qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Jiajie Chen <c@jia.je>
To: qemu-devel@nongnu.org
Cc: richard.henderson@linaro.org, gaosong@loongson.cn,
	git@xen0n.name, Jiajie Chen <c@jia.je>
Subject: [PATCH v3 16/16] tcg/loongarch64: Implement 128-bit load & store
Date: Sat,  2 Sep 2023 13:02:16 +0800	[thread overview]
Message-ID: <20230902050415.1832700-17-c@jia.je> (raw)
In-Reply-To: <20230902050415.1832700-1-c@jia.je>

If LSX is available, use LSX instructions to implement 128-bit load &
store.

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target-con-set.h |  2 ++
 tcg/loongarch64/tcg-target.c.inc     | 42 ++++++++++++++++++++++++++++
 tcg/loongarch64/tcg-target.h         |  2 +-
 3 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index 914572d21b..77d62e38e7 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -18,6 +18,7 @@ C_O0_I1(r)
 C_O0_I2(rZ, r)
 C_O0_I2(rZ, rZ)
 C_O0_I2(w, r)
+C_O0_I3(r, r, r)
 C_O1_I1(r, r)
 C_O1_I1(w, r)
 C_O1_I1(w, w)
@@ -37,3 +38,4 @@ C_O1_I2(w, w, wM)
 C_O1_I2(w, w, wA)
 C_O1_I3(w, w, w, w)
 C_O1_I4(r, rZ, rJ, rZ, rZ)
+C_O2_I1(r, r, r)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 2b001598e2..9d999ef58c 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1081,6 +1081,31 @@ static void tcg_out_qemu_st(TCGContext *s, TCGReg data_reg, TCGReg addr_reg,
     }
 }
 
+static void tcg_out_qemu_ldst_i128(TCGContext *s, TCGReg data_lo, TCGReg data_hi,
+                                   TCGReg addr_reg, MemOpIdx oi, bool is_ld)
+{
+    TCGLabelQemuLdst *ldst;
+    HostAddress h;
+
+    ldst = prepare_host_addr(s, &h, addr_reg, oi, true);
+    if (is_ld) {
+        tcg_out_opc_vldx(s, TCG_VEC_TMP0, h.base, h.index);
+        tcg_out_opc_vpickve2gr_d(s, data_lo, TCG_VEC_TMP0, 0);
+        tcg_out_opc_vpickve2gr_d(s, data_hi, TCG_VEC_TMP0, 1);
+    } else {
+        tcg_out_opc_vinsgr2vr_d(s, TCG_VEC_TMP0, data_lo, 0);
+        tcg_out_opc_vinsgr2vr_d(s, TCG_VEC_TMP0, data_hi, 1);
+        tcg_out_opc_vstx(s, TCG_VEC_TMP0, h.base, h.index);
+    }
+
+    if (ldst) {
+        ldst->type = TCG_TYPE_I128;
+        ldst->datalo_reg = data_lo;
+        ldst->datahi_reg = data_hi;
+        ldst->raddr = tcg_splitwx_to_rx(s->code_ptr);
+    }
+}
+
 /*
  * Entry-points
  */
@@ -1145,6 +1170,7 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     TCGArg a0 = args[0];
     TCGArg a1 = args[1];
     TCGArg a2 = args[2];
+    TCGArg a3 = args[3];
     int c2 = const_args[2];
 
     switch (opc) {
@@ -1507,6 +1533,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_qemu_ld_a64_i64:
         tcg_out_qemu_ld(s, a0, a1, a2, TCG_TYPE_I64);
         break;
+    case INDEX_op_qemu_ld_a32_i128:
+    case INDEX_op_qemu_ld_a64_i128:
+        tcg_out_qemu_ldst_i128(s, a0, a1, a2, a3, true);
+        break;
     case INDEX_op_qemu_st_a32_i32:
     case INDEX_op_qemu_st_a64_i32:
         tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I32);
@@ -1515,6 +1545,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_qemu_st_a64_i64:
         tcg_out_qemu_st(s, a0, a1, a2, TCG_TYPE_I64);
         break;
+    case INDEX_op_qemu_st_a32_i128:
+    case INDEX_op_qemu_st_a64_i128:
+        tcg_out_qemu_ldst_i128(s, a0, a1, a2, a3, false);
+        break;
 
     case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
     case INDEX_op_mov_i64:
@@ -1995,6 +2029,14 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_qemu_st_a64_i64:
         return C_O0_I2(rZ, r);
 
+    case INDEX_op_qemu_ld_a32_i128:
+    case INDEX_op_qemu_ld_a64_i128:
+        return C_O2_I1(r, r, r);
+
+    case INDEX_op_qemu_st_a32_i128:
+    case INDEX_op_qemu_st_a64_i128:
+        return C_O0_I3(r, r, r);
+
     case INDEX_op_brcond_i32:
     case INDEX_op_brcond_i64:
         return C_O0_I2(rZ, rZ);
diff --git a/tcg/loongarch64/tcg-target.h b/tcg/loongarch64/tcg-target.h
index 67b0a95532..03017672f6 100644
--- a/tcg/loongarch64/tcg-target.h
+++ b/tcg/loongarch64/tcg-target.h
@@ -171,7 +171,7 @@ extern bool use_lsx_instructions;
 #define TCG_TARGET_HAS_muluh_i64        1
 #define TCG_TARGET_HAS_mulsh_i64        1
 
-#define TCG_TARGET_HAS_qemu_ldst_i128   0
+#define TCG_TARGET_HAS_qemu_ldst_i128   use_lsx_instructions
 
 #define TCG_TARGET_HAS_v64              0
 #define TCG_TARGET_HAS_v128             use_lsx_instructions
-- 
2.42.0



  parent reply	other threads:[~2023-09-02  5:07 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-02  5:02 [PATCH v3 00/16] Lower TCG vector ops to LSX Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 01/16] tcg/loongarch64: Import LSX instructions Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 02/16] tcg/loongarch64: Lower basic tcg vec ops to LSX Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 03/16] tcg: pass vece to tcg_target_const_match() Jiajie Chen
2023-09-03  0:50   ` Richard Henderson
2023-09-02  5:02 ` [PATCH v3 04/16] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt Jiajie Chen
2023-09-03  0:50   ` Richard Henderson
2023-09-02  5:02 ` [PATCH v3 05/16] tcg/loongarch64: Lower add/sub_vec to vadd/vsub Jiajie Chen
2023-09-03  0:54   ` Richard Henderson
2023-09-02  5:02 ` [PATCH v3 06/16] tcg/loongarch64: Lower vector bitwise operations Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 07/16] tcg/loongarch64: Lower neg_vec to vneg Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 08/16] tcg/loongarch64: Lower mul_vec to vmul Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 09/16] tcg/loongarch64: Lower vector min max ops Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 10/16] tcg/loongarch64: Lower vector saturated ops Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 11/16] tcg/loongarch64: Lower vector shift vector ops Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 12/16] tcg/loongarch64: Lower bitsel_vec to vbitsel Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 13/16] tcg/loongarch64: Lower vector shift integer ops Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 14/16] tcg/loongarch64: Lower rotv_vec ops to LSX Jiajie Chen
2023-09-02  5:02 ` [PATCH v3 15/16] tcg/loongarch64: Lower rotli_vec to vrotri Jiajie Chen
2023-09-02  5:02 ` Jiajie Chen [this message]
2023-09-03  1:06   ` [PATCH v3 16/16] tcg/loongarch64: Implement 128-bit load & store Richard Henderson
2023-09-03  1:10     ` Jiajie Chen
2023-09-04  1:43       ` gaosong
2023-09-04  9:43         ` bibo mao

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=20230902050415.1832700-17-c@jia.je \
    --to=c@jia.je \
    --cc=gaosong@loongson.cn \
    --cc=git@xen0n.name \
    --cc=qemu-devel@nongnu.org \
    --cc=richard.henderson@linaro.org \
    /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).