[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
Re: [PATCH v6 21/72] target/riscv: rvv-1.0: fault-only-first unit stride
|
From: |
Alistair Francis |
|
Subject: |
Re: [PATCH v6 21/72] target/riscv: rvv-1.0: fault-only-first unit stride load |
|
Date: |
Tue, 19 Jan 2021 11:19:43 -0800 |
On Tue, Jan 12, 2021 at 1:56 AM <frank.chang@sifive.com> wrote:
>
> From: Frank Chang <frank.chang@sifive.com>
>
> Signed-off-by: Frank Chang <frank.chang@sifive.com>
> Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
Alistair
> ---
> target/riscv/helper.h | 27 +++---------
> target/riscv/insn32.decode | 14 +++----
> target/riscv/insn_trans/trans_rvv.c.inc | 33 ++++-----------
> target/riscv/vector_helper.c | 56 +++++++++----------------
> 4 files changed, 39 insertions(+), 91 deletions(-)
>
> diff --git a/target/riscv/helper.h b/target/riscv/helper.h
> index 98c0c6e29b6..5eb2404a75a 100644
> --- a/target/riscv/helper.h
> +++ b/target/riscv/helper.h
> @@ -135,28 +135,11 @@ DEF_HELPER_6(vsxei64_8_v, void, ptr, ptr, tl, ptr, env,
> i32)
> DEF_HELPER_6(vsxei64_16_v, void, ptr, ptr, tl, ptr, env, i32)
> DEF_HELPER_6(vsxei64_32_v, void, ptr, ptr, tl, ptr, env, i32)
> DEF_HELPER_6(vsxei64_64_v, void, ptr, ptr, tl, ptr, env, i32)
> -DEF_HELPER_5(vlbff_v_b, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbff_v_h, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbff_v_d, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlhff_v_h, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlhff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlhff_v_d, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlwff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlwff_v_d, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vleff_v_b, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vleff_v_h, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vleff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vleff_v_d, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbuff_v_b, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbuff_v_h, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbuff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlbuff_v_d, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlhuff_v_h, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlhuff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlhuff_v_d, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlwuff_v_w, void, ptr, ptr, tl, env, i32)
> -DEF_HELPER_5(vlwuff_v_d, void, ptr, ptr, tl, env, i32)
> +DEF_HELPER_5(vle8ff_v, void, ptr, ptr, tl, env, i32)
> +DEF_HELPER_5(vle16ff_v, void, ptr, ptr, tl, env, i32)
> +DEF_HELPER_5(vle32ff_v, void, ptr, ptr, tl, env, i32)
> +DEF_HELPER_5(vle64ff_v, void, ptr, ptr, tl, env, i32)
> +
> #ifdef TARGET_RISCV64
> DEF_HELPER_6(vamoswapw_v_d, void, ptr, ptr, tl, ptr, env, i32)
> DEF_HELPER_6(vamoswapd_v_d, void, ptr, ptr, tl, ptr, env, i32)
> diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
> index c0058c6c756..9e4fe72560b 100644
> --- a/target/riscv/insn32.decode
> +++ b/target/riscv/insn32.decode
> @@ -260,14 +260,6 @@ vsse16_v ... 010 . ..... ..... 101 ..... 0100111
> @r_nfvm
> vsse32_v ... 010 . ..... ..... 110 ..... 0100111 @r_nfvm
> vsse64_v ... 010 . ..... ..... 111 ..... 0100111 @r_nfvm
>
> -vlbff_v ... 100 . 10000 ..... 000 ..... 0000111 @r2_nfvm
> -vlhff_v ... 100 . 10000 ..... 101 ..... 0000111 @r2_nfvm
> -vlwff_v ... 100 . 10000 ..... 110 ..... 0000111 @r2_nfvm
> -vleff_v ... 000 . 10000 ..... 111 ..... 0000111 @r2_nfvm
> -vlbuff_v ... 000 . 10000 ..... 000 ..... 0000111 @r2_nfvm
> -vlhuff_v ... 000 . 10000 ..... 101 ..... 0000111 @r2_nfvm
> -vlwuff_v ... 000 . 10000 ..... 110 ..... 0000111 @r2_nfvm
> -
> # Vector ordered-indexed and unordered-indexed load insns.
> vlxei8_v ... 0-1 . ..... ..... 000 ..... 0000111 @r_nfvm
> vlxei16_v ... 0-1 . ..... ..... 101 ..... 0000111 @r_nfvm
> @@ -280,6 +272,12 @@ vsxei16_v ... 0-1 . ..... ..... 101 ..... 0100111
> @r_nfvm
> vsxei32_v ... 0-1 . ..... ..... 110 ..... 0100111 @r_nfvm
> vsxei64_v ... 0-1 . ..... ..... 111 ..... 0100111 @r_nfvm
>
> +# Vector unit-stride fault-only-first load insns.
> +vle8ff_v ... 000 . 10000 ..... 000 ..... 0000111 @r2_nfvm
> +vle16ff_v ... 000 . 10000 ..... 101 ..... 0000111 @r2_nfvm
> +vle32ff_v ... 000 . 10000 ..... 110 ..... 0000111 @r2_nfvm
> +vle64ff_v ... 000 . 10000 ..... 111 ..... 0000111 @r2_nfvm
> +
> #*** Vector AMO operations are encoded under the standard AMO major opcode
> ***
> vamoswapw_v 00001 . . ..... ..... 110 ..... 0101111 @r_wdvm
> vamoaddw_v 00000 . . ..... ..... 110 ..... 0101111 @r_wdvm
> diff --git a/target/riscv/insn_trans/trans_rvv.c.inc
> b/target/riscv/insn_trans/trans_rvv.c.inc
> index 320d710695f..20161b1ebe3 100644
> --- a/target/riscv/insn_trans/trans_rvv.c.inc
> +++ b/target/riscv/insn_trans/trans_rvv.c.inc
> @@ -943,28 +943,16 @@ static bool ldff_trans(uint32_t vd, uint32_t rs1,
> uint32_t data,
> return true;
> }
>
> -static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
> +static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t eew)
> {
> uint32_t data = 0;
> gen_helper_ldst_us *fn;
> - static gen_helper_ldst_us * const fns[7][4] = {
> - { gen_helper_vlbff_v_b, gen_helper_vlbff_v_h,
> - gen_helper_vlbff_v_w, gen_helper_vlbff_v_d },
> - { NULL, gen_helper_vlhff_v_h,
> - gen_helper_vlhff_v_w, gen_helper_vlhff_v_d },
> - { NULL, NULL,
> - gen_helper_vlwff_v_w, gen_helper_vlwff_v_d },
> - { gen_helper_vleff_v_b, gen_helper_vleff_v_h,
> - gen_helper_vleff_v_w, gen_helper_vleff_v_d },
> - { gen_helper_vlbuff_v_b, gen_helper_vlbuff_v_h,
> - gen_helper_vlbuff_v_w, gen_helper_vlbuff_v_d },
> - { NULL, gen_helper_vlhuff_v_h,
> - gen_helper_vlhuff_v_w, gen_helper_vlhuff_v_d },
> - { NULL, NULL,
> - gen_helper_vlwuff_v_w, gen_helper_vlwuff_v_d }
> + static gen_helper_ldst_us * const fns[4] = {
> + gen_helper_vle8ff_v, gen_helper_vle16ff_v,
> + gen_helper_vle32ff_v, gen_helper_vle64ff_v
> };
>
> - fn = fns[seq][s->sew];
> + fn = fns[eew];
> if (fn == NULL) {
> return false;
> }
> @@ -975,13 +963,10 @@ static bool ldff_op(DisasContext *s, arg_r2nfvm *a,
> uint8_t seq)
> return ldff_trans(a->rd, a->rs1, data, fn, s);
> }
>
> -GEN_VEXT_TRANS(vlbff_v, 0, r2nfvm, ldff_op, ld_us_check)
> -GEN_VEXT_TRANS(vlhff_v, 1, r2nfvm, ldff_op, ld_us_check)
> -GEN_VEXT_TRANS(vlwff_v, 2, r2nfvm, ldff_op, ld_us_check)
> -GEN_VEXT_TRANS(vleff_v, 3, r2nfvm, ldff_op, ld_us_check)
> -GEN_VEXT_TRANS(vlbuff_v, 4, r2nfvm, ldff_op, ld_us_check)
> -GEN_VEXT_TRANS(vlhuff_v, 5, r2nfvm, ldff_op, ld_us_check)
> -GEN_VEXT_TRANS(vlwuff_v, 6, r2nfvm, ldff_op, ld_us_check)
> +GEN_VEXT_TRANS(vle8ff_v, MO_8, r2nfvm, ldff_op, ld_us_check)
> +GEN_VEXT_TRANS(vle16ff_v, MO_16, r2nfvm, ldff_op, ld_us_check)
> +GEN_VEXT_TRANS(vle32ff_v, MO_32, r2nfvm, ldff_op, ld_us_check)
> +GEN_VEXT_TRANS(vle64ff_v, MO_64, r2nfvm, ldff_op, ld_us_check)
>
> /*
> *** vector atomic operation
> diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
> index 9349a36b41b..fd398af8550 100644
> --- a/target/riscv/vector_helper.c
> +++ b/target/riscv/vector_helper.c
> @@ -458,7 +458,7 @@ static inline void
> vext_ldff(void *vd, void *v0, target_ulong base,
> CPURISCVState *env, uint32_t desc,
> vext_ldst_elem_fn *ldst_elem,
> - uint32_t esz, uint32_t msz, uintptr_t ra)
> + uint32_t esz, uintptr_t ra)
> {
> void *host;
> uint32_t i, k, vl = 0;
> @@ -472,24 +472,24 @@ vext_ldff(void *vd, void *v0, target_ulong base,
> if (!vm && !vext_elem_mask(v0, i)) {
> continue;
> }
> - addr = base + nf * i * msz;
> + addr = base + nf * i * esz;
> if (i == 0) {
> - probe_pages(env, addr, nf * msz, ra, MMU_DATA_LOAD);
> + probe_pages(env, addr, nf * esz, ra, MMU_DATA_LOAD);
> } else {
> /* if it triggers an exception, no need to check watchpoint */
> - remain = nf * msz;
> + remain = nf * esz;
> while (remain > 0) {
> offset = -(addr | TARGET_PAGE_MASK);
> host = tlb_vaddr_to_host(env, addr, MMU_DATA_LOAD,
> cpu_mmu_index(env, false));
> if (host) {
> #ifdef CONFIG_USER_ONLY
> - if (page_check_range(addr, nf * msz, PAGE_READ) < 0) {
> + if (page_check_range(addr, nf * esz, PAGE_READ) < 0) {
> vl = i;
> goto ProbeSuccess;
> }
> #else
> - probe_pages(env, addr, nf * msz, ra, MMU_DATA_LOAD);
> + probe_pages(env, addr, nf * esz, ra, MMU_DATA_LOAD);
> #endif
> } else {
> vl = i;
> @@ -514,43 +514,25 @@ ProbeSuccess:
> continue;
> }
> while (k < nf) {
> - target_ulong addr = base + (i * nf + k) * msz;
> + target_ulong addr = base + (i * nf + k) * esz;
> ldst_elem(env, addr, i + k * vlmax, vd, ra);
> k++;
> }
> }
> }
>
> -#define GEN_VEXT_LDFF(NAME, MTYPE, ETYPE, LOAD_FN) \
> -void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> - CPURISCVState *env, uint32_t desc) \
> -{ \
> - vext_ldff(vd, v0, base, env, desc, LOAD_FN, \
> - sizeof(ETYPE), sizeof(MTYPE), GETPC()); \
> -}
> -
> -GEN_VEXT_LDFF(vlbff_v_b, int8_t, int8_t, ldb_b)
> -GEN_VEXT_LDFF(vlbff_v_h, int8_t, int16_t, ldb_h)
> -GEN_VEXT_LDFF(vlbff_v_w, int8_t, int32_t, ldb_w)
> -GEN_VEXT_LDFF(vlbff_v_d, int8_t, int64_t, ldb_d)
> -GEN_VEXT_LDFF(vlhff_v_h, int16_t, int16_t, ldh_h)
> -GEN_VEXT_LDFF(vlhff_v_w, int16_t, int32_t, ldh_w)
> -GEN_VEXT_LDFF(vlhff_v_d, int16_t, int64_t, ldh_d)
> -GEN_VEXT_LDFF(vlwff_v_w, int32_t, int32_t, ldw_w)
> -GEN_VEXT_LDFF(vlwff_v_d, int32_t, int64_t, ldw_d)
> -GEN_VEXT_LDFF(vleff_v_b, int8_t, int8_t, lde_b)
> -GEN_VEXT_LDFF(vleff_v_h, int16_t, int16_t, lde_h)
> -GEN_VEXT_LDFF(vleff_v_w, int32_t, int32_t, lde_w)
> -GEN_VEXT_LDFF(vleff_v_d, int64_t, int64_t, lde_d)
> -GEN_VEXT_LDFF(vlbuff_v_b, uint8_t, uint8_t, ldbu_b)
> -GEN_VEXT_LDFF(vlbuff_v_h, uint8_t, uint16_t, ldbu_h)
> -GEN_VEXT_LDFF(vlbuff_v_w, uint8_t, uint32_t, ldbu_w)
> -GEN_VEXT_LDFF(vlbuff_v_d, uint8_t, uint64_t, ldbu_d)
> -GEN_VEXT_LDFF(vlhuff_v_h, uint16_t, uint16_t, ldhu_h)
> -GEN_VEXT_LDFF(vlhuff_v_w, uint16_t, uint32_t, ldhu_w)
> -GEN_VEXT_LDFF(vlhuff_v_d, uint16_t, uint64_t, ldhu_d)
> -GEN_VEXT_LDFF(vlwuff_v_w, uint32_t, uint32_t, ldwu_w)
> -GEN_VEXT_LDFF(vlwuff_v_d, uint32_t, uint64_t, ldwu_d)
> +#define GEN_VEXT_LDFF(NAME, ETYPE, LOAD_FN) \
> +void HELPER(NAME)(void *vd, void *v0, target_ulong base, \
> + CPURISCVState *env, uint32_t desc) \
> +{ \
> + vext_ldff(vd, v0, base, env, desc, LOAD_FN, \
> + sizeof(ETYPE), GETPC()); \
> +}
> +
> +GEN_VEXT_LDFF(vle8ff_v, int8_t, lde_b)
> +GEN_VEXT_LDFF(vle16ff_v, int16_t, lde_h)
> +GEN_VEXT_LDFF(vle32ff_v, int32_t, lde_w)
> +GEN_VEXT_LDFF(vle64ff_v, int64_t, lde_d)
>
> /*
> *** Vector AMO Operations (Zvamo)
> --
> 2.17.1
>
>
- Re: [PATCH v6 14/72] target/riscv: rvv-1.0: update check functions, (continued)
- [PATCH v6 16/72] target/riscv: rvv:1.0: add translation-time nan-box helper function, frank . chang, 2021/01/12
- [PATCH v6 17/72] target/riscv: rvv-1.0: configure instructions, frank . chang, 2021/01/12
- [PATCH v6 18/72] target/riscv: rvv-1.0: stride load and store instructions, frank . chang, 2021/01/12
- [PATCH v6 19/72] target/riscv: rvv-1.0: index load and store instructions, frank . chang, 2021/01/12
- [PATCH v6 21/72] target/riscv: rvv-1.0: fault-only-first unit stride load, frank . chang, 2021/01/12
- Re: [PATCH v6 21/72] target/riscv: rvv-1.0: fault-only-first unit stride load,
Alistair Francis <=
- [PATCH v6 20/72] target/riscv: rvv-1.0: fix address index overflow bug of indexed load/store insns, frank . chang, 2021/01/12
- [PATCH v6 23/72] target/riscv: rvv-1.0: load/store whole register instructions, frank . chang, 2021/01/12
- [PATCH v6 24/72] target/riscv: rvv-1.0: update vext_max_elems() for load/store insns, frank . chang, 2021/01/12
- [PATCH v6 25/72] target/riscv: rvv-1.0: take fractional LMUL into vector max elements calculation, frank . chang, 2021/01/12
- [PATCH v6 22/72] target/riscv: rvv-1.0: amo operations, frank . chang, 2021/01/12