in 128bit, 256bit and 512bit */
3, 3, 3, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_BYTES (2), /* cost of moving integer to sse register. */
5, 0, /* Gather load static, per_elt. */
5, 0, /* Gather store static, per_elt. */
0, /* size of l1 cache */
{4, 8, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
0, /* size of l1 cache */
{4, 8, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
4, /* size of l1 cache. 486 has 8kB cache
{4, 8, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
8, /* size of l1 cache. */
{4, 8, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
8, /* size of l1 cache. */
{4, 8, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
8, /* size of l1 cache. */
{2, 2, 8, 16, 32}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
2, 2, /* Gather load static, per_elt. */
2, 2, /* Gather store static, per_elt. */
64, /* size of l1 cache. */
{2, 2, 8, 16, 32}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
2, 2, /* Gather load static, per_elt. */
2, 2, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{4, 4, 10, 10, 20}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
5, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
64, /* size of l1 cache. */
{4, 4, 10, 10, 20}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
5, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
64, /* size of l1 cache. */
{4, 4, 5, 10, 20}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
3, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2), /* cost of moving integer to sse register. */
4, 4, /* Gather load static, per_elt. */
4, 4, /* Gather store static, per_elt. */
64, /* size of l1 cache. */
{10, 10, 10, 40, 60}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
16, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2), /* cost of moving integer to sse register. */
12, 12, /* Gather load static, per_elt. */
10, 10, /* Gather store static, per_elt. */
16, /* size of l1 cache. */
{8, 8, 8, 16, 32}, /* cost of unaligned stores. */
2, 3, 6, /* cost of moving XMM,YMM,ZMM register. */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
/* VGATHERDPD is 23 uops and throughput is 9, VGATHERDPD is 35 uops,
throughput 12. Approx 9 uops do not depend on vector size and every load
is 7 uops. */
2, 2, 3, /* cost of moving XMM,YMM,ZMM
register. */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
/* VGATHERDPD is 23 uops and throughput is 9, VGATHERDPD is 35 uops,
throughput 12. Approx 9 uops do not depend on vector size and every load
is 7 uops. */
2, 2, 3, /* cost of moving XMM,YMM,ZMM
register. */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
/* VGATHERDPD is 15 uops and throughput is 4, VGATHERDPS is 23 uops,
throughput 9. Approx 7 uops do not depend on vector size and every load
is 4 uops. */
{8, 8, 8, 8, 16}, /* cost of unaligned stores. */
2, 2, 4, /* cost of moving XMM,YMM,ZMM register */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2)+1, /* cost of moving integer to sse register. */
20, 8, /* Gather load static, per_elt. */
22, 10, /* Gather store static, per_elt. */
64, /* size of l1 cache. */
{8, 8, 8, 8, 16}, /* cost of unaligned stores. */
2, 2, 4, /* cost of moving XMM,YMM,ZMM register */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
20, 8, /* Gather load static, per_elt. */
22, 10, /* Gather store static, per_elt. */
64, /* size of l1 cache. */
{10, 10, 12, 48, 96}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
14, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
10, 10, /* Gather load static, per_elt. */
10, 10, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{10, 10, 12, 48, 96}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
14, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
10, 10, /* Gather load static, per_elt. */
10, 10, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{32, 32, 32, 64, 128}, /* cost of unaligned stores. */
12, 24, 48, /* cost of moving XMM,YMM,ZMM register */
20, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2), /* cost of moving integer to sse register. */
16, 16, /* Gather load static, per_elt. */
16, 16, /* Gather store static, per_elt. */
8, /* size of l1 cache. */
{24, 24, 24, 48, 96}, /* cost of unaligned stores. */
6, 12, 24, /* cost of moving XMM,YMM,ZMM register */
20, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (2), /* cost of moving integer to sse register. */
12, 12, /* Gather load static, per_elt. */
12, 12, /* Gather store static, per_elt. */
8, /* size of l1 cache. */
{16, 16, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
8, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
8, 8, /* Gather load static, per_elt. */
8, 8, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{16, 16, 16, 32, 64}, /* cost of unaligned stores. */
2, 4, 8, /* cost of moving XMM,YMM,ZMM register */
8, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
8, 8, /* Gather load static, per_elt. */
8, 8, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{10, 10, 10, 10, 10}, /* cost of unaligned loads. */
2, 2, 2, /* cost of moving XMM,YMM,ZMM register */
4, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
6, 6, /* Gather load static, per_elt. */
6, 6, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{6, 6, 6, 10, 15}, /* cost of unaligned storess. */
2, 3, 4, /* cost of moving XMM,YMM,ZMM register */
6, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
18, 6, /* Gather load static, per_elt. */
18, 6, /* Gather store static, per_elt. */
32, /* size of l1 cache. */
{6, 6, 6, 6, 12}, /* cost of unaligned stores. */
2, 2, 4, /* cost of moving XMM,YMM,ZMM register */
2, /* cost of moving SSE register to integer. */
- COSTS_N_INSNS (1), /* cost of moving integer to sse register. */
/* VGATHERDPD is 7 uops, rec throughput 5, while VGATHERDPD is 9 uops,
rec. throughput 6.
So 5 uops statically and one uops per load. */