在SSE2 / SSSE3上转换8个16位元素寄存器

时间：2010-03-25 16:53:45

标签： assembly matrix x86 sse simd

（我是SSE / asm的新手，如果这显而易见或多余则道歉）

是否有更好的方法来转换包含16位值的8个SSE寄存器，而不是执行24个unpck [lh] ps和8/16 + shuffle以及使用8个额外的寄存器？ （注意最多使用SSSE 3指令，Intel Merom，又称SSE4缺少BLEND *。）

假设您有寄存器v [0-7]并使用t0-t7作为辅助寄存器。在伪内在函数代码中：

/* Phase 1: process lower parts of the registers */
/* Level 1: work first part of the vectors */
/*   v[0]  A0 A1 A2 A3 A4 A5 A6 A7
**   v[1]  B0 B1 B2 B3 B4 B5 B6 B7
**   v[2]  C0 C1 C2 C3 C4 C5 C6 C7
**   v[3]  D0 D1 D2 D3 D4 D5 D6 D7
**   v[4]  E0 E1 E2 E3 E4 E5 E6 E7
**   v[5]  F0 F1 F2 F3 F4 F5 F6 F7
**   v[6]  G0 G1 G2 G3 G4 G5 G6 G7
**   v[7]  H0 H1 H2 H3 H4 H5 H6 H7 */
t0 = unpcklps (v[0], v[1]); /* Extract first half interleaving */
t1 = unpcklps (v[2], v[3]); /* Extract first half interleaving */
t2 = unpcklps (v[4], v[5]); /* Extract first half interleaving */
t3 = unpcklps (v[6], v[7]); /* Extract first half interleaving */
t0 = pshufhw (t0, 0xD8); /* Flip middle 2 high */
t0 = pshuflw (t0, 0xD8); /* Flip middle 2 low */
t1 = pshufhw (t1, 0xD8); /* Flip middle 2 high */
t1 = pshuflw (t1, 0xD8); /* Flip middle 2 low */
t2 = pshufhw (t2, 0xD8); /* Flip middle 2 high */
t2 = pshuflw (t2, 0xD8); /* Flip middle 2 low */
t3 = pshufhw (t3, 0xD8); /* Flip middle 2 high */
t3 = pshuflw (t3, 0xD8); /* Flip middle 2 low */
/*   t0   A0 B0 A1 B1 A2 B2 A3 B3  (A B - 0 1 2 3)
**   t1   C0 D0 C1 D1 C2 D2 C3 D3  (C D - 0 1 2 3)
**   t2   E0 F0 E1 F1 E2 F2 E3 F3  (E F - 0 1 2 3)
**   t3   G0 H0 G1 H1 G2 H2 G3 H3  (G H - 0 1 2 3) */
/* L2 */
t4 = unpcklps (t0, t1);
t5 = unpcklps (t2, t3);
t6 = unpckhps (t0, t1);
t7 = unpckhps (t2, t3);
/*   t4   A0 B0 C0 D0 A1 B1 C1 D1 (A B C D - 0 1)
**   t5   E0 F0 G0 H0 E1 F1 G1 H1 (E F G H - 0 1)
**   t6   A2 B2 C2 D2 A3 B3 C3 D3 (A B C D - 2 3)
**   t7   E2 F2 G2 H2 E3 F3 G3 H3 (E F G H - 2 3) */
/* Phase 2: same with higher parts of the registers */
/*   A    A0 A1 A2 A3 A4 A5 A6 A7
**   B    B0 B1 B2 B3 B4 B5 B6 B7
**   C    C0 C1 C2 C3 C4 C5 C6 C7
**   D    D0 D1 D2 D3 D4 D5 D6 D7
**   E    E0 E1 E2 E3 E4 E5 E6 E7
**   F    F0 F1 F2 F3 F4 F5 F6 F7
**   G    G0 G1 G2 G3 G4 G5 G6 G7
**   H    H0 H1 H2 H3 H4 H5 H6 H7 */
t0 = unpckhps (v[0], v[1]);
t0 = pshufhw (t0, 0xD8); /* Flip middle 2 high */
t0 = pshuflw (t0, 0xD8); /* Flip middle 2 low */
t1 = unpckhps (v[2], v[3]);
t1 = pshufhw (t1, 0xD8); /* Flip middle 2 high */
t1 = pshuflw (t1, 0xD8); /* Flip middle 2 low */
t2 = unpckhps (v[4], v[5]);
t2 = pshufhw (t2, 0xD8); /* Flip middle 2 high */
t2 = pshuflw (t2, 0xD8); /* Flip middle 2 low */
t3 = unpckhps (v[6], v[7]);
t3 = pshufhw (t3, 0xD8); /* Flip middle 2 high */
t3 = pshuflw (t3, 0xD8); /* Flip middle 2 low */
/*   t0   A4 B4 A5 B5 A6 B6 A7 B7  (A B - 4 5 6 7)
**   t1   C4 D4 C5 D5 C6 D6 C7 D7  (C D - 4 5 6 7)
**   t2   E4 F4 E5 F5 E6 F6 E7 F7  (E F - 4 5 6 7)
**   t3   G4 H4 G5 H5 G6 H6 G7 H7  (G H - 4 5 6 7) */
/* Back to first part, v[0-3] can be re-written now */
/* L3 */
v[0] = unpcklpd (t4, t5);
v[1] = unpckhpd (t4, t5);
v[2] = unpcklpd (t6, t7);
v[3] = unpckhpd (t6, t7);
/* v[0] = A0 B0 C0 D0 E0 F0 G0 H0
** v[1] = A1 B1 C1 D1 E1 F1 G1 H1
** v[2] = A2 B2 C2 D2 E2 F2 G2 H2
** v[3] = A3 B3 C3 D3 E3 F3 G3 H3 */
/* Back to second part, t[4-7] can be re-written now... */
/* L2 */
t4 = unpcklps (t0, t1);
t5 = unpcklps (t2, t3);
t6 = unpckhps (t0, t1);
t7 = unpckhps (t2, t3);
/*   t4   A4 B4 C4 D4 A5 B5 C5 D5 (A B C D - 4 5)
**   t5   E4 F4 G4 H4 E5 F5 G5 H5 (E F G H - 4 5)
**   t6   A6 B6 C6 D6 A7 B7 C7 D7 (A B C D - 6 7)
**   t7   E6 F6 G6 H6 E7 F7 G7 H7 (E F G H - 6 7) */
/* L3 */
v[4] = unpcklpd (t4, t5);
v[5] = unpckhpd (t4, t5);
v[6] = unpcklpd (t6, t7);
v[7] = unpckhpd (t6, t7);
/* v[4] = A4 B4 C4 D4 E4 F4 G4 H4
** v[5] = A5 B5 C5 D5 E5 F5 G5 H5
** v[6] = A6 B6 C6 D6 E6 F6 G6 H6
** v[7] = A7 B7 C7 D7 E7 F7 G7 H7 */

每个unpck *需要3个周期的延迟，或2个用于倒数吞吐量（由Agner报告。）这使得使用SSE（在此代码上）获得了大部分性能提升，因为这个寄存器舞蹈每个元素几乎需要一个周期。我试图理解x264的asm文件用于x86转置但却无法理解宏。

谢谢！

3 个答案:

答案 0 :(得分：6)

是的，您可以完成24条指令：

8 x _mm_unpacklo_epi16/_mm_unpackhi_epi16 (PUNPCKLWD/PUNPCKHWD)
8 x _mm_unpacklo_epi32/_mm_unpackhi_epi32 (PUNPCKLDQ/PUNPCKHDQ)
8 x _mm_unpacklo_epi64/_mm_unpackhi_epi64 (PUNPCKLQDQ/PUNPCKHQDQ)

如果您需要更多细节，请告诉我，但这很明显。

答案 1 :(得分：5)

我必须自己做，所以这是我的最终结果。请注意，我使用的加载和存储指令用于16字节对齐的数组，这些数组是使用声明的 m128i * array =（__ m128i *）_ mm_malloc（N * sizeof（uint16_t），16）; 要么 int16_t array [N] __ attribute （（aligned（16）））; 

__m128i *p_input  = (__m128i*)array;
__m128i *p_output = (__m128i*)array;
__m128i a = _mm_load_si128(p_input++);
__m128i b = _mm_load_si128(p_input++);
__m128i c = _mm_load_si128(p_input++);
__m128i d = _mm_load_si128(p_input++);
__m128i e = _mm_load_si128(p_input++);
__m128i f = _mm_load_si128(p_input++);
__m128i g = _mm_load_si128(p_input++);
__m128i h = _mm_load_si128(p_input);

__m128i a03b03 = _mm_unpacklo_epi16(a, b);
__m128i c03d03 = _mm_unpacklo_epi16(c, d);
__m128i e03f03 = _mm_unpacklo_epi16(e, f);
__m128i g03h03 = _mm_unpacklo_epi16(g, h);
__m128i a47b47 = _mm_unpackhi_epi16(a, b);
__m128i c47d47 = _mm_unpackhi_epi16(c, d);
__m128i e47f47 = _mm_unpackhi_epi16(e, f);
__m128i g47h47 = _mm_unpackhi_epi16(g, h);

__m128i a01b01c01d01 = _mm_unpacklo_epi32(a03b03, c03d03);
__m128i a23b23c23d23 = _mm_unpackhi_epi32(a03b03, c03d03);
__m128i e01f01g01h01 = _mm_unpacklo_epi32(e03f03, g03h03);
__m128i e23f23g23h23 = _mm_unpackhi_epi32(e03f03, g03h03);
__m128i a45b45c45d45 = _mm_unpacklo_epi32(a47b47, c47d47);
__m128i a67b67c67d67 = _mm_unpackhi_epi32(a47b47, c47d47);
__m128i e45f45g45h45 = _mm_unpacklo_epi32(e47f47, g47h47);
__m128i e67f67g67h67 = _mm_unpackhi_epi32(e47f47, g47h47);

__m128i a0b0c0d0e0f0g0h0 = _mm_unpacklo_epi64(a01b01c01d01, e01f01g01h01);
__m128i a1b1c1d1e1f1g1h1 = _mm_unpackhi_epi64(a01b01c01d01, e01f01g01h01);
__m128i a2b2c2d2e2f2g2h2 = _mm_unpacklo_epi64(a23b23c23d23, e23f23g23h23);
__m128i a3b3c3d3e3f3g3h3 = _mm_unpackhi_epi64(a23b23c23d23, e23f23g23h23);
__m128i a4b4c4d4e4f4g4h4 = _mm_unpacklo_epi64(a45b45c45d45, e45f45g45h45);
__m128i a5b5c5d5e5f5g5h5 = _mm_unpackhi_epi64(a45b45c45d45, e45f45g45h45);
__m128i a6b6c6d6e6f6g6h6 = _mm_unpacklo_epi64(a67b67c67d67, e67f67g67h67);
__m128i a7b7c7d7e7f7g7h7 = _mm_unpackhi_epi64(a67b67c67d67, e67f67g67h67);

_mm_store_si128(p_output++, a0b0c0d0e0f0g0h0);
_mm_store_si128(p_output++, a1b1c1d1e1f1g1h1);
_mm_store_si128(p_output++, a2b2c2d2e2f2g2h2);
_mm_store_si128(p_output++, a3b3c3d3e3f3g3h3);
_mm_store_si128(p_output++, a4b4c4d4e4f4g4h4);
_mm_store_si128(p_output++, a5b5c5d5e5f5g5h5);
_mm_store_si128(p_output++, a6b6c6d6e6f6g6h6);
_mm_store_si128(p_output, a7b7c7d7e7f7g7h7);

答案 2 :(得分：0)

我的想法来自http://www.randombit.net/bitbashing/programming/integer_matrix_transpose_in_sse2.html

我会将一个8x8分割为四个4x4 而不是提到的技巧。 最后交换块（0,1）和块（1,0）

然而，我仍然没有得到Paul R的伎俩。 保罗，你会给我一些更多的点击吗？

相关问题
最新问题