| Message ID | 20250505202751.3510517-16-richard.henderson@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | tcg/optimize: Track and use known 1's | expand |
On 5/5/25 22:27, Richard Henderson wrote: > + uint64_t v1 = ti_const_val(t1); > + uint64_t v2 = ti_const_val(t2); Are v1 and v2 needed at all? If starting from z1==o1 and z2==o2, you will always end up with z1|z2 == o1|o2 after these: > + z1 = (uint32_t)z1 >> shr; > + o1 = (uint32_t)o1 >> shr; > + z2 = (uint64_t)((int32_t)z2 << (32 - shr)); > + o2 = (uint64_t)((int32_t)o2 << (32 - shr)); or these: > + z1 >>= shr; > + o1 >>= shr; > + z2 <<= 64 - shr; > + o2 <<= 64 - shr; so fold_masks_zo would do the job. Paolo
On 5/6/25 04:12, Paolo Bonzini wrote: > On 5/5/25 22:27, Richard Henderson wrote: >> + uint64_t v1 = ti_const_val(t1); >> + uint64_t v2 = ti_const_val(t2); > > Are v1 and v2 needed at all? > > If starting from z1==o1 and z2==o2, you will always end up with z1|z2 == o1|o2 after these: > >> + z1 = (uint32_t)z1 >> shr; >> + o1 = (uint32_t)o1 >> shr; >> + z2 = (uint64_t)((int32_t)z2 << (32 - shr)); >> + o2 = (uint64_t)((int32_t)o2 << (32 - shr)); > > or these: > >> + z1 >>= shr; >> + o1 >>= shr; >> + z2 <<= 64 - shr; >> + o2 <<= 64 - shr; > > so fold_masks_zo would do the job. Yes indeed, thanks again. r~
diff --git a/tcg/optimize.c b/tcg/optimize.c index c5243392af..424fd57922 100644 --- a/tcg/optimize.c +++ b/tcg/optimize.c @@ -1986,21 +1986,37 @@ static bool fold_extract(OptContext *ctx, TCGOp *op) static bool fold_extract2(OptContext *ctx, TCGOp *op) { - if (arg_is_const(op->args[1]) && arg_is_const(op->args[2])) { - uint64_t v1 = arg_const_val(op->args[1]); - uint64_t v2 = arg_const_val(op->args[2]); - int shr = op->args[3]; + TempOptInfo *t1 = arg_info(op->args[1]); + TempOptInfo *t2 = arg_info(op->args[2]); + uint64_t v1 = ti_const_val(t1); + uint64_t v2 = ti_const_val(t2); + uint64_t z1 = t1->z_mask; + uint64_t z2 = t2->z_mask; + uint64_t o1 = t1->o_mask; + uint64_t o2 = t2->o_mask; + int shr = op->args[3]; - if (ctx->type == TCG_TYPE_I32) { - v1 = (uint32_t)v1 >> shr; - v2 = (uint64_t)((int32_t)v2 << (32 - shr)); - } else { - v1 >>= shr; - v2 <<= 64 - shr; - } + if (ctx->type == TCG_TYPE_I32) { + v1 = (uint32_t)v1 >> shr; + z1 = (uint32_t)z1 >> shr; + o1 = (uint32_t)o1 >> shr; + v2 = (uint64_t)((int32_t)v2 << (32 - shr)); + z2 = (uint64_t)((int32_t)z2 << (32 - shr)); + o2 = (uint64_t)((int32_t)o2 << (32 - shr)); + } else { + v1 >>= shr; + z1 >>= shr; + o1 >>= shr; + v2 <<= 64 - shr; + z2 <<= 64 - shr; + o2 <<= 64 - shr; + } + + if (ti_is_const(t1) && ti_is_const(t2)) { return tcg_opt_gen_movi(ctx, op, op->args[0], v1 | v2); } - return finish_folding(ctx, op); + + return fold_masks_zo(ctx, op, z1 | z2, o1 | o2); } static bool fold_exts(OptContext *ctx, TCGOp *op)
Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- tcg/optimize.c | 40 ++++++++++++++++++++++++++++------------ 1 file changed, 28 insertions(+), 12 deletions(-)