-struct processor_costs bdver1_cost = {
- COSTS_N_INSNS (1), /* cost of an add instruction */
- COSTS_N_INSNS (2), /* cost of a lea instruction */
- COSTS_N_INSNS (1), /* variable shift costs */
- COSTS_N_INSNS (1), /* constant shift costs */
- {COSTS_N_INSNS (3), /* cost of starting multiply for QI */
- COSTS_N_INSNS (4), /* HI */
- COSTS_N_INSNS (3), /* SI */
- COSTS_N_INSNS (4), /* DI */
- COSTS_N_INSNS (5)}, /* other */
- 0, /* cost of multiply per each bit set */
- {COSTS_N_INSNS (19), /* cost of a divide/mod for QI */
- COSTS_N_INSNS (35), /* HI */
- COSTS_N_INSNS (51), /* SI */
- COSTS_N_INSNS (83), /* DI */
- COSTS_N_INSNS (83)}, /* other */
- COSTS_N_INSNS (1), /* cost of movsx */
- COSTS_N_INSNS (1), /* cost of movzx */
- 8, /* "large" insn */
- 9, /* MOVE_RATIO */
- 4, /* cost for loading QImode using movzbl */
- {3, 4, 3}, /* cost of loading integer registers
- in QImode, HImode and SImode.
- Relative to reg-reg move (2). */
- {3, 4, 3}, /* cost of storing integer registers */
- 4, /* cost of reg,reg fld/fst */
- {4, 4, 12}, /* cost of loading fp registers
- in SFmode, DFmode and XFmode */
- {6, 6, 8}, /* cost of storing fp registers
- in SFmode, DFmode and XFmode */
- 2, /* cost of moving MMX register */
- {3, 3}, /* cost of loading MMX registers
- in SImode and DImode */
- {4, 4}, /* cost of storing MMX registers
- in SImode and DImode */
- 2, /* cost of moving SSE register */
- {4, 4, 3}, /* cost of loading SSE registers
- in SImode, DImode and TImode */
- {4, 4, 5}, /* cost of storing SSE registers
- in SImode, DImode and TImode */
- 3, /* MMX or SSE register to integer */
- /* On K8
- MOVD reg64, xmmreg Double FSTORE 4
- MOVD reg32, xmmreg Double FSTORE 4
- On AMDFAM10
- MOVD reg64, xmmreg Double FADD 3
- 1/1 1/1
- MOVD reg32, xmmreg Double FADD 3
- 1/1 1/1 */
- 64, /* size of l1 cache. */
- 1024, /* size of l2 cache. */
- 64, /* size of prefetch block */
- /* New AMD processors never drop prefetches; if they cannot be performed
- immediately, they are queued. We set number of simultaneous prefetches
- to a large constant to reflect this (it probably is not a good idea not
- to limit number of prefetches at all, as their execution also takes some
- time). */
- 100, /* number of parallel prefetches */
- 2, /* Branch cost */
- COSTS_N_INSNS (4), /* cost of FADD and FSUB insns. */
- COSTS_N_INSNS (4), /* cost of FMUL instruction. */
- COSTS_N_INSNS (19), /* cost of FDIV instruction. */
- COSTS_N_INSNS (2), /* cost of FABS instruction. */
- COSTS_N_INSNS (2), /* cost of FCHS instruction. */
- COSTS_N_INSNS (35), /* cost of FSQRT instruction. */
-
- /* BDVER1 has optimized REP instruction for medium sized blocks, but for
- very small blocks it is better to use loop. For large blocks, libcall can
- do nontemporary accesses and beat inline considerably. */
- {{libcall, {{6, loop}, {14, unrolled_loop}, {-1, rep_prefix_4_byte}}},
- {libcall, {{16, loop}, {8192, rep_prefix_8_byte}, {-1, libcall}}}},
- {{libcall, {{8, loop}, {24, unrolled_loop},
- {2048, rep_prefix_4_byte}, {-1, libcall}}},
- {libcall, {{48, unrolled_loop}, {8192, rep_prefix_8_byte}, {-1, libcall}}}},
- 4, /* scalar_stmt_cost. */
- 2, /* scalar load_cost. */
- 2, /* scalar_store_cost. */
- 6, /* vec_stmt_cost. */
- 0, /* vec_to_scalar_cost. */
- 2, /* scalar_to_vec_cost. */
- 2, /* vec_align_load_cost. */
- 2, /* vec_unalign_load_cost. */
- 2, /* vec_store_cost. */
- 2, /* cond_taken_branch_cost. */
- 1, /* cond_not_taken_branch_cost. */
-};
-