| Message ID | 20211015074627.3957162-70-frank.chang@sifive.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | support vector extension v1.0 | expand |
On Fri, Oct 15, 2021 at 6:47 PM <frank.chang@sifive.com> wrote: > > From: Frank Chang <frank.chang@sifive.com> > > Add the following instructions: > > * vfwcvt.rtz.xu.f.v > * vfwcvt.rtz.x.f.v > > Also adjust GEN_OPFV_WIDEN_TRANS() to accept multiple floating-point > rounding modes. > > Signed-off-by: Frank Chang <frank.chang@sifive.com> Acked-by: Alistair Francis <alistair.francis@wdc.com> Alistair > --- > target/riscv/helper.h | 2 + > target/riscv/insn32.decode | 13 +++--- > target/riscv/insn_trans/trans_rvv.c.inc | 55 +++++++++++++++++++++---- > target/riscv/vector_helper.c | 7 +++- > 4 files changed, 63 insertions(+), 14 deletions(-) > > diff --git a/target/riscv/helper.h b/target/riscv/helper.h > index 1727075dce4..53cf88cd402 100644 > --- a/target/riscv/helper.h > +++ b/target/riscv/helper.h > @@ -928,8 +928,10 @@ DEF_HELPER_5(vfwcvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32) > +DEF_HELPER_5(vfwcvt_f_xu_v_b, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32) > +DEF_HELPER_5(vfwcvt_f_x_v_b, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32) > DEF_HELPER_5(vfwcvt_f_f_v_h, void, ptr, ptr, ptr, env, i32) > diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode > index 02064f8ec98..664d0fb3716 100644 > --- a/target/riscv/insn32.decode > +++ b/target/riscv/insn32.decode > @@ -592,11 +592,14 @@ vfcvt_f_xu_v 010010 . ..... 00010 001 ..... 1010111 @r2_vm > vfcvt_f_x_v 010010 . ..... 00011 001 ..... 1010111 @r2_vm > vfcvt_rtz_xu_f_v 010010 . ..... 00110 001 ..... 1010111 @r2_vm > vfcvt_rtz_x_f_v 010010 . ..... 00111 001 ..... 1010111 @r2_vm > -vfwcvt_xu_f_v 100010 . ..... 01000 001 ..... 1010111 @r2_vm > -vfwcvt_x_f_v 100010 . ..... 01001 001 ..... 1010111 @r2_vm > -vfwcvt_f_xu_v 100010 . ..... 01010 001 ..... 1010111 @r2_vm > -vfwcvt_f_x_v 100010 . ..... 01011 001 ..... 1010111 @r2_vm > -vfwcvt_f_f_v 100010 . ..... 01100 001 ..... 1010111 @r2_vm > + > +vfwcvt_xu_f_v 010010 . ..... 01000 001 ..... 1010111 @r2_vm > +vfwcvt_x_f_v 010010 . ..... 01001 001 ..... 1010111 @r2_vm > +vfwcvt_f_xu_v 010010 . ..... 01010 001 ..... 1010111 @r2_vm > +vfwcvt_f_x_v 010010 . ..... 01011 001 ..... 1010111 @r2_vm > +vfwcvt_f_f_v 010010 . ..... 01100 001 ..... 1010111 @r2_vm > +vfwcvt_rtz_xu_f_v 010010 . ..... 01110 001 ..... 1010111 @r2_vm > +vfwcvt_rtz_x_f_v 010010 . ..... 01111 001 ..... 1010111 @r2_vm > vfncvt_xu_f_v 100010 . ..... 10000 001 ..... 1010111 @r2_vm > vfncvt_x_f_v 100010 . ..... 10001 001 ..... 1010111 @r2_vm > vfncvt_f_xu_v 100010 . ..... 10010 001 ..... 1010111 @r2_vm > diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc > index b1ea15517c0..63d33b22068 100644 > --- a/target/riscv/insn_trans/trans_rvv.c.inc > +++ b/target/riscv/insn_trans/trans_rvv.c.inc > @@ -2535,12 +2535,55 @@ static bool opfv_widen_check(DisasContext *s, arg_rmr *a) > vext_check_ds(s, a->rd, a->rs2, a->vm); > } > > -#define GEN_OPFV_WIDEN_TRANS(NAME) \ > +#define GEN_OPFV_WIDEN_TRANS(NAME, HELPER, FRM) \ > static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ > { \ > if (opfv_widen_check(s, a)) { \ > uint32_t data = 0; \ > static gen_helper_gvec_3_ptr * const fns[2] = { \ > + gen_helper_##HELPER##_h, \ > + gen_helper_##HELPER##_w, \ > + }; \ > + TCGLabel *over = gen_new_label(); \ > + gen_set_rm(s, FRM); \ > + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ > + \ > + data = FIELD_DP32(data, VDATA, VM, a->vm); \ > + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ > + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ > + vreg_ofs(s, a->rs2), cpu_env, \ > + s->vlen / 8, s->vlen / 8, data, \ > + fns[s->sew - 1]); \ > + mark_vs_dirty(s); \ > + gen_set_label(over); \ > + return true; \ > + } \ > + return false; \ > +} > + > +GEN_OPFV_WIDEN_TRANS(vfwcvt_xu_f_v, vfwcvt_xu_f_v, RISCV_FRM_DYN) > +GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v, vfwcvt_x_f_v, RISCV_FRM_DYN) > +GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v, vfwcvt_f_f_v, RISCV_FRM_DYN) > +/* Reuse the helper functions from vfwcvt.xu.f.v and vfwcvt.x.f.v */ > +GEN_OPFV_WIDEN_TRANS(vfwcvt_rtz_xu_f_v, vfwcvt_xu_f_v, RISCV_FRM_RTZ) > +GEN_OPFV_WIDEN_TRANS(vfwcvt_rtz_x_f_v, vfwcvt_x_f_v, RISCV_FRM_RTZ) > + > +static bool opfxv_widen_check(DisasContext *s, arg_rmr *a) > +{ > + return require_rvv(s) && > + require_scale_rvf(s) && > + vext_check_isa_ill(s) && > + /* OPFV widening instructions ignore vs1 check */ > + vext_check_ds(s, a->rd, a->rs2, a->vm); > +} > + > +#define GEN_OPFXV_WIDEN_TRANS(NAME) \ > +static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ > +{ \ > + if (opfxv_widen_check(s, a)) { \ > + uint32_t data = 0; \ > + static gen_helper_gvec_3_ptr * const fns[3] = { \ > + gen_helper_##NAME##_b, \ > gen_helper_##NAME##_h, \ > gen_helper_##NAME##_w, \ > }; \ > @@ -2549,11 +2592,10 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ > tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ > \ > data = FIELD_DP32(data, VDATA, VM, a->vm); \ > - data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ > tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ > vreg_ofs(s, a->rs2), cpu_env, \ > s->vlen / 8, s->vlen / 8, data, \ > - fns[s->sew - 1]); \ > + fns[s->sew]); \ > mark_vs_dirty(s); \ > gen_set_label(over); \ > return true; \ > @@ -2561,11 +2603,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ > return false; \ > } > > -GEN_OPFV_WIDEN_TRANS(vfwcvt_xu_f_v) > -GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v) > -GEN_OPFV_WIDEN_TRANS(vfwcvt_f_xu_v) > -GEN_OPFV_WIDEN_TRANS(vfwcvt_f_x_v) > -GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v) > +GEN_OPFXV_WIDEN_TRANS(vfwcvt_f_xu_v) > +GEN_OPFXV_WIDEN_TRANS(vfwcvt_f_x_v) > > /* Narrowing Floating-Point/Integer Type-Convert Instructions */ > > diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c > index c19cd937e1a..dda8e2ab5a2 100644 > --- a/target/riscv/vector_helper.c > +++ b/target/riscv/vector_helper.c > @@ -3773,6 +3773,7 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8) > > /* Widening Floating-Point/Integer Type-Convert Instructions */ > /* (TD, T2, TX2) */ > +#define WOP_UU_B uint16_t, uint8_t, uint8_t > #define WOP_UU_H uint32_t, uint16_t, uint16_t > #define WOP_UU_W uint64_t, uint32_t, uint32_t > /* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/ > @@ -3788,19 +3789,23 @@ GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4) > GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8) > > /* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */ > +RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16) > RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32) > RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64) > +GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 1, 2) > GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4) > GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8) > > /* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */ > +RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16) > RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32) > RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64) > +GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 1, 2) > GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4) > GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8) > > /* > - * vfwcvt.f.f.v vd, vs2, vm # > + * vfwcvt.f.f.v vd, vs2, vm > * Convert single-width float to double-width float. > */ > static uint32_t vfwcvtffv16(uint16_t a, float_status *s) > -- > 2.25.1 > >
diff --git a/target/riscv/helper.h b/target/riscv/helper.h index 1727075dce4..53cf88cd402 100644 --- a/target/riscv/helper.h +++ b/target/riscv/helper.h @@ -928,8 +928,10 @@ DEF_HELPER_5(vfwcvt_xu_f_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_xu_f_v_w, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_x_f_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_x_f_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_xu_v_b, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_f_xu_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_f_xu_v_w, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_5(vfwcvt_f_x_v_b, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_f_x_v_h, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_f_x_v_w, void, ptr, ptr, ptr, env, i32) DEF_HELPER_5(vfwcvt_f_f_v_h, void, ptr, ptr, ptr, env, i32) diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode index 02064f8ec98..664d0fb3716 100644 --- a/target/riscv/insn32.decode +++ b/target/riscv/insn32.decode @@ -592,11 +592,14 @@ vfcvt_f_xu_v 010010 . ..... 00010 001 ..... 1010111 @r2_vm vfcvt_f_x_v 010010 . ..... 00011 001 ..... 1010111 @r2_vm vfcvt_rtz_xu_f_v 010010 . ..... 00110 001 ..... 1010111 @r2_vm vfcvt_rtz_x_f_v 010010 . ..... 00111 001 ..... 1010111 @r2_vm -vfwcvt_xu_f_v 100010 . ..... 01000 001 ..... 1010111 @r2_vm -vfwcvt_x_f_v 100010 . ..... 01001 001 ..... 1010111 @r2_vm -vfwcvt_f_xu_v 100010 . ..... 01010 001 ..... 1010111 @r2_vm -vfwcvt_f_x_v 100010 . ..... 01011 001 ..... 1010111 @r2_vm -vfwcvt_f_f_v 100010 . ..... 01100 001 ..... 1010111 @r2_vm + +vfwcvt_xu_f_v 010010 . ..... 01000 001 ..... 1010111 @r2_vm +vfwcvt_x_f_v 010010 . ..... 01001 001 ..... 1010111 @r2_vm +vfwcvt_f_xu_v 010010 . ..... 01010 001 ..... 1010111 @r2_vm +vfwcvt_f_x_v 010010 . ..... 01011 001 ..... 1010111 @r2_vm +vfwcvt_f_f_v 010010 . ..... 01100 001 ..... 1010111 @r2_vm +vfwcvt_rtz_xu_f_v 010010 . ..... 01110 001 ..... 1010111 @r2_vm +vfwcvt_rtz_x_f_v 010010 . ..... 01111 001 ..... 1010111 @r2_vm vfncvt_xu_f_v 100010 . ..... 10000 001 ..... 1010111 @r2_vm vfncvt_x_f_v 100010 . ..... 10001 001 ..... 1010111 @r2_vm vfncvt_f_xu_v 100010 . ..... 10010 001 ..... 1010111 @r2_vm diff --git a/target/riscv/insn_trans/trans_rvv.c.inc b/target/riscv/insn_trans/trans_rvv.c.inc index b1ea15517c0..63d33b22068 100644 --- a/target/riscv/insn_trans/trans_rvv.c.inc +++ b/target/riscv/insn_trans/trans_rvv.c.inc @@ -2535,12 +2535,55 @@ static bool opfv_widen_check(DisasContext *s, arg_rmr *a) vext_check_ds(s, a->rd, a->rs2, a->vm); } -#define GEN_OPFV_WIDEN_TRANS(NAME) \ +#define GEN_OPFV_WIDEN_TRANS(NAME, HELPER, FRM) \ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ { \ if (opfv_widen_check(s, a)) { \ uint32_t data = 0; \ static gen_helper_gvec_3_ptr * const fns[2] = { \ + gen_helper_##HELPER##_h, \ + gen_helper_##HELPER##_w, \ + }; \ + TCGLabel *over = gen_new_label(); \ + gen_set_rm(s, FRM); \ + tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs2), cpu_env, \ + s->vlen / 8, s->vlen / 8, data, \ + fns[s->sew - 1]); \ + mark_vs_dirty(s); \ + gen_set_label(over); \ + return true; \ + } \ + return false; \ +} + +GEN_OPFV_WIDEN_TRANS(vfwcvt_xu_f_v, vfwcvt_xu_f_v, RISCV_FRM_DYN) +GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v, vfwcvt_x_f_v, RISCV_FRM_DYN) +GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v, vfwcvt_f_f_v, RISCV_FRM_DYN) +/* Reuse the helper functions from vfwcvt.xu.f.v and vfwcvt.x.f.v */ +GEN_OPFV_WIDEN_TRANS(vfwcvt_rtz_xu_f_v, vfwcvt_xu_f_v, RISCV_FRM_RTZ) +GEN_OPFV_WIDEN_TRANS(vfwcvt_rtz_x_f_v, vfwcvt_x_f_v, RISCV_FRM_RTZ) + +static bool opfxv_widen_check(DisasContext *s, arg_rmr *a) +{ + return require_rvv(s) && + require_scale_rvf(s) && + vext_check_isa_ill(s) && + /* OPFV widening instructions ignore vs1 check */ + vext_check_ds(s, a->rd, a->rs2, a->vm); +} + +#define GEN_OPFXV_WIDEN_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ +{ \ + if (opfxv_widen_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_3_ptr * const fns[3] = { \ + gen_helper_##NAME##_b, \ gen_helper_##NAME##_h, \ gen_helper_##NAME##_w, \ }; \ @@ -2549,11 +2592,10 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_vl, 0, over); \ \ data = FIELD_DP32(data, VDATA, VM, a->vm); \ - data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ tcg_gen_gvec_3_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ vreg_ofs(s, a->rs2), cpu_env, \ s->vlen / 8, s->vlen / 8, data, \ - fns[s->sew - 1]); \ + fns[s->sew]); \ mark_vs_dirty(s); \ gen_set_label(over); \ return true; \ @@ -2561,11 +2603,8 @@ static bool trans_##NAME(DisasContext *s, arg_rmr *a) \ return false; \ } -GEN_OPFV_WIDEN_TRANS(vfwcvt_xu_f_v) -GEN_OPFV_WIDEN_TRANS(vfwcvt_x_f_v) -GEN_OPFV_WIDEN_TRANS(vfwcvt_f_xu_v) -GEN_OPFV_WIDEN_TRANS(vfwcvt_f_x_v) -GEN_OPFV_WIDEN_TRANS(vfwcvt_f_f_v) +GEN_OPFXV_WIDEN_TRANS(vfwcvt_f_xu_v) +GEN_OPFXV_WIDEN_TRANS(vfwcvt_f_x_v) /* Narrowing Floating-Point/Integer Type-Convert Instructions */ diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c index c19cd937e1a..dda8e2ab5a2 100644 --- a/target/riscv/vector_helper.c +++ b/target/riscv/vector_helper.c @@ -3773,6 +3773,7 @@ GEN_VEXT_V_ENV(vfcvt_f_x_v_d, 8, 8) /* Widening Floating-Point/Integer Type-Convert Instructions */ /* (TD, T2, TX2) */ +#define WOP_UU_B uint16_t, uint8_t, uint8_t #define WOP_UU_H uint32_t, uint16_t, uint16_t #define WOP_UU_W uint64_t, uint32_t, uint32_t /* vfwcvt.xu.f.v vd, vs2, vm # Convert float to double-width unsigned integer.*/ @@ -3788,19 +3789,23 @@ GEN_VEXT_V_ENV(vfwcvt_x_f_v_h, 2, 4) GEN_VEXT_V_ENV(vfwcvt_x_f_v_w, 4, 8) /* vfwcvt.f.xu.v vd, vs2, vm # Convert unsigned integer to double-width float */ +RVVCALL(OPFVV1, vfwcvt_f_xu_v_b, WOP_UU_B, H2, H1, uint8_to_float16) RVVCALL(OPFVV1, vfwcvt_f_xu_v_h, WOP_UU_H, H4, H2, uint16_to_float32) RVVCALL(OPFVV1, vfwcvt_f_xu_v_w, WOP_UU_W, H8, H4, uint32_to_float64) +GEN_VEXT_V_ENV(vfwcvt_f_xu_v_b, 1, 2) GEN_VEXT_V_ENV(vfwcvt_f_xu_v_h, 2, 4) GEN_VEXT_V_ENV(vfwcvt_f_xu_v_w, 4, 8) /* vfwcvt.f.x.v vd, vs2, vm # Convert integer to double-width float. */ +RVVCALL(OPFVV1, vfwcvt_f_x_v_b, WOP_UU_B, H2, H1, int8_to_float16) RVVCALL(OPFVV1, vfwcvt_f_x_v_h, WOP_UU_H, H4, H2, int16_to_float32) RVVCALL(OPFVV1, vfwcvt_f_x_v_w, WOP_UU_W, H8, H4, int32_to_float64) +GEN_VEXT_V_ENV(vfwcvt_f_x_v_b, 1, 2) GEN_VEXT_V_ENV(vfwcvt_f_x_v_h, 2, 4) GEN_VEXT_V_ENV(vfwcvt_f_x_v_w, 4, 8) /* - * vfwcvt.f.f.v vd, vs2, vm # + * vfwcvt.f.f.v vd, vs2, vm * Convert single-width float to double-width float. */ static uint32_t vfwcvtffv16(uint16_t a, float_status *s)