Skip to content

R
riscv-gcc-1
Commit a9cc9cc6 by Jan Hubicka Committed by Jan Hubicka
Options

i386.c (*_cost): Add COSTS_N_INSNS. 

	* i386.c (*_cost): Add COSTS_N_INSNS.
	(ix86_rtx_costs): Do not use COSTS_N_INSNS.

From-SVN: r109242
parent 4c4b3eb0
Showing with 256 additions and 170 deletions
gcc/ChangeLog
2006-01-02 Jan Hubicka <jh@suse.cz>
* i386.c (*_cost): Add COSTS_N_INSNS.
(ix86_rtx_costs): Do not use COSTS_N_INSNS.
2006-01-02 Paolo Bonzini <bonzini@gnu.org> 2006-01-02 Paolo Bonzini <bonzini@gnu.org>
PR target/25259 PR target/25259
......
gcc/config/i386/i386.c
...@@ -65,15 +65,23 @@ Boston, MA 02110-1301, USA. */ ...@@ -65,15 +65,23 @@ Boston, MA 02110-1301, USA. */
/* Processor costs (relative to an add) */ /* Processor costs (relative to an add) */
static const static const
struct processor_costs size_cost = { /* costs for tunning for size */ struct processor_costs size_cost = { /* costs for tunning for size */
2, /* cost of an add instruction */ COSTS_N_INSNS (2), /* cost of an add instruction */
3, /* cost of a lea instruction */ COSTS_N_INSNS (3), /* cost of a lea instruction */
2, /* variable shift costs */ COSTS_N_INSNS (2), /* variable shift costs */
3, /* constant shift costs */ COSTS_N_INSNS (3), /* constant shift costs */
{3, 3, 3, 3, 5}, /* cost of starting a multiply */ {COSTS_N_INSNS (3), /* cost of starting multiply for QI */
COSTS_N_INSNS (3), /* HI */
COSTS_N_INSNS (3), /* SI */
COSTS_N_INSNS (3), /* DI */
COSTS_N_INSNS (5)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{3, 3, 3, 3, 5}, /* cost of a divide/mod */ {COSTS_N_INSNS (3), /* cost of a divide/mod for QI */
3, /* cost of movsx */ COSTS_N_INSNS (3), /* HI */
3, /* cost of movzx */ COSTS_N_INSNS (3), /* SI */
COSTS_N_INSNS (3), /* DI */
COSTS_N_INSNS (5)}, /* other */
COSTS_N_INSNS (3), /* cost of movsx */
COSTS_N_INSNS (3), /* cost of movzx */
0, /* "large" insn */ 0, /* "large" insn */
2, /* MOVE_RATIO */ 2, /* MOVE_RATIO */
2, /* cost for loading QImode using movzbl */ 2, /* cost for loading QImode using movzbl */
...@@ -99,26 +107,34 @@ struct processor_costs size_cost = { /* costs for tunning for size */ ...@@ -99,26 +107,34 @@ struct processor_costs size_cost = { /* costs for tunning for size */
0, /* size of prefetch block */ 0, /* size of prefetch block */
0, /* number of parallel prefetches */ 0, /* number of parallel prefetches */
1, /* Branch cost */ 1, /* Branch cost */
2, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (2), /* cost of FADD and FSUB insns. */
2, /* cost of FMUL instruction. */ COSTS_N_INSNS (2), /* cost of FMUL instruction. */
2, /* cost of FDIV instruction. */ COSTS_N_INSNS (2), /* cost of FDIV instruction. */
2, /* cost of FABS instruction. */ COSTS_N_INSNS (2), /* cost of FABS instruction. */
2, /* cost of FCHS instruction. */ COSTS_N_INSNS (2), /* cost of FCHS instruction. */
2, /* cost of FSQRT instruction. */ COSTS_N_INSNS (2), /* cost of FSQRT instruction. */
}; };
/* Processor costs (relative to an add) */ /* Processor costs (relative to an add) */
static const static const
struct processor_costs i386_cost = { /* 386 specific costs */ struct processor_costs i386_cost = { /* 386 specific costs */
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
1, /* cost of a lea instruction */ COSTS_N_INSNS (1), /* cost of a lea instruction */
3, /* variable shift costs */ COSTS_N_INSNS (3), /* variable shift costs */
2, /* constant shift costs */ COSTS_N_INSNS (2), /* constant shift costs */
{6, 6, 6, 6, 6}, /* cost of starting a multiply */ {COSTS_N_INSNS (6), /* cost of starting multiply for QI */
1, /* cost of multiply per each bit set */ COSTS_N_INSNS (6), /* HI */
{23, 23, 23, 23, 23}, /* cost of a divide/mod */ COSTS_N_INSNS (6), /* SI */
3, /* cost of movsx */ COSTS_N_INSNS (6), /* DI */
2, /* cost of movzx */ COSTS_N_INSNS (6)}, /* other */
COSTS_N_INSNS (1), /* cost of multiply per each bit set */
{COSTS_N_INSNS (23), /* cost of a divide/mod for QI */
COSTS_N_INSNS (23), /* HI */
COSTS_N_INSNS (23), /* SI */
COSTS_N_INSNS (23), /* DI */
COSTS_N_INSNS (23)}, /* other */
COSTS_N_INSNS (3), /* cost of movsx */
COSTS_N_INSNS (2), /* cost of movzx */
15, /* "large" insn */ 15, /* "large" insn */
3, /* MOVE_RATIO */ 3, /* MOVE_RATIO */
4, /* cost for loading QImode using movzbl */ 4, /* cost for loading QImode using movzbl */
...@@ -144,25 +160,33 @@ struct processor_costs i386_cost = { /* 386 specific costs */ ...@@ -144,25 +160,33 @@ struct processor_costs i386_cost = { /* 386 specific costs */
0, /* size of prefetch block */ 0, /* size of prefetch block */
0, /* number of parallel prefetches */ 0, /* number of parallel prefetches */
1, /* Branch cost */ 1, /* Branch cost */
23, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (23), /* cost of FADD and FSUB insns. */
27, /* cost of FMUL instruction. */ COSTS_N_INSNS (27), /* cost of FMUL instruction. */
88, /* cost of FDIV instruction. */ COSTS_N_INSNS (88), /* cost of FDIV instruction. */
22, /* cost of FABS instruction. */ COSTS_N_INSNS (22), /* cost of FABS instruction. */
24, /* cost of FCHS instruction. */ COSTS_N_INSNS (24), /* cost of FCHS instruction. */
122, /* cost of FSQRT instruction. */ COSTS_N_INSNS (122), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs i486_cost = { /* 486 specific costs */ struct processor_costs i486_cost = { /* 486 specific costs */
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
1, /* cost of a lea instruction */ COSTS_N_INSNS (1), /* cost of a lea instruction */
3, /* variable shift costs */ COSTS_N_INSNS (3), /* variable shift costs */
2, /* constant shift costs */ COSTS_N_INSNS (2), /* constant shift costs */
{12, 12, 12, 12, 12}, /* cost of starting a multiply */ {COSTS_N_INSNS (12), /* cost of starting multiply for QI */
COSTS_N_INSNS (12), /* HI */
COSTS_N_INSNS (12), /* SI */
COSTS_N_INSNS (12), /* DI */
COSTS_N_INSNS (12)}, /* other */
1, /* cost of multiply per each bit set */ 1, /* cost of multiply per each bit set */
{40, 40, 40, 40, 40}, /* cost of a divide/mod */ {COSTS_N_INSNS (40), /* cost of a divide/mod for QI */
3, /* cost of movsx */ COSTS_N_INSNS (40), /* HI */
2, /* cost of movzx */ COSTS_N_INSNS (40), /* SI */
COSTS_N_INSNS (40), /* DI */
COSTS_N_INSNS (40)}, /* other */
COSTS_N_INSNS (3), /* cost of movsx */
COSTS_N_INSNS (2), /* cost of movzx */
15, /* "large" insn */ 15, /* "large" insn */
3, /* MOVE_RATIO */ 3, /* MOVE_RATIO */
4, /* cost for loading QImode using movzbl */ 4, /* cost for loading QImode using movzbl */
...@@ -188,25 +212,33 @@ struct processor_costs i486_cost = { /* 486 specific costs */ ...@@ -188,25 +212,33 @@ struct processor_costs i486_cost = { /* 486 specific costs */
0, /* size of prefetch block */ 0, /* size of prefetch block */
0, /* number of parallel prefetches */ 0, /* number of parallel prefetches */
1, /* Branch cost */ 1, /* Branch cost */
8, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (8), /* cost of FADD and FSUB insns. */
16, /* cost of FMUL instruction. */ COSTS_N_INSNS (16), /* cost of FMUL instruction. */
73, /* cost of FDIV instruction. */ COSTS_N_INSNS (73), /* cost of FDIV instruction. */
3, /* cost of FABS instruction. */ COSTS_N_INSNS (3), /* cost of FABS instruction. */
3, /* cost of FCHS instruction. */ COSTS_N_INSNS (3), /* cost of FCHS instruction. */
83, /* cost of FSQRT instruction. */ COSTS_N_INSNS (83), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs pentium_cost = { struct processor_costs pentium_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
1, /* cost of a lea instruction */ COSTS_N_INSNS (1), /* cost of a lea instruction */
4, /* variable shift costs */ COSTS_N_INSNS (4), /* variable shift costs */
1, /* constant shift costs */ COSTS_N_INSNS (1), /* constant shift costs */
{11, 11, 11, 11, 11}, /* cost of starting a multiply */ {COSTS_N_INSNS (11), /* cost of starting multiply for QI */
COSTS_N_INSNS (11), /* HI */
COSTS_N_INSNS (11), /* SI */
COSTS_N_INSNS (11), /* DI */
COSTS_N_INSNS (11)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{25, 25, 25, 25, 25}, /* cost of a divide/mod */ {COSTS_N_INSNS (25), /* cost of a divide/mod for QI */
3, /* cost of movsx */ COSTS_N_INSNS (25), /* HI */
2, /* cost of movzx */ COSTS_N_INSNS (25), /* SI */
COSTS_N_INSNS (25), /* DI */
COSTS_N_INSNS (25)}, /* other */
COSTS_N_INSNS (3), /* cost of movsx */
COSTS_N_INSNS (2), /* cost of movzx */
8, /* "large" insn */ 8, /* "large" insn */
6, /* MOVE_RATIO */ 6, /* MOVE_RATIO */
6, /* cost for loading QImode using movzbl */ 6, /* cost for loading QImode using movzbl */
...@@ -232,25 +264,33 @@ struct processor_costs pentium_cost = { ...@@ -232,25 +264,33 @@ struct processor_costs pentium_cost = {
0, /* size of prefetch block */ 0, /* size of prefetch block */
0, /* number of parallel prefetches */ 0, /* number of parallel prefetches */
2, /* Branch cost */ 2, /* Branch cost */
3, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (3), /* cost of FADD and FSUB insns. */
3, /* cost of FMUL instruction. */ COSTS_N_INSNS (3), /* cost of FMUL instruction. */
39, /* cost of FDIV instruction. */ COSTS_N_INSNS (39), /* cost of FDIV instruction. */
1, /* cost of FABS instruction. */ COSTS_N_INSNS (1), /* cost of FABS instruction. */
1, /* cost of FCHS instruction. */ COSTS_N_INSNS (1), /* cost of FCHS instruction. */
70, /* cost of FSQRT instruction. */ COSTS_N_INSNS (70), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs pentiumpro_cost = { struct processor_costs pentiumpro_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
1, /* cost of a lea instruction */ COSTS_N_INSNS (1), /* cost of a lea instruction */
1, /* variable shift costs */ COSTS_N_INSNS (1), /* variable shift costs */
1, /* constant shift costs */ COSTS_N_INSNS (1), /* constant shift costs */
{4, 4, 4, 4, 4}, /* cost of starting a multiply */ {COSTS_N_INSNS (4), /* cost of starting multiply for QI */
COSTS_N_INSNS (4), /* HI */
COSTS_N_INSNS (4), /* SI */
COSTS_N_INSNS (4), /* DI */
COSTS_N_INSNS (4)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{17, 17, 17, 17, 17}, /* cost of a divide/mod */ {COSTS_N_INSNS (17), /* cost of a divide/mod for QI */
1, /* cost of movsx */ COSTS_N_INSNS (17), /* HI */
1, /* cost of movzx */ COSTS_N_INSNS (17), /* SI */
COSTS_N_INSNS (17), /* DI */
COSTS_N_INSNS (17)}, /* other */
COSTS_N_INSNS (1), /* cost of movsx */
COSTS_N_INSNS (1), /* cost of movzx */
8, /* "large" insn */ 8, /* "large" insn */
6, /* MOVE_RATIO */ 6, /* MOVE_RATIO */
2, /* cost for loading QImode using movzbl */ 2, /* cost for loading QImode using movzbl */
...@@ -276,25 +316,33 @@ struct processor_costs pentiumpro_cost = { ...@@ -276,25 +316,33 @@ struct processor_costs pentiumpro_cost = {
32, /* size of prefetch block */ 32, /* size of prefetch block */
6, /* number of parallel prefetches */ 6, /* number of parallel prefetches */
2, /* Branch cost */ 2, /* Branch cost */
3, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (3), /* cost of FADD and FSUB insns. */
5, /* cost of FMUL instruction. */ COSTS_N_INSNS (5), /* cost of FMUL instruction. */
56, /* cost of FDIV instruction. */ COSTS_N_INSNS (56), /* cost of FDIV instruction. */
2, /* cost of FABS instruction. */ COSTS_N_INSNS (2), /* cost of FABS instruction. */
2, /* cost of FCHS instruction. */ COSTS_N_INSNS (2), /* cost of FCHS instruction. */
56, /* cost of FSQRT instruction. */ COSTS_N_INSNS (56), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs k6_cost = { struct processor_costs k6_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
2, /* cost of a lea instruction */ COSTS_N_INSNS (2), /* cost of a lea instruction */
1, /* variable shift costs */ COSTS_N_INSNS (1), /* variable shift costs */
1, /* constant shift costs */ COSTS_N_INSNS (1), /* constant shift costs */
{3, 3, 3, 3, 3}, /* cost of starting a multiply */ {COSTS_N_INSNS (3), /* cost of starting multiply for QI */
COSTS_N_INSNS (3), /* HI */
COSTS_N_INSNS (3), /* SI */
COSTS_N_INSNS (3), /* DI */
COSTS_N_INSNS (3)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{18, 18, 18, 18, 18}, /* cost of a divide/mod */ {COSTS_N_INSNS (18), /* cost of a divide/mod for QI */
2, /* cost of movsx */ COSTS_N_INSNS (18), /* HI */
2, /* cost of movzx */ COSTS_N_INSNS (18), /* SI */
COSTS_N_INSNS (18), /* DI */
COSTS_N_INSNS (18)}, /* other */
COSTS_N_INSNS (2), /* cost of movsx */
COSTS_N_INSNS (2), /* cost of movzx */
8, /* "large" insn */ 8, /* "large" insn */
4, /* MOVE_RATIO */ 4, /* MOVE_RATIO */
3, /* cost for loading QImode using movzbl */ 3, /* cost for loading QImode using movzbl */
...@@ -320,25 +368,33 @@ struct processor_costs k6_cost = { ...@@ -320,25 +368,33 @@ struct processor_costs k6_cost = {
32, /* size of prefetch block */ 32, /* size of prefetch block */
1, /* number of parallel prefetches */ 1, /* number of parallel prefetches */
1, /* Branch cost */ 1, /* Branch cost */
2, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (2), /* cost of FADD and FSUB insns. */
2, /* cost of FMUL instruction. */ COSTS_N_INSNS (2), /* cost of FMUL instruction. */
56, /* cost of FDIV instruction. */ COSTS_N_INSNS (56), /* cost of FDIV instruction. */
2, /* cost of FABS instruction. */ COSTS_N_INSNS (2), /* cost of FABS instruction. */
2, /* cost of FCHS instruction. */ COSTS_N_INSNS (2), /* cost of FCHS instruction. */
56, /* cost of FSQRT instruction. */ COSTS_N_INSNS (56), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs athlon_cost = { struct processor_costs athlon_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
2, /* cost of a lea instruction */ COSTS_N_INSNS (2), /* cost of a lea instruction */
1, /* variable shift costs */ COSTS_N_INSNS (1), /* variable shift costs */
1, /* constant shift costs */ COSTS_N_INSNS (1), /* constant shift costs */
{5, 5, 5, 5, 5}, /* cost of starting a multiply */ {COSTS_N_INSNS (5), /* cost of starting multiply for QI */
COSTS_N_INSNS (5), /* HI */
COSTS_N_INSNS (5), /* SI */
COSTS_N_INSNS (5), /* DI */
COSTS_N_INSNS (5)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{18, 26, 42, 74, 74}, /* cost of a divide/mod */ {COSTS_N_INSNS (18), /* cost of a divide/mod for QI */
1, /* cost of movsx */ COSTS_N_INSNS (26), /* HI */
1, /* cost of movzx */ COSTS_N_INSNS (42), /* SI */
COSTS_N_INSNS (74), /* DI */
COSTS_N_INSNS (74)}, /* other */
COSTS_N_INSNS (1), /* cost of movsx */
COSTS_N_INSNS (1), /* cost of movzx */
8, /* "large" insn */ 8, /* "large" insn */
9, /* MOVE_RATIO */ 9, /* MOVE_RATIO */
4, /* cost for loading QImode using movzbl */ 4, /* cost for loading QImode using movzbl */
...@@ -364,25 +420,33 @@ struct processor_costs athlon_cost = { ...@@ -364,25 +420,33 @@ struct processor_costs athlon_cost = {
64, /* size of prefetch block */ 64, /* size of prefetch block */
6, /* number of parallel prefetches */ 6, /* number of parallel prefetches */
5, /* Branch cost */ 5, /* Branch cost */
4, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (4), /* cost of FADD and FSUB insns. */
4, /* cost of FMUL instruction. */ COSTS_N_INSNS (4), /* cost of FMUL instruction. */
24, /* cost of FDIV instruction. */ COSTS_N_INSNS (24), /* cost of FDIV instruction. */
2, /* cost of FABS instruction. */ COSTS_N_INSNS (2), /* cost of FABS instruction. */
2, /* cost of FCHS instruction. */ COSTS_N_INSNS (2), /* cost of FCHS instruction. */
35, /* cost of FSQRT instruction. */ COSTS_N_INSNS (35), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs k8_cost = { struct processor_costs k8_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
2, /* cost of a lea instruction */ COSTS_N_INSNS (2), /* cost of a lea instruction */
1, /* variable shift costs */ COSTS_N_INSNS (1), /* variable shift costs */
1, /* constant shift costs */ COSTS_N_INSNS (1), /* constant shift costs */
{3, 4, 3, 4, 5}, /* cost of starting a multiply */ {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 */ 0, /* cost of multiply per each bit set */
{18, 26, 42, 74, 74}, /* cost of a divide/mod */ {COSTS_N_INSNS (18), /* cost of a divide/mod for QI */
1, /* cost of movsx */ COSTS_N_INSNS (26), /* HI */
1, /* cost of movzx */ COSTS_N_INSNS (42), /* SI */
COSTS_N_INSNS (74), /* DI */
COSTS_N_INSNS (74)}, /* other */
COSTS_N_INSNS (1), /* cost of movsx */
COSTS_N_INSNS (1), /* cost of movzx */
8, /* "large" insn */ 8, /* "large" insn */
9, /* MOVE_RATIO */ 9, /* MOVE_RATIO */
4, /* cost for loading QImode using movzbl */ 4, /* cost for loading QImode using movzbl */
...@@ -408,25 +472,33 @@ struct processor_costs k8_cost = { ...@@ -408,25 +472,33 @@ struct processor_costs k8_cost = {
64, /* size of prefetch block */ 64, /* size of prefetch block */
6, /* number of parallel prefetches */ 6, /* number of parallel prefetches */
5, /* Branch cost */ 5, /* Branch cost */
4, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (4), /* cost of FADD and FSUB insns. */
4, /* cost of FMUL instruction. */ COSTS_N_INSNS (4), /* cost of FMUL instruction. */
19, /* cost of FDIV instruction. */ COSTS_N_INSNS (19), /* cost of FDIV instruction. */
2, /* cost of FABS instruction. */ COSTS_N_INSNS (2), /* cost of FABS instruction. */
2, /* cost of FCHS instruction. */ COSTS_N_INSNS (2), /* cost of FCHS instruction. */
35, /* cost of FSQRT instruction. */ COSTS_N_INSNS (35), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs pentium4_cost = { struct processor_costs pentium4_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
3, /* cost of a lea instruction */ COSTS_N_INSNS (3), /* cost of a lea instruction */
4, /* variable shift costs */ COSTS_N_INSNS (4), /* variable shift costs */
4, /* constant shift costs */ COSTS_N_INSNS (4), /* constant shift costs */
{15, 15, 15, 15, 15}, /* cost of starting a multiply */ {COSTS_N_INSNS (15), /* cost of starting multiply for QI */
COSTS_N_INSNS (15), /* HI */
COSTS_N_INSNS (15), /* SI */
COSTS_N_INSNS (15), /* DI */
COSTS_N_INSNS (15)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{56, 56, 56, 56, 56}, /* cost of a divide/mod */ {COSTS_N_INSNS (56), /* cost of a divide/mod for QI */
1, /* cost of movsx */ COSTS_N_INSNS (56), /* HI */
1, /* cost of movzx */ COSTS_N_INSNS (56), /* SI */
COSTS_N_INSNS (56), /* DI */
COSTS_N_INSNS (56)}, /* other */
COSTS_N_INSNS (1), /* cost of movsx */
COSTS_N_INSNS (1), /* cost of movzx */
16, /* "large" insn */ 16, /* "large" insn */
6, /* MOVE_RATIO */ 6, /* MOVE_RATIO */
2, /* cost for loading QImode using movzbl */ 2, /* cost for loading QImode using movzbl */
...@@ -452,25 +524,33 @@ struct processor_costs pentium4_cost = { ...@@ -452,25 +524,33 @@ struct processor_costs pentium4_cost = {
64, /* size of prefetch block */ 64, /* size of prefetch block */
6, /* number of parallel prefetches */ 6, /* number of parallel prefetches */
2, /* Branch cost */ 2, /* Branch cost */
5, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (5), /* cost of FADD and FSUB insns. */
7, /* cost of FMUL instruction. */ COSTS_N_INSNS (7), /* cost of FMUL instruction. */
43, /* cost of FDIV instruction. */ COSTS_N_INSNS (43), /* cost of FDIV instruction. */
2, /* cost of FABS instruction. */ COSTS_N_INSNS (2), /* cost of FABS instruction. */
2, /* cost of FCHS instruction. */ COSTS_N_INSNS (2), /* cost of FCHS instruction. */
43, /* cost of FSQRT instruction. */ COSTS_N_INSNS (43), /* cost of FSQRT instruction. */
}; };
static const static const
struct processor_costs nocona_cost = { struct processor_costs nocona_cost = {
1, /* cost of an add instruction */ COSTS_N_INSNS (1), /* cost of an add instruction */
1, /* cost of a lea instruction */ COSTS_N_INSNS (1), /* cost of a lea instruction */
1, /* variable shift costs */ COSTS_N_INSNS (1), /* variable shift costs */
1, /* constant shift costs */ COSTS_N_INSNS (1), /* constant shift costs */
{10, 10, 10, 10, 10}, /* cost of starting a multiply */ {COSTS_N_INSNS (10), /* cost of starting multiply for QI */
COSTS_N_INSNS (10), /* HI */
COSTS_N_INSNS (10), /* SI */
COSTS_N_INSNS (10), /* DI */
COSTS_N_INSNS (10)}, /* other */
0, /* cost of multiply per each bit set */ 0, /* cost of multiply per each bit set */
{66, 66, 66, 66, 66}, /* cost of a divide/mod */ {COSTS_N_INSNS (66), /* cost of a divide/mod for QI */
1, /* cost of movsx */ COSTS_N_INSNS (66), /* HI */
1, /* cost of movzx */ COSTS_N_INSNS (66), /* SI */
COSTS_N_INSNS (66), /* DI */
COSTS_N_INSNS (66)}, /* other */
COSTS_N_INSNS (1), /* cost of movsx */
COSTS_N_INSNS (1), /* cost of movzx */
16, /* "large" insn */ 16, /* "large" insn */
17, /* MOVE_RATIO */ 17, /* MOVE_RATIO */
4, /* cost for loading QImode using movzbl */ 4, /* cost for loading QImode using movzbl */
...@@ -496,12 +576,12 @@ struct processor_costs nocona_cost = { ...@@ -496,12 +576,12 @@ struct processor_costs nocona_cost = {
128, /* size of prefetch block */ 128, /* size of prefetch block */
8, /* number of parallel prefetches */ 8, /* number of parallel prefetches */
1, /* Branch cost */ 1, /* Branch cost */
6, /* cost of FADD and FSUB insns. */ COSTS_N_INSNS (6), /* cost of FADD and FSUB insns. */
8, /* cost of FMUL instruction. */ COSTS_N_INSNS (8), /* cost of FMUL instruction. */
40, /* cost of FDIV instruction. */ COSTS_N_INSNS (40), /* cost of FDIV instruction. */
3, /* cost of FABS instruction. */ COSTS_N_INSNS (3), /* cost of FABS instruction. */
3, /* cost of FCHS instruction. */ COSTS_N_INSNS (3), /* cost of FCHS instruction. */
44, /* cost of FSQRT instruction. */ COSTS_N_INSNS (44), /* cost of FSQRT instruction. */
}; };
const struct processor_costs *ix86_cost = &pentium_cost; const struct processor_costs *ix86_cost = &pentium_cost;
...@@ -16320,13 +16400,13 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16320,13 +16400,13 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
&& GET_MODE (XEXP (x, 0)) == SImode) && GET_MODE (XEXP (x, 0)) == SImode)
*total = 1; *total = 1;
else if (TARGET_ZERO_EXTEND_WITH_AND) else if (TARGET_ZERO_EXTEND_WITH_AND)
*total = COSTS_N_INSNS (ix86_cost->add); *total = ix86_cost->add;
else else
*total = COSTS_N_INSNS (ix86_cost->movzx); *total = ix86_cost->movzx;
return false; return false;
case SIGN_EXTEND: case SIGN_EXTEND:
*total = COSTS_N_INSNS (ix86_cost->movsx); *total = ix86_cost->movsx;
return false; return false;
case ASHIFT: case ASHIFT:
...@@ -16336,13 +16416,14 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16336,13 +16416,14 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
HOST_WIDE_INT value = INTVAL (XEXP (x, 1)); HOST_WIDE_INT value = INTVAL (XEXP (x, 1));
if (value == 1) if (value == 1)
{ {
*total = COSTS_N_INSNS (ix86_cost->add); *total = ix86_cost->add;
return false; return false;
} }
if ((value == 2 || value == 3) if ((value == 2 || value == 3)
&& !TARGET_DECOMPOSE_LEA
&& ix86_cost->lea <= ix86_cost->shift_const) && ix86_cost->lea <= ix86_cost->shift_const)
{ {
*total = COSTS_N_INSNS (ix86_cost->lea); *total = ix86_cost->lea;
return false; return false;
} }
} }
...@@ -16357,31 +16438,31 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16357,31 +16438,31 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
if (GET_CODE (XEXP (x, 1)) == CONST_INT) if (GET_CODE (XEXP (x, 1)) == CONST_INT)
{ {
if (INTVAL (XEXP (x, 1)) > 32) if (INTVAL (XEXP (x, 1)) > 32)
*total = COSTS_N_INSNS(ix86_cost->shift_const + 2); *total = ix86_cost->shift_const + COSTS_N_INSNS (2);
else else
*total = COSTS_N_INSNS(ix86_cost->shift_const * 2); *total = ix86_cost->shift_const * 2;
} }
else else
{ {
if (GET_CODE (XEXP (x, 1)) == AND) if (GET_CODE (XEXP (x, 1)) == AND)
*total = COSTS_N_INSNS(ix86_cost->shift_var * 2); *total = ix86_cost->shift_var * 2;
else else
*total = COSTS_N_INSNS(ix86_cost->shift_var * 6 + 2); *total = ix86_cost->shift_var * 6 + COSTS_N_INSNS (2);
} }
} }
else else
{ {
if (GET_CODE (XEXP (x, 1)) == CONST_INT) if (GET_CODE (XEXP (x, 1)) == CONST_INT)
*total = COSTS_N_INSNS (ix86_cost->shift_const); *total = ix86_cost->shift_const;
else else
*total = COSTS_N_INSNS (ix86_cost->shift_var); *total = ix86_cost->shift_var;
} }
return false; return false;
case MULT: case MULT:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
{ {
*total = COSTS_N_INSNS (ix86_cost->fmul); *total = ix86_cost->fmul;
return false; return false;
} }
else else
...@@ -16422,9 +16503,9 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16422,9 +16503,9 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
op0 = XEXP (op0, 0), mode = GET_MODE (op0); op0 = XEXP (op0, 0), mode = GET_MODE (op0);
} }
*total = COSTS_N_INSNS (ix86_cost->mult_init[MODE_INDEX (mode)] *total = (ix86_cost->mult_init[MODE_INDEX (mode)]
+ nbits * ix86_cost->mult_bit) + nbits * ix86_cost->mult_bit
+ rtx_cost (op0, outer_code) + rtx_cost (op1, outer_code); + rtx_cost (op0, outer_code) + rtx_cost (op1, outer_code));
return true; return true;
} }
...@@ -16434,14 +16515,14 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16434,14 +16515,14 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
case MOD: case MOD:
case UMOD: case UMOD:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
*total = COSTS_N_INSNS (ix86_cost->fdiv); *total = ix86_cost->fdiv;
else else
*total = COSTS_N_INSNS (ix86_cost->divide[MODE_INDEX (mode)]); *total = ix86_cost->divide[MODE_INDEX (mode)];
return false; return false;
case PLUS: case PLUS:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
*total = COSTS_N_INSNS (ix86_cost->fadd); *total = ix86_cost->fadd;
else if (GET_MODE_CLASS (mode) == MODE_INT else if (GET_MODE_CLASS (mode) == MODE_INT
&& GET_MODE_BITSIZE (mode) <= GET_MODE_BITSIZE (Pmode)) && GET_MODE_BITSIZE (mode) <= GET_MODE_BITSIZE (Pmode))
{ {
...@@ -16453,7 +16534,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16453,7 +16534,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
HOST_WIDE_INT val = INTVAL (XEXP (XEXP (XEXP (x, 0), 0), 1)); HOST_WIDE_INT val = INTVAL (XEXP (XEXP (XEXP (x, 0), 0), 1));
if (val == 2 || val == 4 || val == 8) if (val == 2 || val == 4 || val == 8)
{ {
*total = COSTS_N_INSNS (ix86_cost->lea); *total = ix86_cost->lea;
*total += rtx_cost (XEXP (XEXP (x, 0), 1), outer_code); *total += rtx_cost (XEXP (XEXP (x, 0), 1), outer_code);
*total += rtx_cost (XEXP (XEXP (XEXP (x, 0), 0), 0), *total += rtx_cost (XEXP (XEXP (XEXP (x, 0), 0), 0),
outer_code); outer_code);
...@@ -16467,7 +16548,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16467,7 +16548,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
HOST_WIDE_INT val = INTVAL (XEXP (XEXP (x, 0), 1)); HOST_WIDE_INT val = INTVAL (XEXP (XEXP (x, 0), 1));
if (val == 2 || val == 4 || val == 8) if (val == 2 || val == 4 || val == 8)
{ {
*total = COSTS_N_INSNS (ix86_cost->lea); *total = ix86_cost->lea;
*total += rtx_cost (XEXP (XEXP (x, 0), 0), outer_code); *total += rtx_cost (XEXP (XEXP (x, 0), 0), outer_code);
*total += rtx_cost (XEXP (x, 1), outer_code); *total += rtx_cost (XEXP (x, 1), outer_code);
return true; return true;
...@@ -16475,7 +16556,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16475,7 +16556,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
} }
else if (GET_CODE (XEXP (x, 0)) == PLUS) else if (GET_CODE (XEXP (x, 0)) == PLUS)
{ {
*total = COSTS_N_INSNS (ix86_cost->lea); *total = ix86_cost->lea;
*total += rtx_cost (XEXP (XEXP (x, 0), 0), outer_code); *total += rtx_cost (XEXP (XEXP (x, 0), 0), outer_code);
*total += rtx_cost (XEXP (XEXP (x, 0), 1), outer_code); *total += rtx_cost (XEXP (XEXP (x, 0), 1), outer_code);
*total += rtx_cost (XEXP (x, 1), outer_code); *total += rtx_cost (XEXP (x, 1), outer_code);
...@@ -16487,7 +16568,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16487,7 +16568,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
case MINUS: case MINUS:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
{ {
*total = COSTS_N_INSNS (ix86_cost->fadd); *total = ix86_cost->fadd;
return false; return false;
} }
/* FALLTHRU */ /* FALLTHRU */
...@@ -16497,7 +16578,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16497,7 +16578,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
case XOR: case XOR:
if (!TARGET_64BIT && mode == DImode) if (!TARGET_64BIT && mode == DImode)
{ {
*total = (COSTS_N_INSNS (ix86_cost->add) * 2 *total = (ix86_cost->add * 2
+ (rtx_cost (XEXP (x, 0), outer_code) + (rtx_cost (XEXP (x, 0), outer_code)
<< (GET_MODE (XEXP (x, 0)) != DImode)) << (GET_MODE (XEXP (x, 0)) != DImode))
+ (rtx_cost (XEXP (x, 1), outer_code) + (rtx_cost (XEXP (x, 1), outer_code)
...@@ -16509,16 +16590,16 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16509,16 +16590,16 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
case NEG: case NEG:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
{ {
*total = COSTS_N_INSNS (ix86_cost->fchs); *total = ix86_cost->fchs;
return false; return false;
} }
/* FALLTHRU */ /* FALLTHRU */
case NOT: case NOT:
if (!TARGET_64BIT && mode == DImode) if (!TARGET_64BIT && mode == DImode)
*total = COSTS_N_INSNS (ix86_cost->add * 2); *total = ix86_cost->add * 2;
else else
*total = COSTS_N_INSNS (ix86_cost->add); *total = ix86_cost->add;
return false; return false;
case COMPARE: case COMPARE:
...@@ -16529,7 +16610,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16529,7 +16610,7 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
{ {
/* This kind of construct is implemented using test[bwl]. /* This kind of construct is implemented using test[bwl].
Treat it as if we had an AND. */ Treat it as if we had an AND. */
*total = (COSTS_N_INSNS (ix86_cost->add) *total = (ix86_cost->add
+ rtx_cost (XEXP (XEXP (x, 0), 0), outer_code) + rtx_cost (XEXP (XEXP (x, 0), 0), outer_code)
+ rtx_cost (const1_rtx, outer_code)); + rtx_cost (const1_rtx, outer_code));
return true; return true;
...@@ -16545,12 +16626,12 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total) ...@@ -16545,12 +16626,12 @@ ix86_rtx_costs (rtx x, int code, int outer_code, int *total)
case ABS: case ABS:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
*total = COSTS_N_INSNS (ix86_cost->fabs); *total = ix86_cost->fabs;
return false; return false;
case SQRT: case SQRT:
if (FLOAT_MODE_P (mode)) if (FLOAT_MODE_P (mode))
*total = COSTS_N_INSNS (ix86_cost->fsqrt); *total = ix86_cost->fsqrt;
return false; return false;
case UNSPEC: case UNSPEC:
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment