From 06092b88b970acc642a4b370c03865561b806808 Mon Sep 17 00:00:00 2001 From: LIU Zhiwei Date: Fri, 5 Mar 2021 09:39:53 -0500 Subject: [PATCH] target/riscv: vector single-width floating-point add/subtract instructions Backports ce2a0343f441f0ee949690eabae5ab600397e2eb --- qemu/header_gen.py | 27 +++ qemu/riscv32.h | 27 +++ qemu/riscv64.h | 27 +++ qemu/target/riscv/helper.h | 29 +++ qemu/target/riscv/insn32.decode | 11 + qemu/target/riscv/insn_trans/trans_rvv.inc.c | 211 +++++++++++++++++++ qemu/target/riscv/vector_helper.c | 125 +++++++++++ 7 files changed, 457 insertions(+) diff --git a/qemu/header_gen.py b/qemu/header_gen.py index c29f8f00..5bf5ebee 100644 --- a/qemu/header_gen.py +++ b/qemu/header_gen.py @@ -6965,6 +6965,33 @@ riscv_symbols = ( 'helper_vnclip_vx_b', 'helper_vnclip_vx_h', 'helper_vnclip_vx_w', + 'helper_vfadd_vv_h', + 'helper_vfadd_vv_w', + 'helper_vfadd_vv_d', + 'helper_vfsub_vv_h', + 'helper_vfsub_vv_w', + 'helper_vfsub_vv_d', + 'helper_vfadd_vf_h', + 'helper_vfadd_vf_w', + 'helper_vfadd_vf_d', + 'helper_vfsub_vf_h', + 'helper_vfsub_vf_w', + 'helper_vfsub_vf_d', + 'helper_vfrsub_vf_h', + 'helper_vfrsub_vf_w', + 'helper_vfrsub_vf_d', + 'helper_vnsrl_vv_b', + 'helper_vnsrl_vv_h', + 'helper_vnsrl_vv_w', + 'helper_vnsra_vv_b', + 'helper_vnsra_vv_h', + 'helper_vnsra_vv_w', + 'helper_vnsrl_vx_b', + 'helper_vnsrl_vx_h', + 'helper_vnsrl_vx_w', + 'helper_vnsra_vx_b', + 'helper_vnsra_vx_h', + 'helper_vnsra_vx_w', 'pmp_hart_has_privs', 'pmpaddr_csr_read', 'pmpaddr_csr_write', diff --git a/qemu/riscv32.h b/qemu/riscv32.h index 3a900aca..ec06321c 100644 --- a/qemu/riscv32.h +++ b/qemu/riscv32.h @@ -4401,6 +4401,33 @@ #define helper_vnclip_vx_b helper_vnclip_vx_b_riscv32 #define helper_vnclip_vx_h helper_vnclip_vx_h_riscv32 #define helper_vnclip_vx_w helper_vnclip_vx_w_riscv32 +#define helper_vfadd_vv_h helper_vfadd_vv_h_riscv32 +#define helper_vfadd_vv_w helper_vfadd_vv_w_riscv32 +#define helper_vfadd_vv_d helper_vfadd_vv_d_riscv32 +#define helper_vfsub_vv_h helper_vfsub_vv_h_riscv32 +#define helper_vfsub_vv_w helper_vfsub_vv_w_riscv32 +#define helper_vfsub_vv_d helper_vfsub_vv_d_riscv32 +#define helper_vfadd_vf_h helper_vfadd_vf_h_riscv32 +#define helper_vfadd_vf_w helper_vfadd_vf_w_riscv32 +#define helper_vfadd_vf_d helper_vfadd_vf_d_riscv32 +#define helper_vfsub_vf_h helper_vfsub_vf_h_riscv32 +#define helper_vfsub_vf_w helper_vfsub_vf_w_riscv32 +#define helper_vfsub_vf_d helper_vfsub_vf_d_riscv32 +#define helper_vfrsub_vf_h helper_vfrsub_vf_h_riscv32 +#define helper_vfrsub_vf_w helper_vfrsub_vf_w_riscv32 +#define helper_vfrsub_vf_d helper_vfrsub_vf_d_riscv32 +#define helper_vnsrl_vv_b helper_vnsrl_vv_b_riscv32 +#define helper_vnsrl_vv_h helper_vnsrl_vv_h_riscv32 +#define helper_vnsrl_vv_w helper_vnsrl_vv_w_riscv32 +#define helper_vnsra_vv_b helper_vnsra_vv_b_riscv32 +#define helper_vnsra_vv_h helper_vnsra_vv_h_riscv32 +#define helper_vnsra_vv_w helper_vnsra_vv_w_riscv32 +#define helper_vnsrl_vx_b helper_vnsrl_vx_b_riscv32 +#define helper_vnsrl_vx_h helper_vnsrl_vx_h_riscv32 +#define helper_vnsrl_vx_w helper_vnsrl_vx_w_riscv32 +#define helper_vnsra_vx_b helper_vnsra_vx_b_riscv32 +#define helper_vnsra_vx_h helper_vnsra_vx_h_riscv32 +#define helper_vnsra_vx_w helper_vnsra_vx_w_riscv32 #define pmp_hart_has_privs pmp_hart_has_privs_riscv32 #define pmpaddr_csr_read pmpaddr_csr_read_riscv32 #define pmpaddr_csr_write pmpaddr_csr_write_riscv32 diff --git a/qemu/riscv64.h b/qemu/riscv64.h index 789bc82e..ac256844 100644 --- a/qemu/riscv64.h +++ b/qemu/riscv64.h @@ -4401,6 +4401,33 @@ #define helper_vnclip_vx_b helper_vnclip_vx_b_riscv64 #define helper_vnclip_vx_h helper_vnclip_vx_h_riscv64 #define helper_vnclip_vx_w helper_vnclip_vx_w_riscv64 +#define helper_vfadd_vv_h helper_vfadd_vv_h_riscv64 +#define helper_vfadd_vv_w helper_vfadd_vv_w_riscv64 +#define helper_vfadd_vv_d helper_vfadd_vv_d_riscv64 +#define helper_vfsub_vv_h helper_vfsub_vv_h_riscv64 +#define helper_vfsub_vv_w helper_vfsub_vv_w_riscv64 +#define helper_vfsub_vv_d helper_vfsub_vv_d_riscv64 +#define helper_vfadd_vf_h helper_vfadd_vf_h_riscv64 +#define helper_vfadd_vf_w helper_vfadd_vf_w_riscv64 +#define helper_vfadd_vf_d helper_vfadd_vf_d_riscv64 +#define helper_vfsub_vf_h helper_vfsub_vf_h_riscv64 +#define helper_vfsub_vf_w helper_vfsub_vf_w_riscv64 +#define helper_vfsub_vf_d helper_vfsub_vf_d_riscv64 +#define helper_vfrsub_vf_h helper_vfrsub_vf_h_riscv64 +#define helper_vfrsub_vf_w helper_vfrsub_vf_w_riscv64 +#define helper_vfrsub_vf_d helper_vfrsub_vf_d_riscv64 +#define helper_vnsrl_vv_b helper_vnsrl_vv_b_riscv64 +#define helper_vnsrl_vv_h helper_vnsrl_vv_h_riscv64 +#define helper_vnsrl_vv_w helper_vnsrl_vv_w_riscv64 +#define helper_vnsra_vv_b helper_vnsra_vv_b_riscv64 +#define helper_vnsra_vv_h helper_vnsra_vv_h_riscv64 +#define helper_vnsra_vv_w helper_vnsra_vv_w_riscv64 +#define helper_vnsrl_vx_b helper_vnsrl_vx_b_riscv64 +#define helper_vnsrl_vx_h helper_vnsrl_vx_h_riscv64 +#define helper_vnsrl_vx_w helper_vnsrl_vx_w_riscv64 +#define helper_vnsra_vx_b helper_vnsra_vx_b_riscv64 +#define helper_vnsra_vx_h helper_vnsra_vx_h_riscv64 +#define helper_vnsra_vx_w helper_vnsra_vx_w_riscv64 #define pmp_hart_has_privs pmp_hart_has_privs_riscv64 #define pmpaddr_csr_read pmpaddr_csr_read_riscv64 #define pmpaddr_csr_write pmpaddr_csr_write_riscv64 diff --git a/qemu/target/riscv/helper.h b/qemu/target/riscv/helper.h index bc8c2c37..1a915f8c 100644 --- a/qemu/target/riscv/helper.h +++ b/qemu/target/riscv/helper.h @@ -436,6 +436,19 @@ DEF_HELPER_6(vsra_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vsra_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vsra_vx_d, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsrl_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsrl_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsrl_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsra_vv_b, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsra_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsra_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vnsrl_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsrl_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsrl_vx_w, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsra_vx_b, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsra_vx_h, void, ptr, ptr, tl, ptr, env, i32) +DEF_HELPER_6(vnsra_vx_w, void, ptr, ptr, tl, ptr, env, i32) + DEF_HELPER_6(vmseq_vv_b, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vmseq_vv_h, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_6(vmseq_vv_w, void, ptr, ptr, ptr, ptr, env, i32) @@ -793,3 +806,19 @@ DEF_HELPER_6(vnclipu_vx_w, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnclip_vx_b, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnclip_vx_h, void, ptr, ptr, tl, ptr, env, i32) DEF_HELPER_6(vnclip_vx_w, void, ptr, ptr, tl, ptr, env, i32) + +DEF_HELPER_6(vfadd_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_h, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_w, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfsub_vv_d, void, ptr, ptr, ptr, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfadd_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_h, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_w, void, ptr, ptr, i64, ptr, env, i32) +DEF_HELPER_6(vfrsub_vf_d, void, ptr, ptr, i64, ptr, env, i32) diff --git a/qemu/target/riscv/insn32.decode b/qemu/target/riscv/insn32.decode index 80cf5413..9e26ed36 100644 --- a/qemu/target/riscv/insn32.decode +++ b/qemu/target/riscv/insn32.decode @@ -332,6 +332,12 @@ vsrl_vi 101000 . ..... ..... 011 ..... 1010111 @r_vm vsra_vv 101001 . ..... ..... 000 ..... 1010111 @r_vm vsra_vx 101001 . ..... ..... 100 ..... 1010111 @r_vm vsra_vi 101001 . ..... ..... 011 ..... 1010111 @r_vm +vnsrl_vv 101100 . ..... ..... 000 ..... 1010111 @r_vm +vnsrl_vx 101100 . ..... ..... 100 ..... 1010111 @r_vm +vnsrl_vi 101100 . ..... ..... 011 ..... 1010111 @r_vm +vnsra_vv 101101 . ..... ..... 000 ..... 1010111 @r_vm +vnsra_vx 101101 . ..... ..... 100 ..... 1010111 @r_vm +vnsra_vi 101101 . ..... ..... 011 ..... 1010111 @r_vm vmseq_vv 011000 . ..... ..... 000 ..... 1010111 @r_vm vmseq_vx 011000 . ..... ..... 100 ..... 1010111 @r_vm vmseq_vi 011000 . ..... ..... 011 ..... 1010111 @r_vm @@ -439,6 +445,11 @@ vnclipu_vi 101110 . ..... ..... 011 ..... 1010111 @r_vm vnclip_vv 101111 . ..... ..... 000 ..... 1010111 @r_vm vnclip_vx 101111 . ..... ..... 100 ..... 1010111 @r_vm vnclip_vi 101111 . ..... ..... 011 ..... 1010111 @r_vm +vfadd_vv 000000 . ..... ..... 001 ..... 1010111 @r_vm +vfadd_vf 000000 . ..... ..... 101 ..... 1010111 @r_vm +vfsub_vv 000010 . ..... ..... 001 ..... 1010111 @r_vm +vfsub_vf 000010 . ..... ..... 101 ..... 1010111 @r_vm +vfrsub_vf 100111 . ..... ..... 101 ..... 1010111 @r_vm vsetvli 0 ........... ..... 111 ..... 1010111 @r2_zimm vsetvl 1000000 ..... ..... 111 ..... 1010111 @r diff --git a/qemu/target/riscv/insn_trans/trans_rvv.inc.c b/qemu/target/riscv/insn_trans/trans_rvv.inc.c index 677bbba4..ead8c136 100644 --- a/qemu/target/riscv/insn_trans/trans_rvv.inc.c +++ b/qemu/target/riscv/insn_trans/trans_rvv.inc.c @@ -1447,6 +1447,97 @@ GEN_OPIVI_GVEC_TRANS(vsll_vi, 1, vsll_vx, shli) GEN_OPIVI_GVEC_TRANS(vsrl_vi, 1, vsrl_vx, shri) GEN_OPIVI_GVEC_TRANS(vsra_vi, 1, vsra_vx, sari) +/* Vector Narrowing Integer Right Shift Instructions */ +static bool opivv_narrow_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, true) && + vext_check_reg(s, a->rs1, false) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, + 2 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +/* OPIVV with NARROW */ +#define GEN_OPIVV_NARROW_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + TCGContext *tcg_ctx = s->uc->tcg_ctx; \ + if (opivv_narrow_check(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_4_ptr * const fns[3] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + }; \ + TCGLabel *over = gen_new_label(tcg_ctx); \ + tcg_gen_brcondi_tl(tcg_ctx, TCG_COND_EQ, tcg_ctx->cpu_vl_risc, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_4_ptr(tcg_ctx, vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs1), \ + vreg_ofs(s, a->rs2), tcg_ctx->cpu_env, 0, \ + s->vlen / 8, data, fns[s->sew]); \ + gen_set_label(tcg_ctx, over); \ + return true; \ + } \ + return false; \ +} +GEN_OPIVV_NARROW_TRANS(vnsra_vv) +GEN_OPIVV_NARROW_TRANS(vnsrl_vv) + +static bool opivx_narrow_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, true) && + vext_check_overlap_group(a->rd, 1 << s->lmul, a->rs2, + 2 << s->lmul) && + (s->lmul < 0x3) && (s->sew < 0x3)); +} + +/* OPIVX with NARROW */ +#define GEN_OPIVX_NARROW_TRANS(NAME) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opivx_narrow_check(s, a)) { \ + static gen_helper_opivx * const fns[3] = { \ + gen_helper_##NAME##_b, \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + }; \ + return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);\ + } \ + return false; \ +} + +GEN_OPIVX_NARROW_TRANS(vnsra_vx) +GEN_OPIVX_NARROW_TRANS(vnsrl_vx) + +/* OPIVI with NARROW */ +#define GEN_OPIVI_NARROW_TRANS(NAME, ZX, OPIVX) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (opivx_narrow_check(s, a)) { \ + static gen_helper_opivx * const fns[3] = { \ + gen_helper_##OPIVX##_b, \ + gen_helper_##OPIVX##_h, \ + gen_helper_##OPIVX##_w, \ + }; \ + return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, \ + fns[s->sew], s, ZX); \ + } \ + return false; \ +} + +GEN_OPIVI_NARROW_TRANS(vnsra_vi, 1, vnsra_vx) +GEN_OPIVI_NARROW_TRANS(vnsrl_vi, 1, vnsrl_vx) + /* Vector Integer Comparison Instructions */ /* * For all comparison instructions, an illegal instruction exception is raised @@ -1720,3 +1811,123 @@ GEN_OPIVX_NARROW_TRANS(vnclipu_vx) GEN_OPIVX_NARROW_TRANS(vnclip_vx) GEN_OPIVI_NARROW_TRANS(vnclipu_vi, 1, vnclipu_vx) GEN_OPIVI_NARROW_TRANS(vnclip_vi, 1, vnclip_vx) + +/* + *** Vector Float Point Arithmetic Instructions + */ +/* Vector Single-Width Floating-Point Add/Subtract Instructions */ + +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised. + */ +static bool opfvv_check(DisasContext *s, arg_rmrr *a) +{ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + vext_check_reg(s, a->rs1, false) && + (s->sew != 0)); +} + +/* OPFVV without GVEC IR */ +#define GEN_OPFVV_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + TCGContext *tcg_ctx = s->uc->tcg_ctx; \ + if (CHECK(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_gvec_4_ptr * const fns[3] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + TCGLabel *over = gen_new_label(tcg_ctx); \ + gen_set_rm(s, 7); \ + tcg_gen_brcondi_tl(tcg_ctx, TCG_COND_EQ, tcg_ctx->cpu_vl_risc, 0, over); \ + \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + tcg_gen_gvec_4_ptr(tcg_ctx, vreg_ofs(s, a->rd), vreg_ofs(s, 0), \ + vreg_ofs(s, a->rs1), \ + vreg_ofs(s, a->rs2), tcg_ctx->cpu_env, 0, \ + s->vlen / 8, data, fns[s->sew - 1]); \ + gen_set_label(tcg_ctx, over); \ + return true; \ + } \ + return false; \ +} +GEN_OPFVV_TRANS(vfadd_vv, opfvv_check) +GEN_OPFVV_TRANS(vfsub_vv, opfvv_check) + +typedef void gen_helper_opfvf(TCGContext *, TCGv_ptr, TCGv_ptr, TCGv_i64, TCGv_ptr, + TCGv_env, TCGv_i32); + +static bool opfvf_trans(uint32_t vd, uint32_t rs1, uint32_t vs2, + uint32_t data, gen_helper_opfvf *fn, DisasContext *s) +{ + TCGContext *tcg_ctx = s->uc->tcg_ctx; + TCGv_ptr dest, src2, mask; + TCGv_i32 desc; + + TCGLabel *over = gen_new_label(tcg_ctx); + tcg_gen_brcondi_tl(tcg_ctx, TCG_COND_EQ, tcg_ctx->cpu_vl_risc, 0, over); + + dest = tcg_temp_new_ptr(tcg_ctx); + mask = tcg_temp_new_ptr(tcg_ctx); + src2 = tcg_temp_new_ptr(tcg_ctx); + desc = tcg_const_i32(tcg_ctx, simd_desc(0, s->vlen / 8, data)); + + tcg_gen_addi_ptr(tcg_ctx, dest, tcg_ctx->cpu_env, vreg_ofs(s, vd)); + tcg_gen_addi_ptr(tcg_ctx, src2, tcg_ctx->cpu_env, vreg_ofs(s, vs2)); + tcg_gen_addi_ptr(tcg_ctx, mask, tcg_ctx->cpu_env, vreg_ofs(s, 0)); + + fn(tcg_ctx, dest, mask, tcg_ctx->cpu_fpr_risc[rs1], src2, tcg_ctx->cpu_env, desc); + + tcg_temp_free_ptr(tcg_ctx, dest); + tcg_temp_free_ptr(tcg_ctx, mask); + tcg_temp_free_ptr(tcg_ctx, src2); + tcg_temp_free_i32(tcg_ctx, desc); + gen_set_label(tcg_ctx, over); + return true; +} + +static bool opfvf_check(DisasContext *s, arg_rmrr *a) +{ +/* + * If the current SEW does not correspond to a supported IEEE floating-point + * type, an illegal instruction exception is raised + */ + return (vext_check_isa_ill(s) && + vext_check_overlap_mask(s, a->rd, a->vm, false) && + vext_check_reg(s, a->rd, false) && + vext_check_reg(s, a->rs2, false) && + (s->sew != 0)); +} + +/* OPFVF without GVEC IR */ +#define GEN_OPFVF_TRANS(NAME, CHECK) \ +static bool trans_##NAME(DisasContext *s, arg_rmrr *a) \ +{ \ + if (CHECK(s, a)) { \ + uint32_t data = 0; \ + static gen_helper_opfvf *const fns[3] = { \ + gen_helper_##NAME##_h, \ + gen_helper_##NAME##_w, \ + gen_helper_##NAME##_d, \ + }; \ + gen_set_rm(s, 7); \ + data = FIELD_DP32(data, VDATA, MLEN, s->mlen); \ + data = FIELD_DP32(data, VDATA, VM, a->vm); \ + data = FIELD_DP32(data, VDATA, LMUL, s->lmul); \ + return opfvf_trans(a->rd, a->rs1, a->rs2, data, \ + fns[s->sew - 1], s); \ + } \ + return false; \ +} + +GEN_OPFVF_TRANS(vfadd_vf, opfvf_check) +GEN_OPFVF_TRANS(vfsub_vf, opfvf_check) +GEN_OPFVF_TRANS(vfrsub_vf, opfvf_check) diff --git a/qemu/target/riscv/vector_helper.c b/qemu/target/riscv/vector_helper.c index c1e1c1e8..28fbd023 100644 --- a/qemu/target/riscv/vector_helper.c +++ b/qemu/target/riscv/vector_helper.c @@ -22,6 +22,7 @@ #include "exec/memop.h" #include "exec/exec-all.h" #include "exec/helper-proto.h" +#include "fpu/softfloat.h" #include "tcg/tcg-gvec-desc.h" #include "internals.h" #include @@ -1423,6 +1424,20 @@ GEN_VEXT_SHIFT_VX(vsra_vx_h, int16_t, int16_t, H2, H2, DO_SRL, 0xf, clearh) GEN_VEXT_SHIFT_VX(vsra_vx_w, int32_t, int32_t, H4, H4, DO_SRL, 0x1f, clearl) GEN_VEXT_SHIFT_VX(vsra_vx_d, int64_t, int64_t, H8, H8, DO_SRL, 0x3f, clearq) +/* Vector Narrowing Integer Right Shift Instructions */ +GEN_VEXT_SHIFT_VV(vnsrl_vv_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VV(vnsrl_vv_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VV(vnsrl_vv_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f, clearl) +GEN_VEXT_SHIFT_VV(vnsra_vv_b, uint8_t, int16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VV(vnsra_vv_h, uint16_t, int32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VV(vnsra_vv_w, uint32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl) +GEN_VEXT_SHIFT_VX(vnsrl_vx_b, uint8_t, uint16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VX(vnsrl_vx_h, uint16_t, uint32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VX(vnsrl_vx_w, uint32_t, uint64_t, H4, H8, DO_SRL, 0x3f, clearl) +GEN_VEXT_SHIFT_VX(vnsra_vx_b, int8_t, int16_t, H1, H2, DO_SRL, 0xf, clearb) +GEN_VEXT_SHIFT_VX(vnsra_vx_h, int16_t, int32_t, H2, H4, DO_SRL, 0x1f, clearh) +GEN_VEXT_SHIFT_VX(vnsra_vx_w, int32_t, int64_t, H4, H8, DO_SRL, 0x3f, clearl) + /* Vector Integer Comparison Instructions */ #define DO_MSEQ(N, M) (N == M) #define DO_MSNE(N, M) (N != M) @@ -3154,3 +3169,113 @@ RVVCALL(OPIVX2_RM, vnclipu_vx_w, NOP_UUU_W, H4, H8, vnclipu32) GEN_VEXT_VX_RM(vnclipu_vx_b, 1, 1, clearb) GEN_VEXT_VX_RM(vnclipu_vx_h, 2, 2, clearh) GEN_VEXT_VX_RM(vnclipu_vx_w, 4, 4, clearl) + +/* + *** Vector Float Point Arithmetic Instructions + */ +/* Vector Single-Width Floating-Point Add/Subtract Instructions */ +#define OPFVV2(NAME, TD, T1, T2, TX1, TX2, HD, HS1, HS2, OP) \ +static void do_##NAME(void *vd, void *vs1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX1 s1 = *((T1 *)vs1 + HS1(i)); \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, s1, &env->fp_status); \ +} + +#define GEN_VEXT_VV_ENV(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, void *vs1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vlmax = vext_maxsz(desc) / ESZ; \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + do_##NAME(vd, vs1, vs2, i, env); \ + } \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ +} + +RVVCALL(OPFVV2, vfadd_vv_h, OP_UUU_H, H2, H2, H2, float16_add) +RVVCALL(OPFVV2, vfadd_vv_w, OP_UUU_W, H4, H4, H4, float32_add) +RVVCALL(OPFVV2, vfadd_vv_d, OP_UUU_D, H8, H8, H8, float64_add) +GEN_VEXT_VV_ENV(vfadd_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfadd_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfadd_vv_d, 8, 8, clearq) + +#define OPFVF2(NAME, TD, T1, T2, TX1, TX2, HD, HS2, OP) \ +static void do_##NAME(void *vd, uint64_t s1, void *vs2, int i, \ + CPURISCVState *env) \ +{ \ + TX2 s2 = *((T2 *)vs2 + HS2(i)); \ + *((TD *)vd + HD(i)) = OP(s2, (TX1)(T1)s1, &env->fp_status);\ +} + +#define GEN_VEXT_VF(NAME, ESZ, DSZ, CLEAR_FN) \ +void HELPER(NAME)(void *vd, void *v0, uint64_t s1, \ + void *vs2, CPURISCVState *env, \ + uint32_t desc) \ +{ \ + uint32_t vlmax = vext_maxsz(desc) / ESZ; \ + uint32_t mlen = vext_mlen(desc); \ + uint32_t vm = vext_vm(desc); \ + uint32_t vl = env->vl; \ + uint32_t i; \ + \ + for (i = 0; i < vl; i++) { \ + if (!vm && !vext_elem_mask(v0, mlen, i)) { \ + continue; \ + } \ + do_##NAME(vd, s1, vs2, i, env); \ + } \ + CLEAR_FN(vd, vl, vl * DSZ, vlmax * DSZ); \ +} + +RVVCALL(OPFVF2, vfadd_vf_h, OP_UUU_H, H2, H2, float16_add) +RVVCALL(OPFVF2, vfadd_vf_w, OP_UUU_W, H4, H4, float32_add) +RVVCALL(OPFVF2, vfadd_vf_d, OP_UUU_D, H8, H8, float64_add) +GEN_VEXT_VF(vfadd_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfadd_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfadd_vf_d, 8, 8, clearq) + +RVVCALL(OPFVV2, vfsub_vv_h, OP_UUU_H, H2, H2, H2, float16_sub) +RVVCALL(OPFVV2, vfsub_vv_w, OP_UUU_W, H4, H4, H4, float32_sub) +RVVCALL(OPFVV2, vfsub_vv_d, OP_UUU_D, H8, H8, H8, float64_sub) +GEN_VEXT_VV_ENV(vfsub_vv_h, 2, 2, clearh) +GEN_VEXT_VV_ENV(vfsub_vv_w, 4, 4, clearl) +GEN_VEXT_VV_ENV(vfsub_vv_d, 8, 8, clearq) +RVVCALL(OPFVF2, vfsub_vf_h, OP_UUU_H, H2, H2, float16_sub) +RVVCALL(OPFVF2, vfsub_vf_w, OP_UUU_W, H4, H4, float32_sub) +RVVCALL(OPFVF2, vfsub_vf_d, OP_UUU_D, H8, H8, float64_sub) +GEN_VEXT_VF(vfsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfsub_vf_d, 8, 8, clearq) + +static uint16_t float16_rsub(uint16_t a, uint16_t b, float_status *s) +{ + return float16_sub(b, a, s); +} + +static uint32_t float32_rsub(uint32_t a, uint32_t b, float_status *s) +{ + return float32_sub(b, a, s); +} + +static uint64_t float64_rsub(uint64_t a, uint64_t b, float_status *s) +{ + return float64_sub(b, a, s); +} + +RVVCALL(OPFVF2, vfrsub_vf_h, OP_UUU_H, H2, H2, float16_rsub) +RVVCALL(OPFVF2, vfrsub_vf_w, OP_UUU_W, H4, H4, float32_rsub) +RVVCALL(OPFVF2, vfrsub_vf_d, OP_UUU_D, H8, H8, float64_rsub) +GEN_VEXT_VF(vfrsub_vf_h, 2, 2, clearh) +GEN_VEXT_VF(vfrsub_vf_w, 4, 4, clearl) +GEN_VEXT_VF(vfrsub_vf_d, 8, 8, clearq)