On Sun, Sep 27, 2026 at 5:08 AM Richard Henderson <[email protected]> wrote: > > Signed-off-by: Richard Henderson <[email protected]> > --- > include/tcg/tcg-op-common.h | 6 ------ > include/tcg/tcg-op-def.h.inc | 1 + > tcg/tcg-op-gvec.c | 41 ------------------------------------ > tcg/tcg-op.c | 16 ++++++++++++++ > 4 files changed, 17 insertions(+), 47 deletions(-) > > diff --git a/include/tcg/tcg-op-common.h b/include/tcg/tcg-op-common.h > index 65b9d828e38..583f6ebb2f5 100644 > --- a/include/tcg/tcg-op-common.h > +++ b/include/tcg/tcg-op-common.h > @@ -137,9 +137,6 @@ void tcg_gen_bswap32_i32(TCGv_i32 ret, TCGv_i32 arg); > void tcg_gen_hswap_i32(TCGv_i32 ret, TCGv_i32 arg); > void tcg_gen_revbit32_i32(TCGv_i32 ret, TCGv_i32 arg); > > -/* Replicate a value of size @vece from @in to all the lanes in @out */ > -void tcg_gen_dup_i32(unsigned vece, TCGv_i32 out, TCGv_i32 in); > - > /* 64 bit ops */ > > void tcg_gen_addN_i64(int n, TCGv_i64 *r, TCGv_i64 *a, TCGv_i64 *b); > @@ -153,9 +150,6 @@ void tcg_gen_wswap_i64(TCGv_i64 ret, TCGv_i64 arg); > void tcg_gen_revbit32_i64(TCGv_i64 ret, TCGv_i64 arg, unsigned flags); > void tcg_gen_revbit64_i64(TCGv_i64 ret, TCGv_i64 arg); > > -/* Replicate a value of size @vece from @in to all the lanes in @out */ > -void tcg_gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in); > - > void tcg_gen_st32_i64(TCGv_i64 arg1, TCGv_ptr arg2, tcg_target_long offset); > > void tcg_gen_ld32u_i64(TCGv_i64 ret, TCGv_ptr arg2, tcg_target_long offset); > diff --git a/include/tcg/tcg-op-def.h.inc b/include/tcg/tcg-op-def.h.inc > index f9dab50a911..556f7470cd6 100644 > --- a/include/tcg/tcg-op-def.h.inc > +++ b/include/tcg/tcg-op-def.h.inc > @@ -23,6 +23,7 @@ DEF4(deposit_z, TCGV, TCGV, unsigned, unsigned) > DEF1(discard, TCGV) > DEF3(div, TCGV, TCGV, TCGV) > DEF3(divu, TCGV, TCGV, TCGV) > +DEF3(dup, unsigned, TCGV, TCGV) > DEF3(ext, TCGV, TCGV, MemOp) > DEF2(ext8s, TCGV, TCGV) > DEF2(ext8u, TCGV, TCGV) > diff --git a/tcg/tcg-op-gvec.c b/tcg/tcg-op-gvec.c > index 0d649cc13b2..72abb0a08ec 100644 > --- a/tcg/tcg-op-gvec.c > +++ b/tcg/tcg-op-gvec.c > @@ -434,47 +434,6 @@ uint64_t (dup_const)(unsigned vece, uint64_t c) > } > } > > -/* Duplicate IN into OUT as per VECE. */ > -void tcg_gen_dup_i32(unsigned vece, TCGv_i32 out, TCGv_i32 in) > -{ > - switch (vece) { > - case MO_8: > - tcg_gen_ext8u_i32(out, in); > - tcg_gen_muli_i32(out, out, 0x01010101); > - break; > - case MO_16: > - tcg_gen_deposit_i32(out, in, in, 16, 16); > - break; > - case MO_32: > - tcg_gen_mov_i32(out, in); > - break; > - default: > - g_assert_not_reached(); > - } > -} > - > -void tcg_gen_dup_i64(unsigned vece, TCGv_i64 out, TCGv_i64 in) > -{ > - switch (vece) { > - case MO_8: > - tcg_gen_ext8u_i64(out, in); > - tcg_gen_muli_i64(out, out, 0x0101010101010101ull); > - break; > - case MO_16: > - tcg_gen_ext16u_i64(out, in); > - tcg_gen_muli_i64(out, out, 0x0001000100010001ull); > - break; > - case MO_32: > - tcg_gen_deposit_i64(out, in, in, 32, 32); > - break; > - case MO_64: > - tcg_gen_mov_i64(out, in); > - break; > - default: > - g_assert_not_reached(); > - } > -} > - > /* Select a supported vector type for implementing an operation on SIZE > * bytes. If OP is 0, assume that the real operation to be performed is > * required by all backends. Otherwise, make sure than OP can be performed > diff --git a/tcg/tcg-op.c b/tcg/tcg-op.c > index 2e8087c938c..924b94414b7 100644 > --- a/tcg/tcg-op.c > +++ b/tcg/tcg-op.c > @@ -661,6 +661,22 @@ void tcg_gen_divu(TCGType type, TCGTemp *dst, TCGTemp > *src1, TCGTemp *src2) > } > } > > +void tcg_gen_dup(TCGType type, unsigned vece, TCGTemp *dst, TCGTemp *src) > +{ > + unsigned t_width = tcg_type_size(type) * 8; > + unsigned e_width = memop_size(vece) * 8; > + > + tcg_debug_assert(e_width <= t_width); > + if (t_width == e_width) { > + tcg_gen_mov(type, dst, src); > + } else if (t_width == e_width * 2) { > + tcg_gen_deposit(type, dst, src, src, e_width, e_width); > + } else { > + tcg_gen_extract(type, dst, src, 0, e_width); > + tcg_gen_muli(type, dst, dst, ~0ull / MAKE_64BIT_MASK(0, e_width));
For I32 with MO_8 this multiplies by an I32 constant 0x0101010101010101 rather than 0x01010101.
