On 8/28/2014 12:15 PM, Paolo Bonzini wrote:
> This makes comparisons much smaller and faster. The speedup is
> approximately 10% on user-mode emulation on x86 host, 3-4% on PPC.
>
> Note that CRF_* constants are flipped to match PowerPC's big
> bit-endianness. Previously, the CR register was effectively stored
> in mixed endianness, so now there is less indirection going on.
>
> Signed-off-by: Paolo Bonzini <pbonz...@redhat.com>
There are some issues with this patch -- it doesn't compile due to some typing
issues. There are also some functional issues. Some details are below
(nit) Also it doesnt pass checkpatch.pl.
> ---
> linux-user/main.c | 4 +-
> target-ppc/cpu.h | 33 ++++--
> target-ppc/fpu_helper.c | 39 ++----
> target-ppc/helper.h | 6 -
> target-ppc/int_helper.c | 2 +-
> target-ppc/machine.c | 9 ++
> target-ppc/translate.c | 307
> +++++++++++++++++++++++++-----------------------
> 7 files changed, 204 insertions(+), 196 deletions(-)
>
> diff --git a/linux-user/main.c b/linux-user/main.c
> index 152c031..b403f24 100644
> --- a/linux-user/main.c
> +++ b/linux-user/main.c
> @@ -1929,7 +1929,7 @@ void cpu_loop(CPUPPCState *env)
> * PPC ABI uses overflow flag in cr0 to signal an error
> * in syscalls.
> */
> - env->crf[0] &= ~0x1;
> + env->cr[CRF_SO] = 0;
> ret = do_syscall(env, env->gpr[0], env->gpr[3], env->gpr[4],
> env->gpr[5], env->gpr[6], env->gpr[7],
> env->gpr[8], 0, 0);
> @@ -1939,7 +1939,7 @@ void cpu_loop(CPUPPCState *env)
> break;
> }
> if (ret > (target_ulong)(-515)) {
> - env->crf[0] |= 0x1;
> + env->cr[CRF_SO] = 1;
> ret = -ret;
> }
> env->gpr[3] = ret;
> diff --git a/target-ppc/cpu.h b/target-ppc/cpu.h
> index 05c29b2..67510e8 100644
> --- a/target-ppc/cpu.h
> +++ b/target-ppc/cpu.h
> @@ -939,7 +939,7 @@ struct CPUPPCState {
> /* CTR */
> target_ulong ctr;
> /* condition register */
> - uint32_t crf[8];
> + uint32_t cr[32];
> #if defined(TARGET_PPC64)
> /* CFAR */
> target_ulong cfar;
> @@ -1058,6 +1058,9 @@ struct CPUPPCState {
> uint64_t dtl_addr, dtl_size;
> #endif /* TARGET_PPC64 */
>
> + /* condition register, for migration compatibility */
> + uint32_t crf[8];
> +
> int error_code;
> uint32_t pending_interrupts;
> #if !defined(CONFIG_USER_ONLY)
> @@ -1200,12 +1203,20 @@ void store_fpscr(CPUPPCState *env, uint64_t arg,
> uint32_t mask);
>
> static inline uint32_t ppc_get_crf(const CPUPPCState *env, int i)
> {
> - return env->crf[i];
> + uint32_t r;
> + r = env->cr[i * 4];
> + r = (r << 1) | (env->cr[i * 4 + 1]);
> + r = (r << 1) | (env->cr[i * 4 + 2]);
> + r = (r << 1) | (env->cr[i * 4 + 3]);
> + return r;
> }
>
> static inline void ppc_set_crf(CPUPPCState *env, int i, uint32_t val)
> {
> - env->crf[i] = val;
> + env->cr[i * 4 + 0] = (val & 0x08) != 0;
> + env->cr[i * 4 + 1] = (val & 0x04) != 0;
> + env->cr[i * 4 + 2] = (val & 0x02) != 0;
> + env->cr[i * 4 + 3] = (val & 0x01) != 0;
> }
>
> static inline uint64_t ppc_dump_gpr(CPUPPCState *env, int gprn)
> @@ -1256,14 +1267,14 @@ static inline int cpu_mmu_index (CPUPPCState *env)
>
>
> /*****************************************************************************/
> /* CRF definitions */
> -#define CRF_LT 3
> -#define CRF_GT 2
> -#define CRF_EQ 1
> -#define CRF_SO 0
> -#define CRF_CH (1 << CRF_LT)
> -#define CRF_CL (1 << CRF_GT)
> -#define CRF_CH_OR_CL (1 << CRF_EQ)
> -#define CRF_CH_AND_CL (1 << CRF_SO)
> +#define CRF_LT 0
> +#define CRF_GT 1
> +#define CRF_EQ 2
> +#define CRF_SO 3
> +#define CRF_CH CRF_LT
> +#define CRF_CL CRF_GT
> +#define CRF_CH_OR_CL CRF_EQ
> +#define CRF_CH_AND_CL CRF_SO
>
> /* XER definitions */
> #define XER_SO 31
> diff --git a/target-ppc/fpu_helper.c b/target-ppc/fpu_helper.c
> index 1ccbcf3..9574ebe 100644
> --- a/target-ppc/fpu_helper.c
> +++ b/target-ppc/fpu_helper.c
> @@ -1098,8 +1098,8 @@ void helper_fcmpu(CPUPPCState *env, uint64_t arg1,
> uint64_t arg2,
> }
>
> env->fpscr &= ~(0x0F << FPSCR_FPRF);
> - env->fpscr |= (0x01 << FPSCR_FPRF) << ret;
> - ppc_set_crf(env, crfD, 1 << ret);
> + env->fpscr |= (0x08 << FPSCR_FPRF) >> ret;
> + ppc_set_crf(env, crfD, 0x08 >> ret);
>
> if (unlikely(ret == CRF_SO
> && (float64_is_signaling_nan(farg1.d) ||
> @@ -1130,8 +1130,8 @@ void helper_fcmpo(CPUPPCState *env, uint64_t arg1,
> uint64_t arg2,
> }
>
> env->fpscr &= ~(0x0F << FPSCR_FPRF);
> - env->fpscr |= (0x01 << FPSCR_FPRF) << ret;
> - ppc_set_crf(env, crfD, 1 << ret);
> + env->fpscr |= (0x08 << FPSCR_FPRF) >> ret;
> + ppc_set_crf(env, crfD, 0x08 >> ret);
>
> if (unlikely(ret == CRF_SO)) {
> if (float64_is_signaling_nan(farg1.d) ||
> @@ -1403,7 +1403,7 @@ static inline uint32_t efscmplt(CPUPPCState *env,
> uint32_t op1, uint32_t op2)
>
> u1.l = op1;
> u2.l = op2;
> - return float32_lt(u1.f, u2.f, &env->vec_status) ? 4 : 0;
> + return float32_lt(u1.f, u2.f, &env->vec_status);
> }
>
> static inline uint32_t efscmpgt(CPUPPCState *env, uint32_t op1, uint32_t op2)
> @@ -1412,7 +1412,7 @@ static inline uint32_t efscmpgt(CPUPPCState *env,
> uint32_t op1, uint32_t op2)
>
> u1.l = op1;
> u2.l = op2;
> - return float32_le(u1.f, u2.f, &env->vec_status) ? 0 : 4;
> + return !float32_le(u1.f, u2.f, &env->vec_status);
> }
>
> static inline uint32_t efscmpeq(CPUPPCState *env, uint32_t op1, uint32_t op2)
> @@ -1421,7 +1421,7 @@ static inline uint32_t efscmpeq(CPUPPCState *env,
> uint32_t op1, uint32_t op2)
>
> u1.l = op1;
> u2.l = op2;
> - return float32_eq(u1.f, u2.f, &env->vec_status) ? 4 : 0;
> + return float32_eq(u1.f, u2.f, &env->vec_status);
> }
>
> static inline uint32_t efststlt(CPUPPCState *env, uint32_t op1, uint32_t op2)
> @@ -1465,25 +1465,6 @@ static inline uint32_t evcmp_merge(int t0, int t1)
> return (t0 << 3) | (t1 << 2) | ((t0 | t1) << 1) | (t0 & t1);
> }
>
> -#define HELPER_VECTOR_SPE_CMP(name) \
> - uint32_t helper_ev##name(CPUPPCState *env, uint64_t op1, uint64_t op2) \
> - { \
> - return evcmp_merge(e##name(env, op1 >> 32, op2 >> 32), \
> - e##name(env, op1, op2)); \
> - }
> -/* evfststlt */
> -HELPER_VECTOR_SPE_CMP(fststlt);
> -/* evfststgt */
> -HELPER_VECTOR_SPE_CMP(fststgt);
> -/* evfststeq */
> -HELPER_VECTOR_SPE_CMP(fststeq);
> -/* evfscmplt */
> -HELPER_VECTOR_SPE_CMP(fscmplt);
> -/* evfscmpgt */
> -HELPER_VECTOR_SPE_CMP(fscmpgt);
> -/* evfscmpeq */
> -HELPER_VECTOR_SPE_CMP(fscmpeq);
> -
> /* Double-precision floating-point conversion */
> uint64_t helper_efdcfsi(CPUPPCState *env, uint32_t val)
> {
> @@ -1725,7 +1706,7 @@ uint32_t helper_efdtstlt(CPUPPCState *env, uint64_t
> op1, uint64_t op2)
>
> u1.ll = op1;
> u2.ll = op2;
> - return float64_lt(u1.d, u2.d, &env->vec_status) ? 4 : 0;
> + return float64_lt(u1.d, u2.d, &env->vec_status);
> }
>
> uint32_t helper_efdtstgt(CPUPPCState *env, uint64_t op1, uint64_t op2)
> @@ -1734,7 +1715,7 @@ uint32_t helper_efdtstgt(CPUPPCState *env, uint64_t
> op1, uint64_t op2)
>
> u1.ll = op1;
> u2.ll = op2;
> - return float64_le(u1.d, u2.d, &env->vec_status) ? 0 : 4;
> + return !float64_le(u1.d, u2.d, &env->vec_status);
> }
>
> uint32_t helper_efdtsteq(CPUPPCState *env, uint64_t op1, uint64_t op2)
> @@ -1743,7 +1724,7 @@ uint32_t helper_efdtsteq(CPUPPCState *env, uint64_t
> op1, uint64_t op2)
>
> u1.ll = op1;
> u2.ll = op2;
> - return float64_eq_quiet(u1.d, u2.d, &env->vec_status) ? 4 : 0;
> + return float64_eq_quiet(u1.d, u2.d, &env->vec_status);
> }
>
> uint32_t helper_efdcmplt(CPUPPCState *env, uint64_t op1, uint64_t op2)
> diff --git a/target-ppc/helper.h b/target-ppc/helper.h
> index 5342f13..8d6a92b 100644
> --- a/target-ppc/helper.h
> +++ b/target-ppc/helper.h
> @@ -493,12 +493,6 @@ DEF_HELPER_3(efststeq, i32, env, i32, i32)
> DEF_HELPER_3(efscmplt, i32, env, i32, i32)
> DEF_HELPER_3(efscmpgt, i32, env, i32, i32)
> DEF_HELPER_3(efscmpeq, i32, env, i32, i32)
> -DEF_HELPER_3(evfststlt, i32, env, i64, i64)
> -DEF_HELPER_3(evfststgt, i32, env, i64, i64)
> -DEF_HELPER_3(evfststeq, i32, env, i64, i64)
> -DEF_HELPER_3(evfscmplt, i32, env, i64, i64)
> -DEF_HELPER_3(evfscmpgt, i32, env, i64, i64)
> -DEF_HELPER_3(evfscmpeq, i32, env, i64, i64)
> DEF_HELPER_2(efdcfsi, i64, env, i32)
> DEF_HELPER_2(efdcfsid, i64, env, i64)
> DEF_HELPER_2(efdcfui, i64, env, i32)
> diff --git a/target-ppc/int_helper.c b/target-ppc/int_helper.c
> index 2287064..d3ace6a 100644
> --- a/target-ppc/int_helper.c
> +++ b/target-ppc/int_helper.c
> @@ -2602,7 +2602,7 @@ target_ulong helper_dlmzb(CPUPPCState *env,
> target_ulong high,
> done:
> env->xer = (env->xer & ~0x7F) | i;
> if (update_Rc) {
> - env->crf[0] |= xer_so;
> + env->cr[CRF_SO] = xer_so;
> }
> return i;
> }
> diff --git a/target-ppc/machine.c b/target-ppc/machine.c
> index c801b82..9fa309a 100644
> --- a/target-ppc/machine.c
> +++ b/target-ppc/machine.c
> @@ -132,6 +132,10 @@ static void cpu_pre_save(void *opaque)
> CPUPPCState *env = &cpu->env;
> int i;
>
> + for (i = 0; i < 8; i++) {
> + env->crf[i] = ppc_get_crf(env, i);
> + }
> +
> env->spr[SPR_LR] = env->lr;
> env->spr[SPR_CTR] = env->ctr;
> env->spr[SPR_XER] = env->xer;
> @@ -165,6 +169,11 @@ static int cpu_post_load(void *opaque, int version_id)
> * software has to take care of running QEMU in a compatible mode.
> */
> env->spr[SPR_PVR] = env->spr_cb[SPR_PVR].default_value;
> +
> + for (i = 0; i < 8; i++) {
> + ppc_set_crf(env, i, env->crf[i]);
> + }
> +
> env->lr = env->spr[SPR_LR];
> env->ctr = env->spr[SPR_CTR];
> env->xer = env->spr[SPR_XER];
> diff --git a/target-ppc/translate.c b/target-ppc/translate.c
> index 1ed6a8f..dd19b39 100644
> --- a/target-ppc/translate.c
> +++ b/target-ppc/translate.c
> @@ -53,13 +53,13 @@ static char cpu_reg_names[10*3 + 22*4 /* GPR */
> + 10*4 + 22*5 /* FPR */
> + 2*(10*6 + 22*7) /* AVRh, AVRl */
> + 10*5 + 22*6 /* VSR */
> - + 8*5 /* CRF */];
> + + 32*8 /* CR */];
> static TCGv cpu_gpr[32];
> static TCGv cpu_gprh[32];
> static TCGv_i64 cpu_fpr[32];
> static TCGv_i64 cpu_avrh[32], cpu_avrl[32];
> static TCGv_i64 cpu_vsr[32];
> -static TCGv_i32 cpu_crf[8];
> +static TCGv_i32 cpu_cr[32];
> static TCGv cpu_nip;
> static TCGv cpu_msr;
> static TCGv cpu_ctr;
> @@ -89,12 +89,13 @@ void ppc_translate_init(void)
> p = cpu_reg_names;
> cpu_reg_names_size = sizeof(cpu_reg_names);
>
> - for (i = 0; i < 8; i++) {
> - snprintf(p, cpu_reg_names_size, "crf%d", i);
> - cpu_crf[i] = tcg_global_mem_new_i32(TCG_AREG0,
> - offsetof(CPUPPCState, crf[i]),
> p);
> - p += 5;
> - cpu_reg_names_size -= 5;
> + for (i = 0; i < 32; i++) {
> + static const char names[] = "lt\0gt\0eq\0so";
> + snprintf(p, cpu_reg_names_size, "cr%d[%s]", i >> 2, names + (i & 3)
> * 3);
> + cpu_cr[i] = tcg_global_mem_new_i32(TCG_AREG0,
> + offsetof(CPUPPCState, cr[i]), p);
> + p += 8;
> + cpu_reg_names_size -= 8;
> }
>
> for (i = 0; i < 32; i++) {
> @@ -251,17 +252,30 @@ static inline void gen_reset_fpstatus(void)
>
> static inline void gen_op_mfcr(TCGv dest, int first_cr, int shift)
> {
> - tcg_gen_shli_i32(dest, cpu_crf[first_cr >> 2], shift);
> + TCGv_i32 t0 = tcg_temp_new_i32();
> +
> + tcg_gen_shli_i32(dest, cpu_cr[first_cr + 3], shift);
> + tcg_gen_shli_i32(t0, cpu_cr[first_cr + 2], shift + 1);
> + tcg_gen_or_i32(dest, dest, t0);
> + tcg_gen_shli_i32(t0, cpu_cr[first_cr + 1], shift + 2);
> + tcg_gen_or_i32(dest, dest, t0);
> + tcg_gen_shli_i32(t0, cpu_cr[first_cr], shift + 3);
This leaks t0.
> }
>
> static inline void gen_op_mtcr(int first_cr, TCGv src, int shift)
> {
> if (shift) {
> - tcg_gen_shri_i32(cpu_crf[first_cr >> 2], src, shift);
> - tcg_gen_andi_i32(cpu_crf[first_cr >> 2], cpu_crf[first_cr >> 2],
> 0x0F);
> + tcg_gen_shri_i32(cpu_cr[first_cr + 3], src, shift);
> + tcg_gen_andi_i32(cpu_cr[first_cr + 3], cpu_cr[first_cr + 3], 1);
> } else {
> - tcg_gen_andi_i32(cpu_crf[first_cr >> 2], src, 0x0F);
> + tcg_gen_andi_i32(cpu_cr[first_cr + 3], src, 1);
> }
> + tcg_gen_shri_i32(cpu_cr[first_cr + 2], src, shift + 1);
> + tcg_gen_andi_i32(cpu_cr[first_cr + 2], cpu_cr[first_cr + 2], 1);
> + tcg_gen_shri_i32(cpu_cr[first_cr + 1], src, shift + 2);
> + tcg_gen_andi_i32(cpu_cr[first_cr + 1], cpu_cr[first_cr + 1], 1);
> + tcg_gen_shri_i32(cpu_cr[first_cr], src, shift + 3);
> + tcg_gen_andi_i32(cpu_cr[first_cr], cpu_cr[first_cr], 1);
> }
>
> static inline void gen_compute_fprf(TCGv_i64 arg, int set_fprf, int set_rc)
> @@ -675,27 +689,19 @@ static bool is_user_mode(DisasContext *ctx)
> static inline void gen_op_cmp(TCGv arg0, TCGv arg1, int s, int crf)
> {
> TCGv t0 = tcg_temp_new();
> - TCGv_i32 t1 = tcg_temp_new_i32();
>
> - tcg_gen_trunc_tl_i32(cpu_crf[crf], cpu_so);
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_SO], cpu_so);
This looks correct to me but is causing problems. The above statement seems to
get dropped in the generated asm ... at least on a PPC host:
IN:
0x00000000100005b4: cmpw cr3,r30,r29
OUT: [size=160]
0x6041ad30: lwz r14,-4(r27)
0x6041ad34: cmpwi cr7,r14,0
0x6041ad38: bne- cr7,0x6041adbc
0x6041ad3c: ld r14,240(r27) <<< r30
0x6041ad40: ld r15,232(r27) <<< r31
0x6041ad44: cmpw cr7,r14,r15 <<< this is the TCG_COND_LTx code
0x6041ad48: li r16,1
0x6041ad4c: li r0,0
0x6041ad50: isel r16,r16,r0,28
0x6041ad54: stw r16,576(r27) <<< store cpu_cr[LT]
0x6041ad58: cmpw cr7,r14,r15
0x6041ad5c: li r16,1
0x6041ad60: li r0,0
0x6041ad64: isel r16,r16,r0,29
0x6041ad68: stw r16,580(r27) <<< store cpu_cr[GT]
0x6041ad6c: cmplw cr7,r14,r15
0x6041ad70: li r14,1
0x6041ad74: li r0,0
0x6041ad78: isel r14,r14,r0,30
0x6041ad7c: stw r14,584(r27) <<< store cpu_cr[EQ]
0x6041ad80: .long 0x0
0x6041ad84: .long 0x0
Richard: any ideas or hints on how to proceed?
>
> tcg_gen_setcond_tl((s ? TCG_COND_LT: TCG_COND_LTU), t0, arg0, arg1);
> - tcg_gen_trunc_tl_i32(t1, t0);
> - tcg_gen_shli_i32(t1, t1, CRF_LT);
> - tcg_gen_or_i32(cpu_crf[crf], cpu_crf[crf], t1);
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_LT], t0);
>
> tcg_gen_setcond_tl((s ? TCG_COND_GT: TCG_COND_GTU), t0, arg0, arg1);
> - tcg_gen_trunc_tl_i32(t1, t0);
> - tcg_gen_shli_i32(t1, t1, CRF_GT);
> - tcg_gen_or_i32(cpu_crf[crf], cpu_crf[crf], t1);
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_GT], t0);
>
> tcg_gen_setcond_tl(TCG_COND_EQ, t0, arg0, arg1);
> - tcg_gen_trunc_tl_i32(t1, t0);
> - tcg_gen_shli_i32(t1, t1, CRF_EQ);
> - tcg_gen_or_i32(cpu_crf[crf], cpu_crf[crf], t1);
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_EQ], t0);
>
> tcg_temp_free(t0);
> - tcg_temp_free_i32(t1);
> }
>
> static inline void gen_op_cmpi(TCGv arg0, target_ulong arg1, int s, int crf)
> @@ -707,17 +713,22 @@ static inline void gen_op_cmpi(TCGv arg0, target_ulong
> arg1, int s, int crf)
>
> static inline void gen_op_cmp32(TCGv arg0, TCGv arg1, int s, int crf)
> {
> - TCGv t0, t1;
> + TCGv_i32 t0, t1;
> +
> t0 = tcg_temp_new();
> t1 = tcg_temp_new();
Needs to be tcg_temp_new_i32() ....
> - if (s) {
> - tcg_gen_ext32s_tl(t0, arg0);
> - tcg_gen_ext32s_tl(t1, arg1);
> - } else {
> - tcg_gen_ext32u_tl(t0, arg0);
> - tcg_gen_ext32u_tl(t1, arg1);
> - }
> - gen_op_cmp(t0, t1, s, crf);
> + tcg_gen_trunc_tl_i32(t0, arg0);
> + tcg_gen_trunc_tl_i32(t1, arg1);
> +
> + tcg_gen_setcond_i32((s ? TCG_COND_LT: TCG_COND_LTU),
> + cpu_cr[crf * 4 + CRF_LT], t0, t1);
> +
> + tcg_gen_setcond_i32((s ? TCG_COND_GT: TCG_COND_GTU),
> + cpu_cr[crf * 4 + CRF_GT], t0, t1);
> +
> + tcg_gen_setcond_i32(TCG_COND_EQ,
> + cpu_cr[crf * 4 + CRF_EQ], t0, t1);
> +
> tcg_temp_free(t1);
> tcg_temp_free(t0);
... and tcg_temp_free_i32()
> }
> @@ -790,15 +801,10 @@ static void gen_cmpli(DisasContext *ctx)
> static void gen_isel(DisasContext *ctx)
> {
> uint32_t bi = rC(ctx->opcode);
> - uint32_t mask;
> - TCGv_i32 t0;
> TCGv t1, true_op, zero;
>
> - mask = 0x08 >> (bi & 0x03);
> - t0 = tcg_temp_new_i32();
> - tcg_gen_andi_i32(t0, cpu_crf[bi >> 2], mask);
> t1 = tcg_temp_new();
> - tcg_gen_extu_i32_tl(t1, t0);
> + tcg_gen_extu_i32_tl(t1, cpu_cr[bi]);
> zero = tcg_const_tl(0);
> if (rA(ctx->opcode) == 0)
> true_op = zero;
> @@ -2288,21 +2294,29 @@ GEN_FLOAT_B(rim, 0x08, 0x0F, 1, PPC_FLOAT_EXT);
>
> static void gen_ftdiv(DisasContext *ctx)
> {
> + TCGv_i32 crf;
> if (unlikely(!ctx->fpu_enabled)) {
> gen_exception(ctx, POWERPC_EXCP_FPU);
> return;
> }
> - gen_helper_ftdiv(cpu_crf[crfD(ctx->opcode)], cpu_fpr[rA(ctx->opcode)],
> + crf = tcg_temp_new_i32();
> + gen_helper_ftdiv(crf, cpu_fpr[rA(ctx->opcode)],
> cpu_fpr[rB(ctx->opcode)]);
> + gen_op_mtcr(crfD(ctx->opcode) << 2, crf, 0);
> + tcg_temp_free_i32(crf);
> }
>
> static void gen_ftsqrt(DisasContext *ctx)
> {
> + TCGv_i32 crf;
> if (unlikely(!ctx->fpu_enabled)) {
> gen_exception(ctx, POWERPC_EXCP_FPU);
> return;
> }
> - gen_helper_ftsqrt(cpu_crf[crfD(ctx->opcode)], cpu_fpr[rB(ctx->opcode)]);
> + crf = tcg_temp_new_i32();
> + gen_helper_ftsqrt(crf, cpu_fpr[rB(ctx->opcode)]);
> + gen_op_mtcr(crfD(ctx->opcode) << 2, crf, 0);
> + tcg_temp_free_i32(crf);
> }
>
>
> @@ -3300,10 +3314,13 @@ static void gen_conditional_store(DisasContext *ctx,
> TCGv EA,
> {
> int l1;
>
> - tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_so);
> + tcg_gen_trunc_tl_i32(cpu_cr[CRF_SO], cpu_so);
> + tcg_gen_movi_i32(cpu_cr[CRF_LT], 0);
> + tcg_gen_movi_i32(cpu_cr[CRF_EQ], 0);
> + tcg_gen_movi_i32(cpu_cr[CRF_GT], 0);
> l1 = gen_new_label();
> tcg_gen_brcond_tl(TCG_COND_NE, EA, cpu_reserve, l1);
> - tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], 1 << CRF_EQ);
> + tcg_gen_movi_i32(cpu_cr[CRF_EQ], 1);
> #if defined(TARGET_PPC64)
> if (size == 8) {
> gen_qemu_st64(ctx, cpu_gpr[reg], EA);
> @@ -3870,17 +3887,11 @@ static inline void gen_bcond(DisasContext *ctx, int
> type)
> if ((bo & 0x10) == 0) {
> /* Test CR */
> uint32_t bi = BI(ctx->opcode);
> - uint32_t mask = 0x08 >> (bi & 0x03);
> - TCGv_i32 temp = tcg_temp_new_i32();
> -
> if (bo & 0x8) {
> - tcg_gen_andi_i32(temp, cpu_crf[bi >> 2], mask);
> - tcg_gen_brcondi_i32(TCG_COND_EQ, temp, 0, l1);
> + tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_cr[bi], 0, l1);
> } else {
> - tcg_gen_andi_i32(temp, cpu_crf[bi >> 2], mask);
> - tcg_gen_brcondi_i32(TCG_COND_NE, temp, 0, l1);
> + tcg_gen_brcondi_i32(TCG_COND_NE, cpu_cr[bi], 0, l1);
> }
> - tcg_temp_free_i32(temp);
> }
> gen_update_cfar(ctx, ctx->nip);
> if (type == BCOND_IM) {
> @@ -3929,35 +3940,11 @@ static void gen_bctar(DisasContext *ctx)
> }
>
> /*** Condition register logical
> ***/
> -#define GEN_CRLOGIC(name, tcg_op, opc)
> \
> -static void glue(gen_, name)(DisasContext *ctx)
> \
> -{
> \
> - uint8_t bitmask;
> \
> - int sh;
> \
> - TCGv_i32 t0, t1;
> \
> - sh = (crbD(ctx->opcode) & 0x03) - (crbA(ctx->opcode) & 0x03);
> \
> - t0 = tcg_temp_new_i32();
> \
> - if (sh > 0)
> \
> - tcg_gen_shri_i32(t0, cpu_crf[crbA(ctx->opcode) >> 2], sh);
> \
> - else if (sh < 0)
> \
> - tcg_gen_shli_i32(t0, cpu_crf[crbA(ctx->opcode) >> 2], -sh);
> \
> - else
> \
> - tcg_gen_mov_i32(t0, cpu_crf[crbA(ctx->opcode) >> 2]);
> \
> - t1 = tcg_temp_new_i32();
> \
> - sh = (crbD(ctx->opcode) & 0x03) - (crbB(ctx->opcode) & 0x03);
> \
> - if (sh > 0)
> \
> - tcg_gen_shri_i32(t1, cpu_crf[crbB(ctx->opcode) >> 2], sh);
> \
> - else if (sh < 0)
> \
> - tcg_gen_shli_i32(t1, cpu_crf[crbB(ctx->opcode) >> 2], -sh);
> \
> - else
> \
> - tcg_gen_mov_i32(t1, cpu_crf[crbB(ctx->opcode) >> 2]);
> \
> - tcg_op(t0, t0, t1);
> \
> - bitmask = 0x08 >> (crbD(ctx->opcode) & 0x03);
> \
> - tcg_gen_andi_i32(t0, t0, bitmask);
> \
> - tcg_gen_andi_i32(t1, cpu_crf[crbD(ctx->opcode) >> 2], ~bitmask);
> \
> - tcg_gen_or_i32(cpu_crf[crbD(ctx->opcode) >> 2], t0, t1);
> \
> - tcg_temp_free_i32(t0);
> \
> - tcg_temp_free_i32(t1);
> \
> +#define GEN_CRLOGIC(name, tcg_op, opc)
> \
> +static void glue(gen_, name)(DisasContext *ctx)
> \
> +{
> \
> + tcg_op(cpu_cr[crbD(ctx->opcode)], cpu_cr[crbA(ctx->opcode)],
> \
> + cpu_cr[crbB(ctx->opcode)]);
> \
> }
>
This is a very nice cleanup ... but it oversteers just a little. For some CR
logical instructions, the generated code can produce non-zero bits in the i32
cr variable in places other than the LSB.
For example, consider crnand, which produces the following on a PPC host:
IN:
0x0000000010000578: crnand 4*cr7+so,4*cr7+lt,4*cr7+eq
OUT: [size=112]
0x6041a630: lwz r14,-4(r27)
0x6041a634: cmpwi cr7,r14,0
0x6041a638: bne- cr7,0x6041a68c
0x6041a63c: lwz r14,640(r27)
0x6041a640: lwz r15,648(r27)
0x6041a644: nand r14,r14,r15
0x6041a648: andi. r14,r14,1
0x6041a64c: stw r14,652(r27)
0x6041a650: .long 0x0
0x6041a654: .long 0x0
0x6041a658: .long 0x0
0x6041a65c: .long 0x0
The host nand operation will always produce an i32 value that has 1s in bits
0-30, since they are presumably zero. A brute-force fix would be to add a
tcg_gen_andi_i32(D,D,1) to your macro. But I think this is required only for a
subset of the
instructions (crnand, crnor, creqv, crorc).
> /* crand */
> @@ -3980,7 +3967,11 @@ GEN_CRLOGIC(crxor, tcg_gen_xor_i32, 0x06);
> /* mcrf */
> static void gen_mcrf(DisasContext *ctx)
> {
> - tcg_gen_mov_i32(cpu_crf[crfD(ctx->opcode)], cpu_crf[crfS(ctx->opcode)]);
> + int i;
> + for (i = 0; i < 4; i++) {
> + tcg_gen_mov_i32(cpu_cr[crfD(ctx->opcode) * 4 + i],
> + cpu_cr[crfS(ctx->opcode) * 4 + i]);
> + }
> }
>
> /*** System linkage
> ***/
> @@ -4133,20 +4124,12 @@ static void gen_write_xer(TCGv src)
> /* mcrxr */
> static void gen_mcrxr(DisasContext *ctx)
> {
> - TCGv_i32 t0 = tcg_temp_new_i32();
> - TCGv_i32 t1 = tcg_temp_new_i32();
> - TCGv_i32 dst = cpu_crf[crfD(ctx->opcode)];
> -
> - tcg_gen_trunc_tl_i32(t0, cpu_so);
> - tcg_gen_trunc_tl_i32(t1, cpu_ov);
> - tcg_gen_trunc_tl_i32(dst, cpu_ca);
> - tcg_gen_shli_i32(t0, t0, 3);
> - tcg_gen_shli_i32(t1, t1, 2);
> - tcg_gen_shli_i32(dst, dst, 1);
> - tcg_gen_or_i32(dst, dst, t0);
> - tcg_gen_or_i32(dst, dst, t1);
> - tcg_temp_free_i32(t0);
> - tcg_temp_free_i32(t1);
> + int crf = crfD(ctx->opcode);
> +
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_LT], cpu_so);
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_GT], cpu_ov);
> + tcg_gen_trunc_tl_i32(cpu_cr[crf * 4 + CRF_EQ], cpu_ca);
> + tcg_gen_movi_i32(cpu_cr[crf * 4 + CRF_SO], 0);
>
> tcg_gen_movi_tl(cpu_so, 0);
> tcg_gen_movi_tl(cpu_ov, 0);
> @@ -6320,11 +6303,13 @@ static void gen_tlbsx_40x(DisasContext *ctx)
> gen_helper_4xx_tlbsx(cpu_gpr[rD(ctx->opcode)], cpu_env, t0);
> tcg_temp_free(t0);
> if (Rc(ctx->opcode)) {
> - int l1 = gen_new_label();
> - tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_so);
> - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_gpr[rD(ctx->opcode)], -1, l1);
> - tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], 0x02);
> - gen_set_label(l1);
> + t0 = tcg_temp_new();
> + tcg_gen_trunc_tl_i32(cpu_cr[CRF_SO], cpu_so);
> + tcg_gen_movi_i32(cpu_cr[CRF_LT], 0);
> + tcg_gen_movi_i32(cpu_cr[CRF_GT], 0);
> + tcg_gen_setcondi_tl(TCG_COND_EQ, t0, cpu_gpr[rD(ctx->opcode)], -1);
> + tcg_gen_trunc_tl_i32(cpu_cr[CRF_EQ], t0);
> + tcg_temp_free(t0);
> }
> #endif
> }
> @@ -6401,11 +6386,13 @@ static void gen_tlbsx_440(DisasContext *ctx)
> gen_helper_440_tlbsx(cpu_gpr[rD(ctx->opcode)], cpu_env, t0);
> tcg_temp_free(t0);
> if (Rc(ctx->opcode)) {
> - int l1 = gen_new_label();
> - tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_so);
> - tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_gpr[rD(ctx->opcode)], -1, l1);
> - tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], 0x02);
> - gen_set_label(l1);
> + t0 = tcg_temp_new();
> + tcg_gen_trunc_tl_i32(cpu_cr[CRF_SO], cpu_so);
> + tcg_gen_movi_i32(cpu_cr[CRF_LT], 0);
> + tcg_gen_movi_i32(cpu_cr[CRF_GT], 0);
> + tcg_gen_setcondi_tl(TCG_COND_EQ, t0, cpu_gpr[rD(ctx->opcode)], -1);
> + tcg_gen_trunc_tl_i32(cpu_cr[CRF_EQ], t0);
> + tcg_temp_free(t0);
> }
> #endif
> }
> @@ -7371,7 +7358,7 @@ GEN_VXFORM(vpmsumd, 4, 19)
> static void gen_##op(DisasContext *ctx) \
> { \
> TCGv_ptr ra, rb, rd; \
> - TCGv_i32 ps; \
> + TCGv_i32 ps, crf; \
> \
> if (unlikely(!ctx->altivec_enabled)) { \
> gen_exception(ctx, POWERPC_EXCP_VPU); \
> @@ -7383,13 +7370,16 @@ static void gen_##op(DisasContext *ctx) \
> rd = gen_avr_ptr(rD(ctx->opcode)); \
> \
> ps = tcg_const_i32((ctx->opcode & 0x200) != 0); \
> + crf = tcg_temp_new_i32(); \
> \
> - gen_helper_##op(cpu_crf[6], rd, ra, rb, ps); \
> + gen_helper_##op(crf, rd, ra, rb, ps); \
> + gen_op_mtcr(6 << 2, crf, 0); \
> \
> tcg_temp_free_ptr(ra); \
> tcg_temp_free_ptr(rb); \
> tcg_temp_free_ptr(rd); \
> tcg_temp_free_i32(ps); \
> + tcg_temp_free_ptr(crf); \
tcg_temp_free_i32() ?
> }
>
> GEN_BCD(bcdadd)
> @@ -8217,6 +8207,7 @@ static void gen_##name(DisasContext *ctx) \
> static void gen_##name(DisasContext *ctx) \
> { \
> TCGv_ptr ra, rb; \
> + TCGv_i32 tmp; \
> if (unlikely(!ctx->fpu_enabled)) { \
> gen_exception(ctx, POWERPC_EXCP_FPU); \
> return; \
> @@ -8224,8 +8215,10 @@ static void gen_##name(DisasContext *ctx) \
> gen_update_nip(ctx, ctx->nip - 4); \
> ra = gen_fprp_ptr(rA(ctx->opcode)); \
> rb = gen_fprp_ptr(rB(ctx->opcode)); \
> - gen_helper_##name(cpu_crf[crfD(ctx->opcode)], \
> - cpu_env, ra, rb); \
> + tmp = tcg_temp_new_i32(); \
> + gen_helper_##name(tmp, cpu_env, ra, rb); \
> + gen_op_mtcr(crfD(ctx->opcode) << 2, tmp, 0); \
> + tcg_temp_free_i32(tmp); \
> tcg_temp_free_ptr(ra); \
> tcg_temp_free_ptr(rb); \
> }
> @@ -8234,7 +8227,7 @@ static void gen_##name(DisasContext *ctx) \
> static void gen_##name(DisasContext *ctx) \
> { \
> TCGv_ptr ra; \
> - TCGv_i32 dcm; \
> + TCGv_i32 dcm, tmp; \
> if (unlikely(!ctx->fpu_enabled)) { \
> gen_exception(ctx, POWERPC_EXCP_FPU); \
> return; \
> @@ -8242,8 +8235,10 @@ static void gen_##name(DisasContext *ctx) \
> gen_update_nip(ctx, ctx->nip - 4); \
> ra = gen_fprp_ptr(rA(ctx->opcode)); \
> dcm = tcg_const_i32(DCM(ctx->opcode)); \
> - gen_helper_##name(cpu_crf[crfD(ctx->opcode)], \
> - cpu_env, ra, dcm); \
> + tmp = tcg_temp_new_i32(); \
> + gen_helper_##name(tmp, cpu_env, ra, dcm); \
> + gen_op_mtcr(crfD(ctx->opcode) << 2, tmp, 0); \
> + tcg_temp_free_i32(tmp); \
> tcg_temp_free_ptr(ra); \
> tcg_temp_free_i32(dcm); \
> }
> @@ -8668,37 +8663,32 @@ GEN_SPEOP_ARITH_IMM2(evsubifw, tcg_gen_subi_i32);
> #define GEN_SPEOP_COMP(name, tcg_cond)
> \
> static inline void gen_##name(DisasContext *ctx)
> \
> {
> \
> + TCGv tmp = tcg_temp_new();
> \
> +
> \
> if (unlikely(!ctx->spe_enabled)) {
> \
> gen_exception(ctx, POWERPC_EXCP_SPEU);
> \
> return;
> \
> }
> \
> - int l1 = gen_new_label();
> \
> - int l2 = gen_new_label();
> \
> - int l3 = gen_new_label();
> \
> - int l4 = gen_new_label();
> \
>
> \
> tcg_gen_ext32s_tl(cpu_gpr[rA(ctx->opcode)], cpu_gpr[rA(ctx->opcode)]);
> \
> tcg_gen_ext32s_tl(cpu_gpr[rB(ctx->opcode)], cpu_gpr[rB(ctx->opcode)]);
> \
> tcg_gen_ext32s_tl(cpu_gprh[rA(ctx->opcode)], cpu_gprh[rA(ctx->opcode)]);
> \
> tcg_gen_ext32s_tl(cpu_gprh[rB(ctx->opcode)], cpu_gprh[rB(ctx->opcode)]);
> \
>
> \
> - tcg_gen_brcond_tl(tcg_cond, cpu_gpr[rA(ctx->opcode)],
> \
> - cpu_gpr[rB(ctx->opcode)], l1);
> \
> - tcg_gen_movi_i32(cpu_crf[crfD(ctx->opcode)], 0);
> \
> - tcg_gen_br(l2);
> \
> - gen_set_label(l1);
> \
> - tcg_gen_movi_i32(cpu_crf[crfD(ctx->opcode)],
> \
> - CRF_CL | CRF_CH_OR_CL | CRF_CH_AND_CL);
> \
> - gen_set_label(l2);
> \
> - tcg_gen_brcond_tl(tcg_cond, cpu_gprh[rA(ctx->opcode)],
> \
> - cpu_gprh[rB(ctx->opcode)], l3);
> \
> - tcg_gen_andi_i32(cpu_crf[crfD(ctx->opcode)], cpu_crf[crfD(ctx->opcode)],
> \
> - ~(CRF_CH | CRF_CH_AND_CL));
> \
> - tcg_gen_br(l4);
> \
> - gen_set_label(l3);
> \
> - tcg_gen_ori_i32(cpu_crf[crfD(ctx->opcode)], cpu_crf[crfD(ctx->opcode)],
> \
> - CRF_CH | CRF_CH_OR_CL);
> \
> - gen_set_label(l4);
> \
> + tcg_gen_setcond_tl(tcg_cond, tmp,
> \
> + cpu_gpr[rA(ctx->opcode)],
> \
> + cpu_gpr[rB(ctx->opcode)]);
> \
> + tcg_gen_trunc_tl_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CL], tmp);
> \
> + tcg_gen_setcond_tl(tcg_cond, tmp,
> \
> + cpu_gprh[rA(ctx->opcode)],
> \
> + cpu_gprh[rB(ctx->opcode)]);
> \
> + tcg_gen_trunc_tl_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH], tmp);
> \
> + tcg_gen_or_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH_OR_CL],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CL]);
> \
> + tcg_gen_and_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH_AND_CL],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CL]);
> \
> }
> GEN_SPEOP_COMP(evcmpgtu, TCG_COND_GTU);
> GEN_SPEOP_COMP(evcmpgts, TCG_COND_GT);
> @@ -8769,22 +8759,20 @@ static inline void gen_evsel(DisasContext *ctx)
> int l2 = gen_new_label();
> int l3 = gen_new_label();
> int l4 = gen_new_label();
> - TCGv_i32 t0 = tcg_temp_local_new_i32();
> - tcg_gen_andi_i32(t0, cpu_crf[ctx->opcode & 0x07], 1 << 3);
> - tcg_gen_brcondi_i32(TCG_COND_EQ, t0, 0, l1);
> +
> + tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_cr[(ctx->opcode & 0x07) * 4], 0,
> l1);
> tcg_gen_mov_tl(cpu_gprh[rD(ctx->opcode)], cpu_gprh[rA(ctx->opcode)]);
> tcg_gen_br(l2);
> gen_set_label(l1);
> tcg_gen_mov_tl(cpu_gprh[rD(ctx->opcode)], cpu_gprh[rB(ctx->opcode)]);
> gen_set_label(l2);
> - tcg_gen_andi_i32(t0, cpu_crf[ctx->opcode & 0x07], 1 << 2);
> - tcg_gen_brcondi_i32(TCG_COND_EQ, t0, 0, l3);
> +
> + tcg_gen_brcondi_i32(TCG_COND_EQ, cpu_cr[(ctx->opcode & 0x07) * 4 + 1],
> 0, l3);
> tcg_gen_mov_tl(cpu_gpr[rD(ctx->opcode)], cpu_gpr[rA(ctx->opcode)]);
> tcg_gen_br(l4);
> gen_set_label(l3);
> tcg_gen_mov_tl(cpu_gpr[rD(ctx->opcode)], cpu_gpr[rB(ctx->opcode)]);
> gen_set_label(l4);
> - tcg_temp_free_i32(t0);
> }
>
> static void gen_evsel0(DisasContext *ctx)
> @@ -9366,9 +9354,12 @@ static inline void gen_##name(DisasContext *ctx)
> \
> t0 = tcg_temp_new_i32();
> \
> t1 = tcg_temp_new_i32();
> \
>
> \
> + tcg_gen_movi_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_LT], 0);
> \
> + tcg_gen_movi_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_GT], 0);
> \
> + tcg_gen_movi_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_SO], 0);
> \
> tcg_gen_trunc_tl_i32(t0, cpu_gpr[rA(ctx->opcode)]);
> \
> tcg_gen_trunc_tl_i32(t1, cpu_gpr[rB(ctx->opcode)]);
> \
> - gen_helper_##name(cpu_crf[crfD(ctx->opcode)], cpu_env, t0, t1);
> \
> + gen_helper_##name(cpu_cr[crfD(ctx->opcode) * 4 + CRF_EQ], cpu_env, t0,
> t1); \
>
> \
> tcg_temp_free_i32(t0);
> \
> tcg_temp_free_i32(t1);
> \
> @@ -9385,10 +9376,32 @@ static inline void gen_##name(DisasContext *ctx)
> \
> t1 = tcg_temp_new_i64();
> \
> gen_load_gpr64(t0, rA(ctx->opcode));
> \
> gen_load_gpr64(t1, rB(ctx->opcode));
> \
> - gen_helper_##name(cpu_crf[crfD(ctx->opcode)], cpu_env, t0, t1);
> \
> + tcg_gen_movi_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_LT], 0);
> \
> + tcg_gen_movi_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_GT], 0);
> \
> + tcg_gen_movi_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_SO], 0);
> \
> + gen_helper_##name(cpu_cr[crfD(ctx->opcode) * 4 + CRF_EQ], cpu_env,
> \
> + t0, t1);
> \
> tcg_temp_free_i64(t0);
> \
> tcg_temp_free_i64(t1);
> \
> }
> +#define GEN_SPEFPUOP_COMP_V64(name, helper)
> \
> +static inline void gen_##name(DisasContext *ctx)
> \
> +{
> \
> + if (unlikely(!ctx->spe_enabled)) {
> \
> + gen_exception(ctx, POWERPC_EXCP_SPEU);
> \
> + return;
> \
> + }
> \
> + gen_helper_##helper(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CL], cpu_env,
> \
> + cpu_gpr[rA(ctx->opcode)], cpu_gpr[rB(ctx->opcode)]);
> \
> + gen_helper_##helper(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH], cpu_env,
> \
> + cpu_gprh[rA(ctx->opcode)],
> cpu_gprh[rB(ctx->opcode)]);\
This doesn't compile for 64 bit targets because the helpers declare i32 types
for the GPR arguments.
> + tcg_gen_or_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH_OR_CL],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CL]);
> \
> + tcg_gen_and_i32(cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH_AND_CL],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CH],
> \
> + cpu_cr[crfD(ctx->opcode) * 4 + CRF_CL]);
> \
> +}
>
> /* Single precision floating-point vectors operations */
> /* Arithmetic */
> @@ -9443,12 +9456,12 @@ GEN_SPEFPUOP_CONV_64_64(evfsctuiz);
> GEN_SPEFPUOP_CONV_64_64(evfsctsiz);
>
> /* Comparison */
> -GEN_SPEFPUOP_COMP_64(evfscmpgt);
> -GEN_SPEFPUOP_COMP_64(evfscmplt);
> -GEN_SPEFPUOP_COMP_64(evfscmpeq);
> -GEN_SPEFPUOP_COMP_64(evfststgt);
> -GEN_SPEFPUOP_COMP_64(evfststlt);
> -GEN_SPEFPUOP_COMP_64(evfststeq);
> +GEN_SPEFPUOP_COMP_V64(evfscmpgt, efscmpgt);
> +GEN_SPEFPUOP_COMP_V64(evfscmplt, efscmplt);
> +GEN_SPEFPUOP_COMP_V64(evfscmpeq, efscmpeq);
> +GEN_SPEFPUOP_COMP_V64(evfststgt, efststgt);
> +GEN_SPEFPUOP_COMP_V64(evfststlt, efststlt);
> +GEN_SPEFPUOP_COMP_V64(evfststeq, efststeq);
>
> /* Opcodes definitions */
> GEN_SPE(evfsadd, evfssub, 0x00, 0x0A, 0x00000000, 0x00000000,
> PPC_SPE_SINGLE); //
>
