diff options
Diffstat (limited to 'target/s390x')
| -rw-r--r-- | target/s390x/helper.h | 1 | ||||
| -rw-r--r-- | target/s390x/int_helper.c | 21 | ||||
| -rw-r--r-- | target/s390x/translate.c | 36 |
3 files changed, 29 insertions, 29 deletions
diff --git a/target/s390x/helper.h b/target/s390x/helper.h index 207a6e7d1c..9102071d0a 100644 --- a/target/s390x/helper.h +++ b/target/s390x/helper.h @@ -70,7 +70,6 @@ DEF_HELPER_FLAGS_4(msdb, TCG_CALL_NO_WG, i64, env, i64, i64, i64) DEF_HELPER_FLAGS_3(tceb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64) DEF_HELPER_FLAGS_3(tcdb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64) DEF_HELPER_FLAGS_4(tcxb, TCG_CALL_NO_RWG_SE, i32, env, i64, i64, i64) -DEF_HELPER_FLAGS_1(clz, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_2(sqeb, TCG_CALL_NO_WG, i64, env, i64) DEF_HELPER_FLAGS_2(sqdb, TCG_CALL_NO_WG, i64, env, i64) DEF_HELPER_FLAGS_3(sqxb, TCG_CALL_NO_WG, i64, env, i64, i64) diff --git a/target/s390x/int_helper.c b/target/s390x/int_helper.c index 370c94da55..f26f36a904 100644 --- a/target/s390x/int_helper.c +++ b/target/s390x/int_helper.c @@ -117,12 +117,6 @@ uint64_t HELPER(divu64)(CPUS390XState *env, uint64_t ah, uint64_t al, return ret; } -/* count leading zeros, for find leftmost one */ -uint64_t HELPER(clz)(uint64_t v) -{ - return clz64(v); -} - uint64_t HELPER(cvd)(int32_t reg) { /* positive 0 */ @@ -143,14 +137,11 @@ uint64_t HELPER(cvd)(int32_t reg) return dec; } -uint64_t HELPER(popcnt)(uint64_t r2) +uint64_t HELPER(popcnt)(uint64_t val) { - uint64_t ret = 0; - int i; - - for (i = 0; i < 64; i += 8) { - uint64_t t = ctpop32((r2 >> i) & 0xff); - ret |= t << i; - } - return ret; + /* Note that we don't fold past bytes. */ + val = (val & 0x5555555555555555ULL) + ((val >> 1) & 0x5555555555555555ULL); + val = (val & 0x3333333333333333ULL) + ((val >> 2) & 0x3333333333333333ULL); + val = (val + (val >> 4)) & 0x0f0f0f0f0f0f0f0fULL; + return val; } diff --git a/target/s390x/translate.c b/target/s390x/translate.c index 02bc7058fd..01c62176bf 100644 --- a/target/s390x/translate.c +++ b/target/s390x/translate.c @@ -2249,7 +2249,7 @@ static ExitStatus op_flogr(DisasContext *s, DisasOps *o) gen_op_update1_cc_i64(s, CC_OP_FLOGR, o->in2); /* R1 = IN ? CLZ(IN) : 64. */ - gen_helper_clz(o->out, o->in2); + tcg_gen_clzi_i64(o->out, o->in2, 64); /* R1+1 = IN & ~(found bit). Note that we may attempt to shift this value by 64, which is undefined. But since the shift is 64 iff the @@ -3134,20 +3134,26 @@ static ExitStatus op_risbg(DisasContext *s, DisasOps *o) } } - /* In some cases we can implement this with deposit, which can be more - efficient on some hosts. */ - if (~mask == imask && i3 <= i4) { - if (s->fields->op2 == 0x5d) { - i3 += 32, i4 += 32; - } + len = i4 - i3 + 1; + pos = 63 - i4; + rot = i5 & 63; + if (s->fields->op2 == 0x5d) { + pos += 32; + } + + /* In some cases we can implement this with extract. */ + if (imask == 0 && pos == 0 && len > 0 && rot + len <= 64) { + tcg_gen_extract_i64(o->out, o->in2, rot, len); + return NO_EXIT; + } + + /* In some cases we can implement this with deposit. */ + if (len > 0 && (imask == 0 || ~mask == imask)) { /* Note that we rotate the bits to be inserted to the lsb, not to the position as described in the PoO. */ - len = i4 - i3 + 1; - pos = 63 - i4; - rot = (i5 - pos) & 63; + rot = (rot - pos) & 63; } else { - pos = len = -1; - rot = i5 & 63; + pos = -1; } /* Rotate the input as necessary. */ @@ -3155,7 +3161,11 @@ static ExitStatus op_risbg(DisasContext *s, DisasOps *o) /* Insert the selected bits into the output. */ if (pos >= 0) { - tcg_gen_deposit_i64(o->out, o->out, o->in2, pos, len); + if (imask == 0) { + tcg_gen_deposit_z_i64(o->out, o->in2, pos, len); + } else { + tcg_gen_deposit_i64(o->out, o->out, o->in2, pos, len); + } } else if (imask == 0) { tcg_gen_andi_i64(o->out, o->in2, mask); } else { |