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 <alistair.francis@wdc.com>,
	palmer@dabbelt.com, LIU Zhiwei <zhiwei_liu@c-sky.com>
Subject: [PATCH v10 45/61] target/riscv: vector single-width integer reduction instructions
Date: Sat, 20 Jun 2020 12:36:45 +0800	[thread overview]
Message-ID: <20200620043701.1323-46-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>
Reviewed-by: Alistair Francis <alistair.francis@wdc.com>
---
 target/riscv/helper.h                   | 33 +++++++++++
 target/riscv/insn32.decode              |  8 +++
 target/riscv/insn_trans/trans_rvv.inc.c | 18 ++++++
 target/riscv/vector_helper.c            | 74 +++++++++++++++++++++++++
 4 files changed, 133 insertions(+)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index 5870c4041e..a7fe4443e4 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1039,3 +1039,36 @@ DEF_HELPER_5(vfncvt_f_x_v_h, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(vfncvt_f_x_v_w, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(vfncvt_f_f_v_h, void, ptr, ptr, ptr, env, i32)
 DEF_HELPER_5(vfncvt_f_f_v_w, void, ptr, ptr, ptr, env, i32)
+
+DEF_HELPER_6(vredsum_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredsum_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmaxu_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmax_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredminu_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredmin_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredand_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_b, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_h, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_w, void, ptr, ptr, ptr, ptr, env, i32)
+DEF_HELPER_6(vredxor_vs_d, void, ptr, ptr, ptr, ptr, env, i32)
diff --git a/target/riscv/insn32.decode b/target/riscv/insn32.decode
index 55fbe166d8..878eeecb7e 100644
--- a/target/riscv/insn32.decode
+++ b/target/riscv/insn32.decode
@@ -531,6 +531,14 @@ vfncvt_x_f_v    100010 . ..... 10001 001 ..... 1010111 @r2_vm
 vfncvt_f_xu_v   100010 . ..... 10010 001 ..... 1010111 @r2_vm
 vfncvt_f_x_v    100010 . ..... 10011 001 ..... 1010111 @r2_vm
 vfncvt_f_f_v    100010 . ..... 10100 001 ..... 1010111 @r2_vm
+vredsum_vs      000000 . ..... ..... 010 ..... 1010111 @r_vm
+vredand_vs      000001 . ..... ..... 010 ..... 1010111 @r_vm
+vredor_vs       000010 . ..... ..... 010 ..... 1010111 @r_vm
+vredxor_vs      000011 . ..... ..... 010 ..... 1010111 @r_vm
+vredminu_vs     000100 . ..... ..... 010 ..... 1010111 @r_vm
+vredmin_vs      000101 . ..... ..... 010 ..... 1010111 @r_vm
+vredmaxu_vs     000110 . ..... ..... 010 ..... 1010111 @r_vm
+vredmax_vs      000111 . ..... ..... 010 ..... 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 4e4631ac6a..b3920eed23 100644
--- a/target/riscv/insn_trans/trans_rvv.inc.c
+++ b/target/riscv/insn_trans/trans_rvv.inc.c
@@ -2324,3 +2324,21 @@ GEN_OPFV_NARROW_TRANS(vfncvt_x_f_v)
 GEN_OPFV_NARROW_TRANS(vfncvt_f_xu_v)
 GEN_OPFV_NARROW_TRANS(vfncvt_f_x_v)
 GEN_OPFV_NARROW_TRANS(vfncvt_f_f_v)
+
+/*
+ *** Vector Reduction Operations
+ */
+/* Vector Single-Width Integer Reduction Instructions */
+static bool reduction_check(DisasContext *s, arg_rmrr *a)
+{
+    return vext_check_isa_ill(s) && vext_check_reg(s, a->rs2, false);
+}
+
+GEN_OPIVV_TRANS(vredsum_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmaxu_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmax_vs, reduction_check)
+GEN_OPIVV_TRANS(vredminu_vs, reduction_check)
+GEN_OPIVV_TRANS(vredmin_vs, reduction_check)
+GEN_OPIVV_TRANS(vredand_vs, reduction_check)
+GEN_OPIVV_TRANS(vredor_vs, reduction_check)
+GEN_OPIVV_TRANS(vredxor_vs, reduction_check)
diff --git a/target/riscv/vector_helper.c b/target/riscv/vector_helper.c
index d1950ebba5..5c357b688f 100644
--- a/target/riscv/vector_helper.c
+++ b/target/riscv/vector_helper.c
@@ -4332,3 +4332,77 @@ RVVCALL(OPFVV1, vfncvt_f_f_v_h, NOP_UU_H, H2, H4, vfncvtffv16)
 RVVCALL(OPFVV1, vfncvt_f_f_v_w, NOP_UU_W, H4, H8, float64_to_float32)
 GEN_VEXT_V_ENV(vfncvt_f_f_v_h, 2, 2, clearh)
 GEN_VEXT_V_ENV(vfncvt_f_f_v_w, 4, 4, clearl)
+
+/*
+ *** Vector Reduction Operations
+ */
+/* Vector Single-Width Integer Reduction Instructions */
+#define GEN_VEXT_RED(NAME, TD, TS2, HD, HS2, OP, 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 vm = vext_vm(desc);                          \
+    uint32_t vl = env->vl;                                \
+    uint32_t i;                                           \
+    uint32_t tot = env_archcpu(env)->cfg.vlen / 8;        \
+    TD s1 =  *((TD *)vs1 + HD(0));                        \
+                                                          \
+    for (i = 0; i < vl; i++) {                            \
+        TS2 s2 = *((TS2 *)vs2 + HS2(i));                  \
+        if (!vm && !vext_elem_mask(v0, mlen, i)) {        \
+            continue;                                     \
+        }                                                 \
+        s1 = OP(s1, (TD)s2);                              \
+    }                                                     \
+    *((TD *)vd + HD(0)) = s1;                             \
+    CLEAR_FN(vd, 1, sizeof(TD), tot);                     \
+}
+
+/* vd[0] = sum(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredsum_vs_b, int8_t, int8_t, H1, H1, DO_ADD, clearb)
+GEN_VEXT_RED(vredsum_vs_h, int16_t, int16_t, H2, H2, DO_ADD, clearh)
+GEN_VEXT_RED(vredsum_vs_w, int32_t, int32_t, H4, H4, DO_ADD, clearl)
+GEN_VEXT_RED(vredsum_vs_d, int64_t, int64_t, H8, H8, DO_ADD, clearq)
+
+/* vd[0] = maxu(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredmaxu_vs_b, uint8_t, uint8_t, H1, H1, DO_MAX, clearb)
+GEN_VEXT_RED(vredmaxu_vs_h, uint16_t, uint16_t, H2, H2, DO_MAX, clearh)
+GEN_VEXT_RED(vredmaxu_vs_w, uint32_t, uint32_t, H4, H4, DO_MAX, clearl)
+GEN_VEXT_RED(vredmaxu_vs_d, uint64_t, uint64_t, H8, H8, DO_MAX, clearq)
+
+/* vd[0] = max(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredmax_vs_b, int8_t, int8_t, H1, H1, DO_MAX, clearb)
+GEN_VEXT_RED(vredmax_vs_h, int16_t, int16_t, H2, H2, DO_MAX, clearh)
+GEN_VEXT_RED(vredmax_vs_w, int32_t, int32_t, H4, H4, DO_MAX, clearl)
+GEN_VEXT_RED(vredmax_vs_d, int64_t, int64_t, H8, H8, DO_MAX, clearq)
+
+/* vd[0] = minu(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredminu_vs_b, uint8_t, uint8_t, H1, H1, DO_MIN, clearb)
+GEN_VEXT_RED(vredminu_vs_h, uint16_t, uint16_t, H2, H2, DO_MIN, clearh)
+GEN_VEXT_RED(vredminu_vs_w, uint32_t, uint32_t, H4, H4, DO_MIN, clearl)
+GEN_VEXT_RED(vredminu_vs_d, uint64_t, uint64_t, H8, H8, DO_MIN, clearq)
+
+/* vd[0] = min(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredmin_vs_b, int8_t, int8_t, H1, H1, DO_MIN, clearb)
+GEN_VEXT_RED(vredmin_vs_h, int16_t, int16_t, H2, H2, DO_MIN, clearh)
+GEN_VEXT_RED(vredmin_vs_w, int32_t, int32_t, H4, H4, DO_MIN, clearl)
+GEN_VEXT_RED(vredmin_vs_d, int64_t, int64_t, H8, H8, DO_MIN, clearq)
+
+/* vd[0] = and(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredand_vs_b, int8_t, int8_t, H1, H1, DO_AND, clearb)
+GEN_VEXT_RED(vredand_vs_h, int16_t, int16_t, H2, H2, DO_AND, clearh)
+GEN_VEXT_RED(vredand_vs_w, int32_t, int32_t, H4, H4, DO_AND, clearl)
+GEN_VEXT_RED(vredand_vs_d, int64_t, int64_t, H8, H8, DO_AND, clearq)
+
+/* vd[0] = or(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredor_vs_b, int8_t, int8_t, H1, H1, DO_OR, clearb)
+GEN_VEXT_RED(vredor_vs_h, int16_t, int16_t, H2, H2, DO_OR, clearh)
+GEN_VEXT_RED(vredor_vs_w, int32_t, int32_t, H4, H4, DO_OR, clearl)
+GEN_VEXT_RED(vredor_vs_d, int64_t, int64_t, H8, H8, DO_OR, clearq)
+
+/* vd[0] = xor(vs1[0], vs2[*]) */
+GEN_VEXT_RED(vredxor_vs_b, int8_t, int8_t, H1, H1, DO_XOR, clearb)
+GEN_VEXT_RED(vredxor_vs_h, int16_t, int16_t, H2, H2, DO_XOR, clearh)
+GEN_VEXT_RED(vredxor_vs_w, int32_t, int32_t, H4, H4, DO_XOR, clearl)
+GEN_VEXT_RED(vredxor_vs_d, int64_t, int64_t, H8, H8, DO_XOR, clearq)
-- 
2.23.0



  parent reply	other threads:[~2020-06-20  6:08 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 ` LIU Zhiwei [this message]
2020-06-20  4:36 ` [PATCH v10 46/61] target/riscv: vector wideing integer reduction instructions 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 ` [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=20200620043701.1323-46-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).