[RFC,v2,15/76] target/riscv: rvv-0.9: add fractional LMUL

Message ID	20200722091641.8834-16-frank.chang@sifive.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <SRS0=6956=BB=nongnu.org=qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@kernel.org> DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org CEC05206D7 From: frank.chang@sifive.com To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org Subject: [RFC v2 15/76] target/riscv: rvv-0.9: add fractional LMUL Date: Wed, 22 Jul 2020 17:15:38 +0800 Message-Id: <20200722091641.8834-16-frank.chang@sifive.com> In-Reply-To: <20200722091641.8834-1-frank.chang@sifive.com> References: <20200722091641.8834-1-frank.chang@sifive.com> Received-SPF: pass client-ip=2607:f8b0:4864:20::1031; envelope-from=frank.chang@sifive.com; helo=mail-pj1-x1031.google.com Precedence: list Cc: Sagar Karandikar <sagark@eecs.berkeley.edu>, Frank Chang <frank.chang@sifive.com>, Bastian Koppelmann <kbastian@mail.uni-paderborn.de>, Richard Henderson <richard.henderson@linaro.org>, Alistair Francis <Alistair.Francis@wdc.com>, Palmer Dabbelt <palmer@dabbelt.com>, LIU Zhiwei <zhiwei_liu@c-sky.com> Errors-To: qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org Sender: "Qemu-devel" <qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org>
Series	target/riscv: support vector extension v0.9 \| expand [RFC,v2,00/76] target/riscv: support vector extension v0.9 [RFC,v2,01/76] target/riscv: drop vector 0.7.1 support [RFC,v2,02/76] target/riscv: rvv-0.9: support vector 0.9 [RFC,v2,03/76] target/riscv: fix rsub gvec tcg_assert_listed_vecop assertion [RFC,v2,04/76] target/riscv: correct the gvec IR called in gen_vec_rsub16_i64() [RFC,v2,05/76] target/riscv: fix return value of do_opivx_widen() [RFC,v2,06/76] target/riscv: fix vill bit index in vtype register [RFC,v2,07/76] target/riscv: Use FIELD_EX32() to extract wd field [RFC,v2,08/76] target/riscv: rvv-0.9: add mstatus VS field [RFC,v2,09/76] target/riscv: rvv-0.9: add sstatus VS field [RFC,v2,10/76] target/riscv: rvv-0.9: add translation-time vector context status [RFC,v2,11/76] target/riscv: rvv-0.9: remove vxrm and vxsat fields from fcsr register [RFC,v2,12/76] target/riscv: rvv-0.9: add vcsr register [RFC,v2,13/76] target/riscv: rvv-0.9: add vlenb register [RFC,v2,14/76] target/riscv: rvv-0.9: remove MLEN calculations [RFC,v2,15/76] target/riscv: rvv-0.9: add fractional LMUL [RFC,v2,16/76] target/riscv: rvv-0.9: add VMA and VTA [RFC,v2,17/76] target/riscv: rvv-0.9: update check functions [RFC,v2,18/76] target/riscv: introduce more imm value modes in translator functions [RFC,v2,19/76] target/riscv: rvv-0.9: add narrower_nanbox_fpr helper [RFC,v2,20/76] target/riscv: rvv-0.9: apply narrower nanbox helper in opfvf_trans [RFC,v2,21/76] target/riscv: rvv-0.9: configure instructions [RFC,v2,22/76] target/riscv: rvv-0.9: stride load and store instructions [RFC,v2,23/76] target/riscv: rvv-0.9: index load and store instructions [RFC,v2,24/76] target/riscv: rvv-0.9: fix address index overflow bug of indexed load/store insns [RFC,v2,25/76] target/riscv: rvv-0.9: fault-only-first unit stride load [RFC,v2,26/76] target/riscv: rvv-0.9: amo operations [RFC,v2,27/76] target/riscv: rvv-0.9: load/store whole register instructions [RFC,v2,28/76] target/riscv: rvv-0.9: update vext_max_elems() for load/store insns [RFC,v2,29/76] target/riscv: rvv-0.9: take fractional LMUL into vector max elements calculation [RFC,v2,30/76] target/riscv: rvv-0.9: floating-point square-root instruction [RFC,v2,31/76] target/riscv: rvv-0.9: floating-point classify instructions [RFC,v2,32/76] target/riscv: rvv-0.9: mask population count instruction [RFC,v2,33/76] target/riscv: rvv-0.9: find-first-set mask bit instruction [RFC,v2,34/76] target/riscv: rvv-0.9: set-X-first mask bit instructions [RFC,v2,35/76] target/riscv: rvv-0.9: iota instruction [RFC,v2,36/76] target/riscv: rvv-0.9: element index instruction [RFC,v2,37/76] target/riscv: rvv-0.9: allow load element with sign-extended [RFC,v2,38/76] target/riscv: rvv-0.9: register gather instructions [RFC,v2,39/76] target/riscv: rvv-0.9: integer scalar move instructions [RFC,v2,40/76] target/riscv: rvv-0.9: floating-point move instruction [RFC,v2,41/76] target/riscv: rvv-0.9: floating-point scalar move instructions [RFC,v2,42/76] target/riscv: rvv-0.9: whole register move instructions [RFC,v2,43/76] target/riscv: rvv-0.9: integer extension instructions [RFC,v2,44/76] target/riscv: rvv-0.9: single-width averaging add and subtract instructions [RFC,v2,45/76] target/riscv: rvv-0.9: single-width bit shift instructions [RFC,v2,46/76] target/riscv: rvv-0.9: integer add-with-carry/subtract-with-borrow [RFC,v2,47/76] target/riscv: rvv-0.9: narrowing integer right shift instructions [RFC,v2,48/76] target/riscv: rvv-0.9: widening integer multiply-add instructions [RFC,v2,49/76] target/riscv: rvv-0.9: quad-widening integer multiply-add instructions [RFC,v2,50/76] target/riscv: rvv-0.9: single-width saturating add and subtract instructions [RFC,v2,51/76] target/riscv: rvv-0.9: integer comparison instructions [RFC,v2,52/76] fpu: implement full set compare for fp16 [RFC,v2,53/76] target/riscv: use softfloat lib float16 comparison functions [RFC,v2,54/76] target/riscv: rvv-0.9: floating-point compare instructions [RFC,v2,55/76] target/riscv: rvv-0.9: single-width integer reduction instructions [RFC,v2,56/76] target/riscv: rvv-0.9: widening integer reduction instructions [RFC,v2,57/76] target/riscv: rvv-0.9: mask-register logical instructions [RFC,v2,58/76] target/riscv: rvv-0.9: slide instructions [RFC,v2,59/76] target/riscv: rvv-0.9: floating-point slide instructions [RFC,v2,60/76] target/riscv: rvv-0.9: narrowing fixed-point clip instructions [RFC,v2,61/76] target/riscv: rvv-0.9: floating-point/integer type-convert instructions [RFC,v2,62/76] target/riscv: rvv-0.9: single-width floating-point reduction [RFC,v2,63/76] target/riscv: rvv-0.9: widening floating-point reduction instructions [RFC,v2,64/76] target/riscv: rvv-0.9: single-width scaling shift instructions [RFC,v2,65/76] target/riscv: rvv-0.9: remove widening saturating scaled multiply-add [RFC,v2,66/76] target/riscv: rvv-0.9: remove vmford.vv and vmford.vf [RFC,v2,67/76] target/riscv: rvv-0.9: remove integer extract instruction [RFC,v2,68/76] fpu: add api to handle alternative sNaN propagation [RFC,v2,69/76] target/riscv: rvv-0.9: floating-point min/max instructions [RFC,v2,70/76] softfloat: add fp16 and uint8/int8 interconvert functions [RFC,v2,71/76] target/riscv: rvv-0.9: widening floating-point/integer type-convert [RFC,v2,72/76] target/riscv: rvv-0.9: narrowing floating-point/integer type-convert [RFC,v2,73/76] fpu: fix float16 nan check [RFC,v2,74/76] target/riscv: gdb: modify gdb csr xml file to align with csr register map [RFC,v2,75/76] target/riscv: gdb: support vector registers for rv64 [RFC,v2,76/76] target/riscv: gdb: support vector registers for rv32

Message ID

20200722091641.8834-16-frank.chang@sifive.com (mailing list archive)

State

New, archived

Headers

DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org CEC05206D7
From: frank.chang@sifive.com
To: qemu-devel@nongnu.org,
	qemu-riscv@nongnu.org
Subject: [RFC v2 15/76] target/riscv: rvv-0.9: add fractional LMUL
Date: Wed, 22 Jul 2020 17:15:38 +0800
Message-Id: <20200722091641.8834-16-frank.chang@sifive.com>
In-Reply-To: <20200722091641.8834-1-frank.chang@sifive.com>
References: <20200722091641.8834-1-frank.chang@sifive.com>
Received-SPF: pass client-ip=2607:f8b0:4864:20::1031;
 envelope-from=frank.chang@sifive.com; helo=mail-pj1-x1031.google.com
X-Spam_score_int: -20
X-Spam_score: -2.1
X-Spam_bar: --
X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1,
 DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1,
 RCVD_IN_DNSWL_NONE=-0.0001, SPF_HELO_NONE=0.001, SPF_PASS=-0.001,
 URIBL_BLOCKED=0.001 autolearn=unavailable autolearn_force=no
X-Spam_action: no action
X-BeenThere: qemu-devel@nongnu.org
X-Mailman-Version: 2.1.23
Precedence: list
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
 <mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <https://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
 <mailto:qemu-devel-request@nongnu.org?subject=subscribe>
Cc: Sagar Karandikar <sagark@eecs.berkeley.edu>,
 Frank Chang <frank.chang@sifive.com>,
 Bastian Koppelmann <kbastian@mail.uni-paderborn.de>,
 Richard Henderson <richard.henderson@linaro.org>,
 Alistair Francis <Alistair.Francis@wdc.com>,
 Palmer Dabbelt <palmer@dabbelt.com>, LIU Zhiwei <zhiwei_liu@c-sky.com>
Errors-To: 
 qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org
Sender: "Qemu-devel"
 <qemu-devel-bounces+patchwork-qemu-devel=patchwork.kernel.org@nongnu.org>

Series

target/riscv: support vector extension v0.9 | expand

Commit Message

Frank Chang July 22, 2020, 9:15 a.m. UTC

From: Frank Chang <frank.chang@sifive.com>

Introduce the concepts of fractional LMUL, EEW and EMUL for RVV 0.9.

Signed-off-by: Frank Chang <frank.chang@sifive.com>
---
 target/riscv/cpu.h                      | 16 ++++++++++------
 target/riscv/insn_trans/trans_rvv.inc.c | 17 ++++++++++++++---
 target/riscv/internals.h                | 11 +++++++++--
 target/riscv/translate.c                |  4 ++++
 target/riscv/vector_helper.c            | 10 ++++++++--
 5 files changed, 45 insertions(+), 13 deletions(-)

Comments

Richard Henderson July 22, 2020, 5:30 p.m. UTC | #1

On 7/22/20 2:15 AM, frank.chang@sifive.com wrote:
>  FIELD(VTYPE, VLMUL, 0, 2)
>  FIELD(VTYPE, VSEW, 2, 3)
> -FIELD(VTYPE, VEDIV, 5, 2)
> -FIELD(VTYPE, RESERVED, 7, sizeof(target_ulong) * 8 - 9)
> +FIELD(VTYPE, VFLMUL, 5, 1)
> +FIELD(VTYPE, VEDIV, 8, 9)
> +FIELD(VTYPE, RESERVED, 10, sizeof(target_ulong) * 8 - 11)
>  FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 1, 1)

The ediv definition is wrong -- should be 8, 2.


> @@ -37,4 +38,10 @@ target_ulong fclass_d(uint64_t frs1);
>  #define SEW32 2
>  #define SEW64 3
>  
> +/* table to convert fractional LMUL value */
> +static const float flmul_table[8] = {
> +    1, 2, 4, 8,      /* LMUL */
> +    -1,              /* reserved */
> +    0.125, 0.25, 0.5 /* fractional LMUL */
> +};
>  #endif

Don't define data in a header file; only declare it.

> @@ -60,6 +60,9 @@ typedef struct DisasContext {
>      /* vector extension */
>      bool vill;
>      uint8_t lmul;
> +    float flmul;
> +    uint8_t eew;
> +    float emul;

Why are you adding floating-point values to DisasContext?

> +static inline float vext_vflmul(uint32_t desc)
> +{
> +    uint32_t lmul = FIELD_EX32(simd_data(desc), VDATA, LMUL);
> +    return flmul_table[lmul];
>  }

And in the helpers?  Are you planning on some sort of path through int -> float
-> int for computation?  That seems questionable.


r~

Frank Chang July 23, 2020, 2:11 a.m. UTC | #2

On Thu, Jul 23, 2020 at 1:30 AM Richard Henderson <
richard.henderson@linaro.org> wrote:

> On 7/22/20 2:15 AM, frank.chang@sifive.com wrote:
> >  FIELD(VTYPE, VLMUL, 0, 2)
> >  FIELD(VTYPE, VSEW, 2, 3)
> > -FIELD(VTYPE, VEDIV, 5, 2)
> > -FIELD(VTYPE, RESERVED, 7, sizeof(target_ulong) * 8 - 9)
> > +FIELD(VTYPE, VFLMUL, 5, 1)
> > +FIELD(VTYPE, VEDIV, 8, 9)
> > +FIELD(VTYPE, RESERVED, 10, sizeof(target_ulong) * 8 - 11)
> >  FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 1, 1)
>
> The ediv definition is wrong -- should be 8, 2.
>

OK, I will correct it.

>
>
> > @@ -37,4 +38,10 @@ target_ulong fclass_d(uint64_t frs1);
> >  #define SEW32 2
> >  #define SEW64 3
> >
> > +/* table to convert fractional LMUL value */
> > +static const float flmul_table[8] = {
> > +    1, 2, 4, 8,      /* LMUL */
> > +    -1,              /* reserved */
> > +    0.125, 0.25, 0.5 /* fractional LMUL */
> > +};
> >  #endif
>
> Don't define data in a header file; only declare it.
>

Fractional LMUL are used in cpu.h, translate.c and vector_helper.c.
I was trying to declare something which can be shared among these files
to calculate the fractional LMUL value.
Perhaps it's better to declare it as the inline function which
calculates fractional LMUL value in internals.h?
Or I can do the calculation explicitly at every place which requires the
fractional LMUL value?
(only 4 places require this value by far.)

> > @@ -60,6 +60,9 @@ typedef struct DisasContext {
> >      /* vector extension */
> >      bool vill;
> >      uint8_t lmul;
> > +    float flmul;
> > +    uint8_t eew;
> > +    float emul;
>
> Why are you adding floating-point values to DisasContext?
>

flmul, eew and emul are required during rvv-0.9 vector load/store
instructions.
Should I move these declarations to the vector load/store instructions
patch to make it clearer?

> > +static inline float vext_vflmul(uint32_t desc)
> > +{
> > +    uint32_t lmul = FIELD_EX32(simd_data(desc), VDATA, LMUL);
> > +    return flmul_table[lmul];
> >  }
>
> And in the helpers?  Are you planning on some sort of path through int ->
> float
> -> int for computation?  That seems questionable.
>

desc only saves the raw LMUL bits.
(total 3 bits, I've packed the fractional LMUL bit together with two other
LMUL bits in cpu_get_tb_cpu_state())
The helper here is to convert the 3-bits LMUL into the actual fractional
number it represents.

> r~
>

Frank Chang

diff --git a/target/riscv/cpu.h b/target/riscv/cpu.h
index 0a175151da..a16c6ed8e6 100644
--- a/target/riscv/cpu.h
+++ b/target/riscv/cpu.h
@@ -96,8 +96,9 @@  typedef struct CPURISCVState CPURISCVState;
 
 FIELD(VTYPE, VLMUL, 0, 2)
 FIELD(VTYPE, VSEW, 2, 3)
-FIELD(VTYPE, VEDIV, 5, 2)
-FIELD(VTYPE, RESERVED, 7, sizeof(target_ulong) * 8 - 9)
+FIELD(VTYPE, VFLMUL, 5, 1)
+FIELD(VTYPE, VEDIV, 8, 9)
+FIELD(VTYPE, RESERVED, 10, sizeof(target_ulong) * 8 - 11)
 FIELD(VTYPE, VILL, sizeof(target_ulong) * 8 - 1, 1)
 
 struct CPURISCVState {
@@ -368,9 +369,10 @@  typedef RISCVCPU ArchCPU;
 #include "exec/cpu-all.h"
 
 FIELD(TB_FLAGS, VL_EQ_VLMAX, 2, 1)
-FIELD(TB_FLAGS, LMUL, 3, 2)
-FIELD(TB_FLAGS, SEW, 5, 3)
-FIELD(TB_FLAGS, VILL, 8, 1)
+FIELD(TB_FLAGS, LMUL, 3, 3)
+FIELD(TB_FLAGS, SEW, 6, 3)
+/* Skip MSTATUS_VS (0x600) fields */
+FIELD(TB_FLAGS, VILL, 11, 1)
 
 /*
  * A simplification for VLMAX
@@ -399,12 +401,14 @@  static inline void cpu_get_tb_cpu_state(CPURISCVState *env, target_ulong *pc,
     if (riscv_has_ext(env, RVV)) {
         uint32_t vlmax = vext_get_vlmax(env_archcpu(env), env->vtype);
         bool vl_eq_vlmax = (env->vstart == 0) && (vlmax == env->vl);
+
         flags = FIELD_DP32(flags, TB_FLAGS, VILL,
                     FIELD_EX64(env->vtype, VTYPE, VILL));
         flags = FIELD_DP32(flags, TB_FLAGS, SEW,
                     FIELD_EX64(env->vtype, VTYPE, VSEW));
         flags = FIELD_DP32(flags, TB_FLAGS, LMUL,
-                    FIELD_EX64(env->vtype, VTYPE, VLMUL));
+                    (FIELD_EX64(env->vtype, VTYPE, VFLMUL) << 2)
+                        | FIELD_EX64(env->vtype, VTYPE, VLMUL));
         flags = FIELD_DP32(flags, TB_FLAGS, VL_EQ_VLMAX, vl_eq_vlmax);
     } else {
         flags = FIELD_DP32(flags, TB_FLAGS, VILL, 1);
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index 018a134599..f6f0954c60 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -249,6 +249,7 @@  static bool ld_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     return ldst_us_trans(a->rd, a->rs1, data, fn, s, false);
 }
@@ -301,6 +302,7 @@  static bool st_us_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     return ldst_us_trans(a->rd, a->rs1, data, fn, s, true);
 }
@@ -387,6 +389,7 @@  static bool ld_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     return ldst_stride_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
 }
@@ -425,6 +428,7 @@  static bool st_stride_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     fn =  fns[seq][s->sew];
     if (fn == NULL) {
@@ -516,6 +520,7 @@  static bool ld_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, false);
 }
@@ -559,6 +564,7 @@  static bool st_index_op(DisasContext *s, arg_rnfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     return ldst_index_trans(a->rd, a->rs1, a->rs2, data, fn, s, true);
 }
@@ -637,6 +643,7 @@  static bool ldff_op(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, NF, a->nf);
     return ldff_trans(a->rd, a->rs1, data, fn, s);
 }
@@ -746,6 +753,7 @@  static bool amo_op(DisasContext *s, arg_rwdvm *a, uint8_t seq)
 
     data = FIELD_DP32(data, VDATA, VM, a->vm);
     data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA, SEW, s->sew);
     data = FIELD_DP32(data, VDATA, WD, a->wd);
     return amo_trans(a->rd, a->rs1, a->rs2, data, fn, s);
 }
@@ -1644,7 +1652,8 @@  static bool trans_vmv_v_v(DisasContext *s, arg_vmv_v_v *a)
                              vreg_ofs(s, a->rs1),
                              MAXSZ(s), MAXSZ(s));
         } else {
-            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+            uint32_t data = 0;
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
             static gen_helper_gvec_2_ptr * const fns[4] = {
                 gen_helper_vmv_v_v_b, gen_helper_vmv_v_v_h,
                 gen_helper_vmv_v_v_w, gen_helper_vmv_v_v_d,
@@ -1682,7 +1691,8 @@  static bool trans_vmv_v_x(DisasContext *s, arg_vmv_v_x *a)
             TCGv_i32 desc ;
             TCGv_i64 s1_i64 = tcg_temp_new_i64();
             TCGv_ptr dest = tcg_temp_new_ptr();
-            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+            uint32_t data = 0;
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
             static gen_helper_vmv_vx * const fns[4] = {
                 gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
                 gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
@@ -1720,7 +1730,8 @@  static bool trans_vmv_v_i(DisasContext *s, arg_vmv_v_i *a)
             TCGv_i32 desc;
             TCGv_i64 s1;
             TCGv_ptr dest;
-            uint32_t data = FIELD_DP32(0, VDATA, LMUL, s->lmul);
+            uint32_t data = 0;
+            data = FIELD_DP32(data, VDATA, LMUL, s->lmul);
             static gen_helper_vmv_vx * const fns[4] = {
                 gen_helper_vmv_v_x_b, gen_helper_vmv_v_x_h,
                 gen_helper_vmv_v_x_w, gen_helper_vmv_v_x_d,
diff --git a/target/riscv/internals.h b/target/riscv/internals.h
index 89fc0753bc..eaf792db5b 100644
--- a/target/riscv/internals.h
+++ b/target/riscv/internals.h
@@ -24,8 +24,9 @@ 
 /* share data between vector helpers and decode code */
 FIELD(VDATA, VM, 0, 1)
 FIELD(VDATA, LMUL, 1, 3)
-FIELD(VDATA, NF, 4, 4)
-FIELD(VDATA, WD, 4, 1)
+FIELD(VDATA, SEW, 4, 3)
+FIELD(VDATA, NF, 7, 4)
+FIELD(VDATA, WD, 7, 1)
 
 /* float point classify helpers */
 target_ulong fclass_h(uint64_t frs1);
@@ -37,4 +38,10 @@  target_ulong fclass_d(uint64_t frs1);
 #define SEW32 2
 #define SEW64 3
 
+/* table to convert fractional LMUL value */
+static const float flmul_table[8] = {
+    1, 2, 4, 8,      /* LMUL */
+    -1,              /* reserved */
+    0.125, 0.25, 0.5 /* fractional LMUL */
+};
 #endif
diff --git a/target/riscv/translate.c b/target/riscv/translate.c
index 7593b41a1f..72eb7c2e74 100644
--- a/target/riscv/translate.c
+++ b/target/riscv/translate.c
@@ -60,6 +60,9 @@  typedef struct DisasContext {
     /* vector extension */
     bool vill;
     uint8_t lmul;
+    float flmul;
+    uint8_t eew;
+    float emul;
     uint8_t sew;
     uint16_t vlen;
     bool vl_eq_vlmax;
@@ -823,6 +826,7 @@  static void riscv_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs)
     ctx->vill = FIELD_EX32(tb_flags, TB_FLAGS, VILL);
     ctx->sew = FIELD_EX32(tb_flags, TB_FLAGS, SEW);
     ctx->lmul = FIELD_EX32(tb_flags, TB_FLAGS, LMUL);
+    ctx->flmul = flmul_table[ctx->lmul];
     ctx->vl_eq_vlmax = FIELD_EX32(tb_flags, TB_FLAGS, VL_EQ_VLMAX);
 }
 
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 6545f91732..a7963c3a2b 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -86,9 +86,15 @@  static inline uint32_t vext_vm(uint32_t desc)
     return FIELD_EX32(simd_data(desc), VDATA, VM);
 }
 
-static inline uint32_t vext_lmul(uint32_t desc)
+static inline uint32_t vext_sew(uint32_t desc)
 {
-    return FIELD_EX32(simd_data(desc), VDATA, LMUL);
+    return 1 << (FIELD_EX32(simd_data(desc), VDATA, SEW) + 3);
+}
+
+static inline float vext_vflmul(uint32_t desc)
+{
+    uint32_t lmul = FIELD_EX32(simd_data(desc), VDATA, LMUL);
+    return flmul_table[lmul];
 }
 
 static uint32_t vext_wd(uint32_t desc)

[RFC,v2,15/76] target/riscv: rvv-0.9: add fractional LMUL

Commit Message

Comments

Patch