target/i386: use compiler builtin to compute PF
This removes the 256 byte parity table from the executable. Suggested-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Paolo Bonzini
parent
46c04e4bcf
commit
24899cdcd2
@ -313,6 +313,15 @@ static inline int ctpop8(uint8_t val)
|
||||
return __builtin_popcount(val);
|
||||
}
|
||||
|
||||
/*
|
||||
* parity8 - return the parity (1 = odd) of an 8-bit value.
|
||||
* @val: The value to search
|
||||
*/
|
||||
static inline int parity8(uint8_t val)
|
||||
{
|
||||
return __builtin_parity(val);
|
||||
}
|
||||
|
||||
/**
|
||||
* ctpop16 - count the population of one bits in a 16-bit value.
|
||||
* @val: The value to search
|
||||
|
||||
@ -22,41 +22,6 @@
|
||||
#include "exec/helper-proto.h"
|
||||
#include "helper-tcg.h"
|
||||
|
||||
const uint8_t parity_table[256] = {
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
CC_P, 0, 0, CC_P, 0, CC_P, CC_P, 0,
|
||||
0, CC_P, CC_P, 0, CC_P, 0, 0, CC_P,
|
||||
};
|
||||
|
||||
#define SHIFT 0
|
||||
#include "cc_helper_template.h.inc"
|
||||
#undef SHIFT
|
||||
|
||||
@ -45,7 +45,7 @@ static uint32_t glue(compute_all_add, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1)
|
||||
DATA_TYPE src2 = dst - src1;
|
||||
|
||||
cf = dst < src1;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = (dst ^ src1 ^ src2) & CC_A;
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -65,7 +65,7 @@ static uint32_t glue(compute_all_adc, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1,
|
||||
DATA_TYPE src2 = dst - src1 - src3;
|
||||
|
||||
cf = (src3 ? dst <= src1 : dst < src1);
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = (dst ^ src1 ^ src2) & 0x10;
|
||||
zf = (dst == 0) << 6;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & 0x80;
|
||||
@ -85,7 +85,7 @@ static uint32_t glue(compute_all_sub, SUFFIX)(DATA_TYPE dst, DATA_TYPE src2)
|
||||
DATA_TYPE src1 = dst + src2;
|
||||
|
||||
cf = src1 < src2;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = (dst ^ src1 ^ src2) & CC_A;
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -107,7 +107,7 @@ static uint32_t glue(compute_all_sbb, SUFFIX)(DATA_TYPE dst, DATA_TYPE src2,
|
||||
DATA_TYPE src1 = dst + src2 + src3;
|
||||
|
||||
cf = (src3 ? src1 <= src2 : src1 < src2);
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = (dst ^ src1 ^ src2) & 0x10;
|
||||
zf = (dst == 0) << 6;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & 0x80;
|
||||
@ -128,7 +128,7 @@ static uint32_t glue(compute_all_logic, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1)
|
||||
uint32_t cf, pf, af, zf, sf, of;
|
||||
|
||||
cf = 0;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = 0;
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -144,7 +144,7 @@ static uint32_t glue(compute_all_inc, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1)
|
||||
cf = src1;
|
||||
src1 = dst - 1;
|
||||
src2 = 1;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = (dst ^ src1 ^ src2) & CC_A;
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -160,7 +160,7 @@ static uint32_t glue(compute_all_dec, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1)
|
||||
cf = src1;
|
||||
src1 = dst + 1;
|
||||
src2 = 1;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = (dst ^ src1 ^ src2) & CC_A;
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -173,7 +173,7 @@ static uint32_t glue(compute_all_shl, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1)
|
||||
uint32_t cf, pf, af, zf, sf, of;
|
||||
|
||||
cf = (src1 >> (DATA_BITS - 1)) & CC_C;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = 0; /* undefined */
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -192,7 +192,7 @@ static uint32_t glue(compute_all_sar, SUFFIX)(DATA_TYPE dst, DATA_TYPE src1)
|
||||
uint32_t cf, pf, af, zf, sf, of;
|
||||
|
||||
cf = src1 & 1;
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = 0; /* undefined */
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
@ -209,7 +209,7 @@ static uint32_t glue(compute_all_mul, SUFFIX)(DATA_TYPE dst, target_long src1)
|
||||
uint32_t cf, pf, af, zf, sf, of;
|
||||
|
||||
cf = (src1 != 0);
|
||||
pf = parity_table[(uint8_t)dst];
|
||||
pf = compute_pf(dst);
|
||||
af = 0; /* undefined */
|
||||
zf = (dst == 0) * CC_Z;
|
||||
sf = lshift(dst, 8 - DATA_BITS) & CC_S;
|
||||
|
||||
@ -21,6 +21,7 @@
|
||||
#define I386_HELPER_TCG_H
|
||||
|
||||
#include "exec/exec-all.h"
|
||||
#include "qemu/host-utils.h"
|
||||
|
||||
/* Maximum instruction code size */
|
||||
#define TARGET_MAX_INSN_SIZE 16
|
||||
@ -87,7 +88,10 @@ G_NORETURN void x86_cpu_do_unaligned_access(CPUState *cs, vaddr vaddr,
|
||||
#endif
|
||||
|
||||
/* cc_helper.c */
|
||||
extern const uint8_t parity_table[256];
|
||||
static inline unsigned int compute_pf(uint8_t x)
|
||||
{
|
||||
return !parity8(x) * CC_P;
|
||||
}
|
||||
|
||||
/* misc_helper.c */
|
||||
void cpu_load_eflags(CPUX86State *env, int eflags, int update_mask);
|
||||
|
||||
@ -237,7 +237,7 @@ void helper_daa(CPUX86State *env)
|
||||
env->regs[R_EAX] = (env->regs[R_EAX] & ~0xff) | al;
|
||||
/* well, speed is not an issue here, so we compute the flags by hand */
|
||||
eflags |= (al == 0) << 6; /* zf */
|
||||
eflags |= parity_table[al]; /* pf */
|
||||
eflags |= compute_pf(al);
|
||||
eflags |= (al & 0x80); /* sf */
|
||||
CC_SRC = eflags;
|
||||
CC_OP = CC_OP_EFLAGS;
|
||||
@ -269,7 +269,7 @@ void helper_das(CPUX86State *env)
|
||||
env->regs[R_EAX] = (env->regs[R_EAX] & ~0xff) | al;
|
||||
/* well, speed is not an issue here, so we compute the flags by hand */
|
||||
eflags |= (al == 0) << 6; /* zf */
|
||||
eflags |= parity_table[al]; /* pf */
|
||||
eflags |= compute_pf(al);
|
||||
eflags |= (al & 0x80); /* sf */
|
||||
CC_SRC = eflags;
|
||||
CC_OP = CC_OP_EFLAGS;
|
||||
|
||||
Loading…
Reference in New Issue
Block a user