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 58/61] target/riscv: vector slide instructions
Date: Sat, 20 Jun 2020 12:36:58 +0800	[thread overview]
Message-ID: <20200620043701.1323-59-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                   |  17 ++++
 target/riscv/insn32.decode              |   6 ++
 target/riscv/insn_trans/trans_rvv.inc.c |  18 ++++
 target/riscv/vector_helper.c            | 114 ++++++++++++++++++++++++
 4 files changed, 155 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index c6695ea7a8..29a5eb7049 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1119,3 +1119,20 @@ DEF_HELPER_4(vid_v_b, void, ptr, ptr, env, i32)
 DEF_HELPER_4(vid_v_h, void, ptr, ptr, env, i32)
 DEF_HELPER_4(vid_v_w, void, ptr, ptr, env, i32)
 DEF_HELPER_4(vid_v_d, void, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vslideup_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslideup_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslideup_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslideup_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslidedown_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_b, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_h, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_w, void, ptr, ptr, tl, ptr, env, i32)
+DEF_HELPER_6(vslide1up_vx_d, void, ptr, ptr, tl, ptr, env, i32)
+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)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 17288a3c95..36123f71b9 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -568,6 +568,12 @@ vext_x_v        001100 1 ..... ..... 010 ..... 1010111 @r
 vmv_s_x         001101 1 00000 ..... 110 ..... 1010111 @r2
 vfmv_f_s        001100 1 ..... 00000 001 ..... 1010111 @r2rd
 vfmv_s_f        001101 1 00000 ..... 101 ..... 1010111 @r2
+vslideup_vx     001110 . ..... ..... 100 ..... 1010111 @r_vm
+vslideup_vi     001110 . ..... ..... 011 ..... 1010111 @r_vm
+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
 
 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 884ad910b1..ffb9835d07 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2758,3 +2758,21 @@ static bool trans_vfmv_s_f(DisasContext *s, arg_vfmv_s_f *a)
     }
     return false;
 }
+
+/* Vector Slide Instructions */
+static bool slideup_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));
+}
+
+GEN_OPIVX_TRANS(vslideup_vx, slideup_check)
+GEN_OPIVX_TRANS(vslide1up_vx, slideup_check)
+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)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index 1dc2a1ccb1..28b54d2589 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4697,3 +4697,117 @@ GEN_VEXT_VID_V(vid_v_b, uint8_t, H1, clearb)
 GEN_VEXT_VID_V(vid_v_h, uint16_t, H2, clearh)
 GEN_VEXT_VID_V(vid_v_w, uint32_t, H4, clearl)
 GEN_VEXT_VID_V(vid_v_d, uint64_t, H8, clearq)
+
+/*
+ *** Vector Permutation Instructions
+ */
+
+/* Vector Slide Instructions */
+#define GEN_VEXT_VSLIDEUP_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;                                                \
+    target_ulong offset = s1, i;                                          \
+                                                                          \
+    for (i = offset; i < vl; i++) {                                       \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - offset));          \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vslideup.vx vd, vs2, rs1, vm # vd[i+rs1] = vs2[i] */
+GEN_VEXT_VSLIDEUP_VX(vslideup_vx_b, uint8_t, H1, clearb)
+GEN_VEXT_VSLIDEUP_VX(vslideup_vx_h, uint16_t, H2, clearh)
+GEN_VEXT_VSLIDEUP_VX(vslideup_vx_w, uint32_t, H4, clearl)
+GEN_VEXT_VSLIDEUP_VX(vslideup_vx_d, uint64_t, H8, clearq)
+
+#define GEN_VEXT_VSLIDEDOWN_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;                                                \
+    target_ulong offset = s1, i;                                          \
+                                                                          \
+    for (i = 0; i < vl; ++i) {                                            \
+        target_ulong j = i + offset;                                      \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        *((ETYPE *)vd + H(i)) = j >= vlmax ? 0 : *((ETYPE *)vs2 + H(j));  \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vslidedown.vx vd, vs2, rs1, vm # vd[i] = vs2[i+rs1] */
+GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_b, uint8_t, H1, clearb)
+GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_h, uint16_t, H2, clearh)
+GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_w, uint32_t, H4, clearl)
+GEN_VEXT_VSLIDEDOWN_VX(vslidedown_vx_d, uint64_t, H8, clearq)
+
+#define GEN_VEXT_VSLIDE1UP_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 i;                                                           \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        if (i == 0) {                                                     \
+            *((ETYPE *)vd + H(i)) = s1;                                   \
+        } else {                                                          \
+            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i - 1));           \
+        }                                                                 \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vslide1up.vx vd, vs2, rs1, vm # vd[0]=x[rs1], vd[i+1] = vs2[i] */
+GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_b, uint8_t, H1, clearb)
+GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_h, uint16_t, H2, clearh)
+GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_w, uint32_t, H4, clearl)
+GEN_VEXT_VSLIDE1UP_VX(vslide1up_vx_d, uint64_t, H8, clearq)
+
+#define GEN_VEXT_VSLIDE1DOWN_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 i;                                                           \
+                                                                          \
+    for (i = 0; i < vl; i++) {                                            \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {                        \
+            continue;                                                     \
+        }                                                                 \
+        if (i == vl - 1) {                                                \
+            *((ETYPE *)vd + H(i)) = s1;                                   \
+        } else {                                                          \
+            *((ETYPE *)vd + H(i)) = *((ETYPE *)vs2 + H(i + 1));           \
+        }                                                                 \
+    }                                                                     \
+    CLEAR_FN(vd, vl, vl * sizeof(ETYPE), vlmax * sizeof(ETYPE));          \
+}
+
+/* vslide1down.vx vd, vs2, rs1, vm # vd[i] = vs2[i+1], vd[vl-1]=x[rs1] */
+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)
-- 
2.23.0



  parent reply	other threads:[~2020-06-20  6:34 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 ` LIU Zhiwei [this message]
2020-06-20  4:36 ` [PATCH v10 59/61] target/riscv: vector register gather instruction LIU Zhiwei
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=20200620043701.1323-59-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).