qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
* [PATCH v5 48/60] target/riscv: vector mask-register logical instructions
  2020-03-12 14:58 [PATCH v5 00/60] target/riscv: support vector extension v0.7.1 LIU Zhiwei
@ 2020-03-12 14:58 ` LIU Zhiwei
  0 siblings, 0 replies; 2+ messages in thread
From: LIU Zhiwei @ 2020-03-12 14:58 UTC (permalink / raw)
  To: richard.henderson, alistair23, chihmin.chao, palmer
  Cc: guoren, qemu-riscv, qemu-devel, wxy194768, wenmeng_zhang,
	LIU Zhiwei

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
---
 target/riscv/helper.h                   |  9 ++++++
 target/riscv/insn32.decode              |  8 +++++
 target/riscv/insn_trans/trans_rvv.inc.c | 28 +++++++++++++++++
 target/riscv/vector_helper.c            | 40 +++++++++++++++++++++++++
 4 files changed, 85 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index b0bb617b42..9301ce0e00 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1074,3 +1074,12 @@ DEF_HELPER_6(vfredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
 
 DEF_HELPER_6(vfwredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
 DEF_HELPER_6(vfwredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vmand_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmnand_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmandnot_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmxor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmornot_mm, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vmxnor_mm, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index f1efc8886d..76a9bae8bb 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -539,6 +539,14 @@ vfredmin_vs     000101 . ..... ..... 001 ..... 1010111 @r_vm
 vfredmax_vs     000111 . ..... ..... 001 ..... 1010111 @r_vm
 # Vector widening ordered and unordered float reduction sum
 vfwredsum_vs    1100-1 . ..... ..... 001 ..... 1010111 @r_vm
+vmand_mm        011001 - ..... ..... 010 ..... 1010111 @r
+vmnand_mm       011101 - ..... ..... 010 ..... 1010111 @r
+vmandnot_mm     011000 - ..... ..... 010 ..... 1010111 @r
+vmxor_mm        011011 - ..... ..... 010 ..... 1010111 @r
+vmor_mm         011010 - ..... ..... 010 ..... 1010111 @r
+vmnor_mm        011110 - ..... ..... 010 ..... 1010111 @r
+vmornot_mm      011100 - ..... ..... 010 ..... 1010111 @r
+vmxnor_mm       011111 - ..... ..... 010 ..... 1010111 @r
 
 vsetvli         0 ........... ..... 111 ..... 1010111  @r2_zimm
 vsetvl          1000000 ..... ..... 111 ..... 1010111  @r
diff --git a/target/riscv/insn_trans/trans_rvv.inc.c b/target/riscv/insn_trans/trans_rvv.inc.c
index ad864c9742..065b415abb 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2052,3 +2052,31 @@ GEN_OPFVV_TRANS(vfredmin_vs, reduction_check)
 
 /* Vector Widening Floating-Point Reduction Instructions */
 GEN_OPFVV_WIDEN_TRANS(vfwredsum_vs, reduction_check)
+
+/*
+ *** Vector Mask Operations
+ */
+/* Vector Mask-Register Logical Instructions */
+#define GEN_MM_TRANS(NAME)                                         \
+static bool trans_##NAME(DisasContext *s, arg_r *a)                \
+{                                                                  \
+    if (vext_check_isa_ill(s, RVV)) {                              \
+        uint32_t data = 0;                                         \
+        gen_helper_gvec_4_ptr * fn = gen_helper_##NAME;            \
+        data = FIELD_DP32(data, VDATA, MLEN, s->mlen);             \
+        data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
+        tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
+            vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),              \
+            cpu_env, 0, s->vlen / 8, data, fn);                    \
+        return true;                                               \
+    }                                                              \
+    return false;                                                  \
+}
+GEN_MM_TRANS(vmand_mm)
+GEN_MM_TRANS(vmnand_mm)
+GEN_MM_TRANS(vmandnot_mm)
+GEN_MM_TRANS(vmxor_mm)
+GEN_MM_TRANS(vmor_mm)
+GEN_MM_TRANS(vmnor_mm)
+GEN_MM_TRANS(vmornot_mm)
+GEN_MM_TRANS(vmxnor_mm)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d325fe5e2e..9e9d172cda 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4238,3 +4238,43 @@ void HELPER(vfwredsum_vs_w)(void *vd, void *v0, void *vs1,
         clearq(vd, 1, sizeof(uint64_t), tot);
     }
 }
+
+/*
+ *** Vector Mask Operations
+ */
+/* Vector Mask-Register Logical Instructions */
+#define GEN_VEXT_MASK_VV(NAME, OP)                        \
+void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
+        void *vs2, CPURISCVState *env, uint32_t desc)     \
+{                                                         \
+    uint32_t mlen = vext_mlen(desc);                      \
+    uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;   \
+    uint32_t vl = env->vl;                                \
+    uint32_t i;                                           \
+    int a, b;                                             \
+    for (i = 0; i < vl; i++) {                            \
+        a = vext_elem_mask(vs1, mlen, i);                 \
+        b = vext_elem_mask(vs2, mlen, i);                 \
+        vext_set_elem_mask(vd, mlen, i, OP(b, a));        \
+    }                                                     \
+    if (i == 0) {                                         \
+        return;                                           \
+    }                                                     \
+    for (; i < vlmax; i++) {                              \
+        vext_set_elem_mask(vd, mlen, i, 0);               \
+    }                                                     \
+}
+#define DO_NAND(N, M)  (!(N & M))
+#define DO_ANDNOT(N, M)  (N & !M)
+#define DO_NOR(N, M)  (!(N | M))
+#define DO_ORNOT(N, M)  (N | !M)
+#define DO_XNOR(N, M)  (!(N ^ M))
+
+GEN_VEXT_MASK_VV(vmand_mm, DO_AND)
+GEN_VEXT_MASK_VV(vmnand_mm, DO_NAND)
+GEN_VEXT_MASK_VV(vmandnot_mm, DO_ANDNOT)
+GEN_VEXT_MASK_VV(vmxor_mm, DO_XOR)
+GEN_VEXT_MASK_VV(vmor_mm, DO_OR)
+GEN_VEXT_MASK_VV(vmnor_mm, DO_NOR)
+GEN_VEXT_MASK_VV(vmornot_mm, DO_ORNOT)
+GEN_VEXT_MASK_VV(vmxnor_mm, DO_XNOR)
-- 
2.23.0



^ permalink raw reply related	[flat|nested] 2+ messages in thread

* Re: [PATCH v5 48/60] target/riscv: vector mask-register logical instructions
       [not found] <86d7d5d0-37c9-e1c3-49d5-984d40e9c4a9@linaro.org>
@ 2020-03-15  6:57 ` Richard Henderson
  0 siblings, 0 replies; 2+ messages in thread
From: Richard Henderson @ 2020-03-15  6:57 UTC (permalink / raw)
  To: qemu-devel, liuzhiwei

Ho hum, failed to send to the list first time.


-------- Forwarded Message --------
Subject: Re: [PATCH v5 48/60] target/riscv: vector mask-register logical
instructions
Date: Sat, 14 Mar 2020 23:41:59 -0700
From: Richard Henderson <richard.henderson@linaro.org>
To: LIU Zhiwei <zhiwei_liu@c-sky.com>

[ Patch didn't make it to the list, so reviewing

https://github.com/romanheros/qemu/commit/8c782677c21909f80c481cfd7ab58c076761642c
]

This is ok as-is, so
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>

But you can do better.

> 
> /* Vector Mask-Register Logical Instructions */
> #define GEN_MM_TRANS(NAME)                                         \
> static bool trans_##NAME(DisasContext *s, arg_r *a)                \
> {                                                                  \
>     if (vext_check_isa_ill(s, RVV)) {                              \
>         uint32_t data = 0;                                         \
>         gen_helper_gvec_4_ptr * fn = gen_helper_##NAME;            \
>         data = FIELD_DP32(data, VDATA, MLEN, s->mlen);             \
>         data = FIELD_DP32(data, VDATA, LMUL, s->lmul);             \
>         tcg_gen_gvec_4_ptr(vreg_ofs(s, a->rd), vreg_ofs(s, 0),     \
>             vreg_ofs(s, a->rs1), vreg_ofs(s, a->rs2),              \
>             cpu_env, 0, s->vlen / 8, data, fn);                    \
>         return true;                                               \
>     }                                                              \
>     return false;                                                  \
> }
> GEN_MM_TRANS(vmand_mm)
> GEN_MM_TRANS(vmnand_mm)
> GEN_MM_TRANS(vmandnot_mm)
> GEN_MM_TRANS(vmxor_mm)
> GEN_MM_TRANS(vmor_mm)
> GEN_MM_TRANS(vmnor_mm)
> GEN_MM_TRANS(vmornot_mm)
> GEN_MM_TRANS(vmxnor_mm)

For vl_eq_vlmax, we should use gvec.

For mlen == 1, nothing more is needed, as all bits are significant.  For mlen >
1, we can use

  tcg_gen_gvec_andi(MO_64, vreg_ofs(s, a->rd),
                    vreg_ofs(s, a->rd),
                    pred_mlen_masks[log2_mlen],
                    s->vlen / 8, s->vlen / 8);

where pred_mlen_masks[] are as discussed vs 49/60 (vmpopc).

It might be worth noticing vmclr.mm, which of course does not require that andi.

> /* Vector Mask-Register Logical Instructions */
> #define GEN_VEXT_MASK_VV(NAME, OP)                        \
> void HELPER(NAME)(void *vd, void *v0, void *vs1,          \
>         void *vs2, CPURISCVState *env, uint32_t desc)     \
> {                                                         \
>     uint32_t mlen = vext_mlen(desc);                      \
>     uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;   \
>     uint32_t vl = env->vl;                                \
>     uint32_t i;                                           \
>     int a, b;                                             \
>     for (i = 0; i < vl; i++) {                            \
>         a = vext_elem_mask(vs1, mlen, i);                 \
>         b = vext_elem_mask(vs2, mlen, i);                 \
>         vext_set_elem_mask(vd, mlen, i, OP(b, a));        \
>     }                                                     \
>     if (i == 0) {                                         \
>         return;                                           \
>     }                                                     \
>     for (; i < vlmax; i++) {                              \
>         vext_set_elem_mask(vd, mlen, i, 0);               \
>     }                                                     \
> }
> #define DO_NAND(N, M)  (!(N & M))
> #define DO_ANDNOT(N, M)  (N & !M)
> #define DO_NOR(N, M)  (!(N | M))
> #define DO_ORNOT(N, M)  (N | !M)
> #define DO_XNOR(N, M)  (!(N ^ M))

Again, these operations can be done in units of uint64_t, applying the
pred_msize_mask and the residual "rmask" that I mentoned wrt vmpopc.

This would mean that you'd want bitwise, not logical nots above in your DO_*
macros.


r~


^ permalink raw reply	[flat|nested] 2+ messages in thread

end of thread, other threads:[~2020-03-15  6:59 UTC | newest]

Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
     [not found] <86d7d5d0-37c9-e1c3-49d5-984d40e9c4a9@linaro.org>
2020-03-15  6:57 ` [PATCH v5 48/60] target/riscv: vector mask-register logical instructions Richard Henderson
2020-03-12 14:58 [PATCH v5 00/60] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-03-12 14:58 ` [PATCH v5 48/60] target/riscv: vector mask-register logical instructions LIU Zhiwei

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).