結果對應的位元組表示形式為（大端儲存） 

接著，把 32bit 當做一個數來旋轉 

temp17=vtrn_u32(temp15.val[0],temp13.val[0]);
temp18=vtrn_u32(temp15.val[1],temp13.val[1]);
temp19=vtrn_u32(temp16.val[0],temp14.val[0]);
temp20=vtrn_u32(temp16.val[1],temp14.val[1]);

 旋轉的結果為

對應的位元組表示形式為 

即最初矩陣的順時針 90 ° 旋轉的結果 

程式碼如下：

            uint8x8x4_t mat1, mat2;
            mat1.val[0] = vld1_u8(srcImg + i * width + j);  // vec8，每個元素 8 bit
            mat1.val[1] = vld1_u8(srcImg + (i + 1) * width + j);
            mat1.val[2] = vld1_u8(srcImg + (i + 2) * width + j);
            mat1.val[3] = vld1_u8(srcImg + (i + 3) * width + j);// 4*vec8
            mat2.val[0] = vld1_u8(srcImg + (i + 4) * width + j);
            mat2.val[1] = vld1_u8(srcImg + (i + 5) * width + j);
            mat2.val[2] = vld1_u8(srcImg + (i + 6) * width + j);
            mat2.val[3] = vld1_u8(srcImg + (i + 7) * width + j);

            uint8x8x2_t temp1, temp2, temp3, temp4;
            temp1 = vtrn_u8(mat1.val[1], mat1.val[0]);
            temp2 = vtrn_u8(mat1.val[3], mat1.val[2]);
            temp3 = vtrn_u8(mat2.val[1], mat2.val[0]);
            temp4 = vtrn_u8(mat2.val[3], mat2.val[2]);

            // ==============================================

            uint16x4x2_t temp5, temp6, temp7, temp8;
            temp5.val[0] = vreinterpret_u16_u8(temp1.val[0]);
            temp5.val[1] = vreinterpret_u16_u8(temp1.val[1]);
            temp6.val[0] = vreinterpret_u16_u8(temp2.val[0]);
            temp6.val[1] = vreinterpret_u16_u8(temp2.val[1]);
            temp7.val[0] = vreinterpret_u16_u8(temp3.val[0]);
            temp7.val[1] = vreinterpret_u16_u8(temp3.val[1]);
            temp8.val[0] = vreinterpret_u16_u8(temp4.val[0]);
            temp8.val[1] = vreinterpret_u16_u8(temp4.val[1]);

            uint16x4x2_t temp9, temp10, temp11, temp12;
            temp9 = vtrn_u16(temp6.val[0], temp5.val[0]);
            temp10 = vtrn_u16(temp6.val[1], temp5.val[1]);
            temp11 = vtrn_u16(temp8.val[0], temp7.val[0]);
            temp12 = vtrn_u16(temp8.val[1], temp7.val[1]);

            // ==============================================

            uint32x2x2_t temp13, temp14, temp15, temp16;
            temp13.val[0]= vreinterpret_u32_u16(temp9.val[0]);
            temp13.val[1]= vreinterpret_u32_u16(temp9.val[1]);
            temp14.val[0]= vreinterpret_u32_u16(temp10.val[0]);
            temp14.val[1]= vreinterpret_u32_u16(temp10.val[1]);
            temp15.val[0]= vreinterpret_u32_u16(temp11.val[0]);
            temp15.val[1]= vreinterpret_u32_u16(temp11.val[1]);
            temp16.val[0]= vreinterpret_u32_u16(temp12.val[0]);
            temp16.val[1]= vreinterpret_u32_u16(temp12.val[1]);

            uint32x2x2_t temp17, temp18, temp19, temp20;
            temp17=vtrn_u32(temp15.val[0],temp13.val[0]);
            temp18=vtrn_u32(temp15.val[1],temp13.val[1]);
            temp19=vtrn_u32(temp16.val[0],temp14.val[0]);
            temp20=vtrn_u32(temp16.val[1],temp14.val[1]);

            // ==============================================

            temp1.val[0]= vreinterpret_u8_u32(temp17.val[0]);
            temp1.val[1]= vreinterpret_u8_u32(temp19.val[0]);
            temp2.val[0]= vreinterpret_u8_u32(temp18.val[0]);
            temp2.val[1]= vreinterpret_u8_u32(temp20.val[0]);
            temp3.val[0]= vreinterpret_u8_u32(temp17.val[1]);
            temp3.val[1]= vreinterpret_u8_u32(temp19.val[1]);
            temp4.val[0]= vreinterpret_u8_u32(temp18.val[1]);
            temp4.val[1]= vreinterpret_u8_u32(temp20.val[1]);

            vst1_u8 (dstImg + j * height + i, temp1.val[0]);
            vst1_u8 (dstImg+ (j+1) * height + i, temp1.val[1]);
            vst1_u8 (dstImg+ (j+2) * height + i, temp2.val[0]);
            vst1_u8 (dstImg+ (j+3) * height + i, temp2.val[1]);
            vst1_u8 (dstImg+ (j+4) * height + i, temp3.val[0]);
            vst1_u8 (dstImg+ (j+5) * height + i, temp3.val[1]);
            vst1_u8 (dstImg+ (j+6) * height + i, temp4.val[0]);
            vst1_u8 (dstImg+ (j+7) * height + i, temp4.val[1]);