qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: LIU Zhiwei <zhiwei_liu@c-sky.com>
To: qemu-devel@nongnu.org, qemu-riscv@nongnu.org
Cc: richard.henderson@linaro.org, wxy194768@alibaba-inc.com,
	wenmeng_zhang@c-sky.com, Alistair.Francis@wdc.com,
	palmer@dabbelt.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v10 59/61] target/riscv: vector register gather instruction
Date: Sat, 20 Jun 2020 12:36:59 +0800	[thread overview]
Message-ID: <20200620043701.1323-60-zhiwei_liu@c-sky.com> (raw)
In-Reply-To: <20200620043701.1323-1-zhiwei_liu@c-sky.com>

Signed-off-by: LIU Zhiwei <zhiwei_liu@c-sky.com>
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/riscv/helper.h                   |  9 +++
 target/riscv/insn32.decode              |  3 +
 target/riscv/insn_trans/trans_rvv.inc.c | 78 +++++++++++++++++++++++++
 target/riscv/vector_helper.c            | 60 +++++++++++++++++++
 4 files changed, 150 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 29a5eb7049..eca1ab541b 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1136,3 +1136,12 @@ DEF_HELPER_6(vslide1down_vx_b, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vslide1down_vx_h, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vslide1down_vx_w, void, ptr, ptr, tl, ptr, env, i32)
 DEF_HELPER_6(vslide1down_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+
+DEF_HELPER_6(vrgather_vv_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vv_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vrgather_vx_d, void, ptr, ptr, tl, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 36123f71b9..80d5ff74a9 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -574,6 +574,9 @@ vslide1up_vx    001110 . ..... ..... 110 ..... 1010111 @r_vm
 vslidedown_vx   001111 . ..... ..... 100 ..... 1010111 @r_vm
 vslidedown_vi   001111 . ..... ..... 011 ..... 1010111 @r_vm
 vslide1down_vx  001111 . ..... ..... 110 ..... 1010111 @r_vm
+vrgather_vv     001100 . ..... ..... 000 ..... 1010111 @r_vm
+vrgather_vx     001100 . ..... ..... 100 ..... 1010111 @r_vm
+vrgather_vi     001100 . ..... ..... 011 ..... 1010111 @r_vm
 
 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 ffb9835d07..f6547f7e6d 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2776,3 +2776,81 @@ GEN_OPIVI_TRANS(vslideup_vi, 1, vslideup_vx, slideup_check)
 GEN_OPIVX_TRANS(vslidedown_vx, opivx_check)
 GEN_OPIVX_TRANS(vslide1down_vx, opivx_check)
 GEN_OPIVI_TRANS(vslidedown_vi, 1, vslidedown_vx, opivx_check)
+
+/* Vector Register Gather Instruction */
+static bool vrgather_vv_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs1, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            (a->rd != a->rs2) && (a->rd != a->rs1));
+}
+
+GEN_OPIVV_TRANS(vrgather_vv, vrgather_vv_check)
+
+static bool vrgather_vx_check(DisasContext *s, arg_rmrr *a)
+{
+    return (vext_check_isa_ill(s) &&
+            vext_check_overlap_mask(s, a->rd, a->vm, true) &&
+            vext_check_reg(s, a->rd, false) &&
+            vext_check_reg(s, a->rs2, false) &&
+            (a->rd != a->rs2));
+}
+
+/* vrgather.vx vd, vs2, rs1, vm # vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
+static bool trans_vrgather_vx(DisasContext *s, arg_rmrr *a)
+{
+    if (!vrgather_vx_check(s, a)) {
+        return false;
+    }
+
+    if (a->vm && s->vl_eq_vlmax) {
+        int vlmax = s->vlen / s->mlen;
+        TCGv_i64 dest = tcg_temp_new_i64();
+
+        if (a->rs1 == 0) {
+            vec_element_loadi(s, dest, a->rs2, 0);
+        } else {
+            vec_element_loadx(s, dest, a->rs2, cpu_gpr[a->rs1], vlmax);
+        }
+
+        tcg_gen_gvec_dup_i64(s->sew, vreg_ofs(s, a->rd),
+                             MAXSZ(s), MAXSZ(s), dest);
+        tcg_temp_free_i64(dest);
+    } else {
+        static gen_helper_opivx * const fns[4] = {
+            gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
+            gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d
+        };
+        return opivx_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s);
+    }
+    return true;
+}
+
+/* vrgather.vi vd, vs2, imm, vm # vd[i] = (imm >= VLMAX) ? 0 : vs2[imm] */
+static bool trans_vrgather_vi(DisasContext *s, arg_rmrr *a)
+{
+    if (!vrgather_vx_check(s, a)) {
+        return false;
+    }
+
+    if (a->vm && s->vl_eq_vlmax) {
+        if (a->rs1 >= s->vlen / s->mlen) {
+            tcg_gen_gvec_dup_imm(SEW64, vreg_ofs(s, a->rd),
+                                 MAXSZ(s), MAXSZ(s), 0);
+        } else {
+            tcg_gen_gvec_dup_mem(s->sew, vreg_ofs(s, a->rd),
+                                 endian_ofs(s, a->rs2, a->rs1),
+                                 MAXSZ(s), MAXSZ(s));
+        }
+    } else {
+        static gen_helper_opivx * const fns[4] = {
+            gen_helper_vrgather_vx_b, gen_helper_vrgather_vx_h,
+            gen_helper_vrgather_vx_w, gen_helper_vrgather_vx_d
+        };
+        return opivi_trans(a->rd, a->rs1, a->rs2, a->vm, fns[s->sew], s, 1);
+    }
+    return true;
+}
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 28b54d2589..220fa76d54 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4811,3 +4811,63 @@ GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_b, uint8_t, H1, clearb)
 GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_h, uint16_t, H2, clearh)
 GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_w, uint32_t, H4, clearl)
 GEN_VEXT_VSLIDE1DOWN_VX(vslide1down_vx_d, uint64_t, H8, clearq)
+
+/* Vector Register Gather Instruction */
+#define GEN_VEXT_VRGATHER_VV(NAME, ETYPE, H, CLEAR_FN)                    \
+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 vm = vext_vm(desc);                                          \
+    uint32_t vl = env->vl;                                                \
+    uint32_t index, i;                                                    \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        index = *((ETYPE *)vs1 + H(i));                                   \
+        if (index >= vlmax) {                                             \
+            *((ETYPE *)vd + H(i)) = 0;                                    \
+        } else {                                                          \
+            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index));           \
+        }                                                                 \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vd[i] = (vs1[i] >= VLMAX) ? 0 : vs2[vs1[i]]; */
+GEN_VEXT_VRGATHER_VV(vrgather_vv_b, uint8_t, H1, clearb)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_h, uint16_t, H2, clearh)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_w, uint32_t, H4, clearl)
+GEN_VEXT_VRGATHER_VV(vrgather_vv_d, uint64_t, H8, clearq)
+
+#define GEN_VEXT_VRGATHER_VX(NAME, ETYPE, H, CLEAR_FN)                    \
+void HELPER(NAME)(void *vd, void *v0, target_ulong s1, void *vs2,         \
+                  CPURISCVState *env, uint32_t desc)                      \
+{                                                                         \
+    uint32_t mlen = vext_mlen(desc);                                      \
+    uint32_t vlmax = env_archcpu(env)->cfg.vlen / mlen;                   \
+    uint32_t vm = vext_vm(desc);                                          \
+    uint32_t vl = env->vl;                                                \
+    uint32_t index = s1, i;                                               \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        if (index >= vlmax) {                                             \
+            *((ETYPE *)vd + H(i)) = 0;                                    \
+        } else {                                                          \
+            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(index));           \
+        }                                                                 \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vd[i] = (x[rs1] >= VLMAX) ? 0 : vs2[rs1] */
+GEN_VEXT_VRGATHER_VX(vrgather_vx_b, uint8_t, H1, clearb)
+GEN_VEXT_VRGATHER_VX(vrgather_vx_h, uint16_t, H2, clearh)
+GEN_VEXT_VRGATHER_VX(vrgather_vx_w, uint32_t, H4, clearl)
+GEN_VEXT_VRGATHER_VX(vrgather_vx_d, uint64_t, H8, clearq)
-- 
2.23.0



  parent reply	other threads:[~2020-06-20  6:36 UTC|newest]

Thread overview: 64+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-20  4:36 [PATCH v10 00/61] target/riscv: support vector extension v0.7.1 LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 01/61] target/riscv: add vector extension field in CPURISCVState LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 02/61] target/riscv: implementation-defined constant parameters LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 03/61] target/riscv: support vector extension csr LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 04/61] target/riscv: add vector configure instruction LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 05/61] target/riscv: add an internals.h header LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 06/61] target/riscv: add vector stride load and store instructions LIU Zhiwei
2020-06-23 16:52   ` Alistair Francis
2020-06-23 21:32     ` LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 07/61] target/riscv: add vector index " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 08/61] target/riscv: add fault-only-first unit stride load LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 09/61] target/riscv: add vector amo operations LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 10/61] target/riscv: vector single-width integer add and subtract LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 11/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 12/61] target/riscv: vector integer add-with-carry / subtract-with-borrow instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 13/61] target/riscv: vector bitwise logical instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 14/61] target/riscv: vector single-width bit shift instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 15/61] target/riscv: vector narrowing integer right " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 16/61] target/riscv: vector integer comparison instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 17/61] target/riscv: vector integer min/max instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 18/61] target/riscv: vector single-width integer multiply instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 19/61] target/riscv: vector integer divide instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 20/61] target/riscv: vector widening integer multiply instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 21/61] target/riscv: vector single-width integer multiply-add instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 22/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 23/61] target/riscv: vector integer merge and move instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 24/61] target/riscv: vector single-width saturating add and subtract LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 25/61] target/riscv: vector single-width averaging " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 26/61] target/riscv: vector single-width fractional multiply with rounding and saturation LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 27/61] target/riscv: vector widening saturating scaled multiply-add LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 28/61] target/riscv: vector single-width scaling shift instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 29/61] target/riscv: vector narrowing fixed-point clip instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 30/61] target/riscv: vector single-width floating-point add/subtract instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 31/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 32/61] target/riscv: vector single-width floating-point multiply/divide instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 33/61] target/riscv: vector widening floating-point multiply LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 34/61] target/riscv: vector single-width floating-point fused multiply-add instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 35/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 36/61] target/riscv: vector floating-point square-root instruction LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 37/61] target/riscv: vector floating-point min/max instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 38/61] target/riscv: vector floating-point sign-injection instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 39/61] target/riscv: vector floating-point compare instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 40/61] target/riscv: vector floating-point classify instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 41/61] target/riscv: vector floating-point merge instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 42/61] target/riscv: vector floating-point/integer type-convert instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 43/61] target/riscv: widening " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 44/61] target/riscv: narrowing " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 45/61] target/riscv: vector single-width integer reduction instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 46/61] target/riscv: vector wideing " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 47/61] target/riscv: vector single-width floating-point " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 48/61] target/riscv: vector widening " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 49/61] target/riscv: vector mask-register logical instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 50/61] target/riscv: vector mask population count vmpopc LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 51/61] target/riscv: vmfirst find-first-set mask bit LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 52/61] target/riscv: set-X-first " LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 53/61] target/riscv: vector iota instruction LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 54/61] target/riscv: vector element index instruction LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 55/61] target/riscv: integer extract instruction LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 56/61] target/riscv: integer scalar move instruction LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 57/61] target/riscv: floating-point scalar move instructions LIU Zhiwei
2020-06-20  4:36 ` [PATCH v10 58/61] target/riscv: vector slide instructions LIU Zhiwei
2020-06-20  4:36 ` LIU Zhiwei [this message]
2020-06-20  4:37 ` [PATCH v10 60/61] target/riscv: vector compress instruction LIU Zhiwei
2020-06-20  4:37 ` [PATCH v10 61/61] target/riscv: configure and turn on vector extension from command line LIU Zhiwei

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200620043701.1323-60-zhiwei_liu@c-sky.com \
    --to=zhiwei_liu@c-sky.com \
    --cc=Alistair.Francis@wdc.com \
    --cc=palmer@dabbelt.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-riscv@nongnu.org \
    --cc=richard.henderson@linaro.org \
    --cc=wenmeng_zhang@c-sky.com \
    --cc=wxy194768@alibaba-inc.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
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).