qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Huang Tao <eric.huang@linux.alibaba.com>
To: qemu-devel@nongnu.org
Cc: qemu-riscv@nongnu.org, zhiwei_liu@linux.alibaba.com,
	dbarboza@ventanamicro.com, liwei1518@gmail.com,
	bin.meng@windriver.com, alistair.francis@wdc.com,
	palmer@dabbelt.com, Huang Tao <eric.huang@linux.alibaba.com>
Subject: [PATCH 11/65] target/riscv: Add unit-stride store instructions for XTheadVector
Date: Fri, 12 Apr 2024 15:36:41 +0800	[thread overview]
Message-ID: <20240412073735.76413-12-eric.huang@linux.alibaba.com> (raw)
In-Reply-To: <20240412073735.76413-1-eric.huang@linux.alibaba.com>

XTheadVector unit-stride store instructions diff from RVV1.0 in the following
points:
1. Different mask reg layout.
2. Different vector reg element width.
3. Different tail/masked elements process policy.
4. Different check policy.

The detials of the difference are the same as strided store instruction, as
unit-stride is the special case of strided operations.

Signed-off-by: Huang Tao <eric.huang@linux.alibaba.com>
---
 target/riscv/helper.h                         | 26 ++++++++
 .../riscv/insn_trans/trans_xtheadvector.c.inc | 59 +++++++++++++++++--
 target/riscv/xtheadvector_helper.c            | 31 ++++++++++
 3 files changed, 112 insertions(+), 4 deletions(-)

diff --git a/target/riscv/helper.h b/target/riscv/helper.h
index f2fa8425b3..eb31784e18 100644
--- a/target/riscv/helper.h
+++ b/target/riscv/helper.h
@@ -1361,3 +1361,29 @@ DEF_HELPER_5(th_vlwu_v_w, void, ptr, ptr, tl, env, i32)
 DEF_HELPER_5(th_vlwu_v_w_mask, void, ptr, ptr, tl, env, i32)
 DEF_HELPER_5(th_vlwu_v_d, void, ptr, ptr, tl, env, i32)
 DEF_HELPER_5(th_vlwu_v_d_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_b_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_h_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_w_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsb_v_d_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsh_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsh_v_h_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsh_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsh_v_w_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsh_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsh_v_d_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsw_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsw_v_w_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsw_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vsw_v_d_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_b, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_b_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_h, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_h_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_w, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_w_mask, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_d, void, ptr, ptr, tl, env, i32)
+DEF_HELPER_5(th_vse_v_d_mask, void, ptr, ptr, tl, env, i32)
diff --git a/target/riscv/insn_trans/trans_xtheadvector.c.inc b/target/riscv/insn_trans/trans_xtheadvector.c.inc
index eb910acf40..9b88ea2fa4 100644
--- a/target/riscv/insn_trans/trans_xtheadvector.c.inc
+++ b/target/riscv/insn_trans/trans_xtheadvector.c.inc
@@ -398,6 +398,61 @@ GEN_TH_TRANS(th_vlbu_v, 4, r2nfvm, ld_us_op_th, ld_us_check_th)
 GEN_TH_TRANS(th_vlhu_v, 5, r2nfvm, ld_us_op_th, ld_us_check_th)
 GEN_TH_TRANS(th_vlwu_v, 6, r2nfvm, ld_us_op_th, ld_us_check_th)
 
+/*
+ * This function is almost the copy of st_us_op, except:
+ * 1) different data encoding.
+ * 2) XTheadVector has more situations, depending on SEW.
+ */
+static bool st_us_op_th(DisasContext *s, arg_r2nfvm *a, uint8_t seq)
+{
+    uint32_t data = 0;
+    gen_helper_ldst_us_th *fn;
+    static gen_helper_ldst_us_th * const fns[2][4][4] = {
+        /* masked unit stride load and store */
+        { { gen_helper_th_vsb_v_b_mask,  gen_helper_th_vsb_v_h_mask,
+            gen_helper_th_vsb_v_w_mask,  gen_helper_th_vsb_v_d_mask },
+          { NULL,                        gen_helper_th_vsh_v_h_mask,
+            gen_helper_th_vsh_v_w_mask,  gen_helper_th_vsh_v_d_mask },
+          { NULL,                        NULL,
+            gen_helper_th_vsw_v_w_mask,  gen_helper_th_vsw_v_d_mask },
+          { gen_helper_th_vse_v_b_mask,  gen_helper_th_vse_v_h_mask,
+            gen_helper_th_vse_v_w_mask,  gen_helper_th_vse_v_d_mask } },
+        /* unmasked unit stride store */
+        { { gen_helper_th_vsb_v_b,  gen_helper_th_vsb_v_h,
+            gen_helper_th_vsb_v_w,  gen_helper_th_vsb_v_d },
+          { NULL,                   gen_helper_th_vsh_v_h,
+            gen_helper_th_vsh_v_w,  gen_helper_th_vsh_v_d },
+          { NULL,                   NULL,
+            gen_helper_th_vsw_v_w,  gen_helper_th_vsw_v_d },
+          { gen_helper_th_vse_v_b,  gen_helper_th_vse_v_h,
+            gen_helper_th_vse_v_w,  gen_helper_th_vse_v_d } }
+    };
+
+    fn =  fns[a->vm][seq][s->sew];
+    if (fn == NULL) {
+        return false;
+    }
+
+    data = FIELD_DP32(data, VDATA_TH, MLEN, s->mlen);
+    data = FIELD_DP32(data, VDATA_TH, VM, a->vm);
+    data = FIELD_DP32(data, VDATA_TH, LMUL, s->lmul);
+    data = FIELD_DP32(data, VDATA_TH, NF, a->nf);
+    return ldst_us_trans(a->rd, a->rs1, data, fn, s, true);
+}
+
+static bool st_us_check_th(DisasContext *s, arg_r2nfvm* a)
+{
+    return (require_xtheadvector(s) &&
+            vext_check_isa_ill(s) &&
+            th_check_reg(s, a->rd, false) &&
+            th_check_nf(s, a->rd, a->nf));
+}
+
+GEN_TH_TRANS(th_vsb_v, 0, r2nfvm, st_us_op_th, st_us_check_th)
+GEN_TH_TRANS(th_vsh_v, 1, r2nfvm, st_us_op_th, st_us_check_th)
+GEN_TH_TRANS(th_vsw_v, 2, r2nfvm, st_us_op_th, st_us_check_th)
+GEN_TH_TRANS(th_vse_v, 3, r2nfvm, st_us_op_th, st_us_check_th)
+
 #define TH_TRANS_STUB(NAME)                                \
 static bool trans_##NAME(DisasContext *s, arg_##NAME *a)   \
 {                                                          \
@@ -411,10 +466,6 @@ TH_TRANS_STUB(th_vleff_v)
 TH_TRANS_STUB(th_vlbuff_v)
 TH_TRANS_STUB(th_vlhuff_v)
 TH_TRANS_STUB(th_vlwuff_v)
-TH_TRANS_STUB(th_vsb_v)
-TH_TRANS_STUB(th_vsh_v)
-TH_TRANS_STUB(th_vsw_v)
-TH_TRANS_STUB(th_vse_v)
 TH_TRANS_STUB(th_vlxb_v)
 TH_TRANS_STUB(th_vlxh_v)
 TH_TRANS_STUB(th_vlxw_v)
diff --git a/target/riscv/xtheadvector_helper.c b/target/riscv/xtheadvector_helper.c
index 7566ab8e31..5c05cd5aa6 100644
--- a/target/riscv/xtheadvector_helper.c
+++ b/target/riscv/xtheadvector_helper.c
@@ -405,3 +405,34 @@ GEN_TH_LD_US(th_vlhu_v_w, uint16_t, uint32_t, ldhu_w, clearl_th)
 GEN_TH_LD_US(th_vlhu_v_d, uint16_t, uint64_t, ldhu_d, clearq_th)
 GEN_TH_LD_US(th_vlwu_v_w, uint32_t, uint32_t, ldwu_w, clearl_th)
 GEN_TH_LD_US(th_vlwu_v_d, uint32_t, uint64_t, ldwu_d, clearq_th)
+
+/* similar to GEN_GEN_VEXT_ST_US, change the function */
+#define GEN_TH_ST_US(NAME, MTYPE, ETYPE, STORE_FN)                      \
+void HELPER(NAME##_mask)(void *vd, void *v0, target_ulong base,         \
+                         CPURISCVState *env, uint32_t desc)             \
+{                                                                       \
+    uint32_t stride = th_nf(desc) * sizeof(MTYPE);                      \
+    th_ldst_stride(vd, v0, base, stride, env, desc, false, STORE_FN,    \
+                   NULL, sizeof(ETYPE), sizeof(MTYPE), GETPC());        \
+}                                                                       \
+                                                                        \
+void HELPER(NAME)(void *vd, void *v0, target_ulong base,                \
+                  CPURISCVState *env, uint32_t desc)                    \
+{                                                                       \
+    th_ldst_us(vd, base, env, desc, STORE_FN, NULL,                     \
+               sizeof(ETYPE), sizeof(MTYPE), GETPC());                  \
+}
+
+GEN_TH_ST_US(th_vsb_v_b, int8_t,  int8_t , stb_b)
+GEN_TH_ST_US(th_vsb_v_h, int8_t,  int16_t, stb_h)
+GEN_TH_ST_US(th_vsb_v_w, int8_t,  int32_t, stb_w)
+GEN_TH_ST_US(th_vsb_v_d, int8_t,  int64_t, stb_d)
+GEN_TH_ST_US(th_vsh_v_h, int16_t, int16_t, sth_h)
+GEN_TH_ST_US(th_vsh_v_w, int16_t, int32_t, sth_w)
+GEN_TH_ST_US(th_vsh_v_d, int16_t, int64_t, sth_d)
+GEN_TH_ST_US(th_vsw_v_w, int32_t, int32_t, stw_w)
+GEN_TH_ST_US(th_vsw_v_d, int32_t, int64_t, stw_d)
+GEN_TH_ST_US(th_vse_v_b, int8_t,  int8_t , ste_b)
+GEN_TH_ST_US(th_vse_v_h, int16_t, int16_t, ste_h)
+GEN_TH_ST_US(th_vse_v_w, int32_t, int32_t, ste_w)
+GEN_TH_ST_US(th_vse_v_d, int64_t, int64_t, ste_d)
-- 
2.44.0



  parent reply	other threads:[~2024-04-12  8:01 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-04-12  7:36 [PATCH 00/65]target/riscv: Support XTheadVector extension Huang Tao
2024-04-12  7:36 ` [PATCH 01/65] riscv: thead: Add th.sxstatus CSR emulation Huang Tao
2024-04-12  7:36 ` [PATCH 02/65] target/riscv: Reuse th_csr.c to add user-mode csrs Huang Tao
2024-04-12  7:36 ` [PATCH 03/65] target/riscv: Add properties for XTheadVector extension Huang Tao
2024-04-12  7:36 ` [PATCH 04/65] target/riscv: Override some csr ops for XTheadVector Huang Tao
2024-04-12  7:36 ` [PATCH 05/65] target/riscv: Add mlen in DisasContext Huang Tao
2024-04-12  7:36 ` [PATCH 06/65] target/riscv: Implement insns decode rules for XTheadVector Huang Tao
2024-04-12  7:36 ` [PATCH 07/65] target/riscv: implement th.vsetvl{i} " Huang Tao
2024-04-12  7:36 ` [PATCH 08/65] target/riscv: Add strided load instructions " Huang Tao
2024-04-12  7:36 ` [PATCH 09/65] target/riscv: Add strided store " Huang Tao
2024-04-12  7:36 ` [PATCH 10/65] target/riscv: Add unit-stride load " Huang Tao
2024-04-12  7:36 ` Huang Tao [this message]
2024-04-12  7:36 ` [PATCH 12/65] target/riscv: Add indexed " Huang Tao
2024-04-12  7:36 ` [PATCH 13/65] target/riscv: Add indexed store " Huang Tao
2024-04-12  7:36 ` [PATCH 14/65] target/riscv: Add unit-stride fault-only-first " Huang Tao
2024-04-12  7:36 ` [PATCH 15/65] target/riscv: Add vector amo operations " Huang Tao
2024-04-12  7:36 ` [PATCH 16/65] target/riscv: Add single-width integer add and subtract instructions " Huang Tao
2024-04-12  7:36 ` [PATCH 17/65] target/riscv: Add widening integer add/subtract " Huang Tao
2024-04-12  7:36 ` [PATCH 18/65] target/riscv: Add integer add-with-carry/sub-with-borrow " Huang Tao
2024-04-12  7:36 ` [PATCH 19/65] target/riscv: Add bitwise logical " Huang Tao
2024-04-12  7:36 ` [PATCH 20/65] target/riscv: Add single-width bit shift " Huang Tao
2024-04-12  7:36 ` [PATCH 21/65] target/riscv: Add narrowing integer right " Huang Tao
2024-04-12  7:36 ` [PATCH 22/65] target/riscv: Add integer compare " Huang Tao
2024-04-12  7:36 ` [PATCH 23/65] target/riscv: Add integer min/max " Huang Tao
2024-04-12  7:36 ` [PATCH 24/65] target/riscv: Add single-width integer multiply " Huang Tao
2024-04-12  7:36 ` [PATCH 25/65] target/riscv: Add integer divide " Huang Tao
2024-04-12  7:36 ` [PATCH 26/65] target/riscv: Add widening integer multiply " Huang Tao
2024-04-12  7:36 ` [PATCH 27/65] target/riscv: Add single-width integer multiply-add " Huang Tao
2024-04-12  7:36 ` [PATCH 28/65] target/riscv: Add widening " Huang Tao
2024-04-12  7:36 ` [PATCH 29/65] target/riscv: Add integer merge and move " Huang Tao
2024-04-12  7:37 ` [PATCH 30/65] target/riscv: Add single-width saturating add and sub " Huang Tao
2024-04-12  7:37 ` [PATCH 31/65] target/riscv: Add single-width average " Huang Tao
2024-04-12  7:37 ` [PATCH 32/65] target/riscv: Add single-width fractional mul with rounding and saturation " Huang Tao
2024-04-12  7:37 ` [PATCH 33/65] target/riscv: Add widening saturating scaled multiply-add instructions " Huang Tao
2024-04-12  7:37 ` [PATCH 34/65] target/riscv: Add single-width scaling shift " Huang Tao
2024-04-12  7:37 ` [PATCH 35/65] target/riscv: Add narrowing fixed-point clip " Huang Tao
2024-04-12  7:37 ` [PATCH 36/65] target/riscv: Add single-width floating-point add/sub " Huang Tao
2024-04-12  7:37 ` [PATCH 37/65] target/riscv: Add widening " Huang Tao
2024-04-12  7:37 ` [PATCH 38/65] target/riscv: Add single-width floating-point multiply/divide " Huang Tao
2024-04-12  7:37 ` [PATCH 39/65] target/riscv: Add widening floating-point multiply " Huang Tao
2024-04-12  7:37 ` [PATCH 40/65] target/riscv: Add single-width floating-point fused multiply-add " Huang Tao
2024-04-12  7:37 ` [PATCH 41/65] target/riscv: Add widening floating-point fused mul-add " Huang Tao
2024-04-12  7:37 ` [PATCH 42/65] target/riscv: Add floating-pointing square-root " Huang Tao
2024-04-12  7:37 ` [PATCH 43/65] target/riscv: Add floating-point MIN/MAX " Huang Tao
2024-04-12  7:37 ` [PATCH 44/65] target/riscv: Add floating-point sign-injection " Huang Tao
2024-04-12  7:37 ` [PATCH 45/65] target/riscv: Add floating-point compare " Huang Tao
2024-04-12  7:37 ` [PATCH 46/65] target/riscv: Add floating-point classify and merge " Huang Tao
2024-04-12  7:37 ` [PATCH 47/65] target/riscv: Add single-width floating-point/integer type-convert " Huang Tao
2024-04-12  7:37 ` [PATCH 48/65] target/riscv: Add widening " Huang Tao
2024-04-12  7:37 ` [PATCH 49/65] target/riscv: Add narrowing " Huang Tao
2024-04-12  7:37 ` [PATCH 50/65] target/riscv: Add single-width integer reduction " Huang Tao
2024-04-12  7:37 ` [PATCH 51/65] target/riscv: Add widening " Huang Tao
2024-04-12  7:37 ` [PATCH 52/65] target/riscv: Add single-width floating-point " Huang Tao
2024-04-12  7:37 ` [PATCH 53/65] target/riscv: Add widening " Huang Tao
2024-04-12  7:37 ` [PATCH 54/65] target/riscv: Add mask-register logical " Huang Tao
2024-04-12  7:37 ` [PATCH 55/65] target/riscv: Add vector mask population count vmpopc " Huang Tao
2024-04-12  7:37 ` [PATCH 56/65] target/riscv: Add th.vmfirst.m " Huang Tao
2024-04-12  7:37 ` [PATCH 57/65] target/riscv: Add set-X-first mask bit instructrions " Huang Tao
2024-04-12  7:37 ` [PATCH 58/65] target/riscv: Add vector iota instruction " Huang Tao
2024-04-12  7:37 ` [PATCH 59/65] target/riscv: Add vector element index " Huang Tao
2024-04-12  7:37 ` [PATCH 60/65] target/riscv: Add integer extract and scalar move instructions " Huang Tao
2024-04-12  7:37 ` [PATCH 61/65] target/riscv: Add floating-point " Huang Tao
2024-04-12  7:37 ` [PATCH 62/65] target/riscv: Add vector slide " Huang Tao
2024-04-12  7:37 ` [PATCH 63/65] target/riscv: Add vector register gather " Huang Tao
2024-04-12  7:37 ` [PATCH 64/65] target/riscv: Add vector compress instruction " Huang Tao
2024-04-12  7:37 ` [PATCH 65/65] target/riscv: Enable XTheadVector extension for c906 Huang Tao

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=20240412073735.76413-12-eric.huang@linux.alibaba.com \
    --to=eric.huang@linux.alibaba.com \
    --cc=alistair.francis@wdc.com \
    --cc=bin.meng@windriver.com \
    --cc=dbarboza@ventanamicro.com \
    --cc=liwei1518@gmail.com \
    --cc=palmer@dabbelt.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-riscv@nongnu.org \
    --cc=zhiwei_liu@linux.alibaba.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).