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 v2 04/14] tcg/loongarch64: Lower add/sub_vec to vadd/vsub
Date: Fri,  1 Sep 2023 17:30:57 +0800	[thread overview]
Message-ID: <20230901093258.942357-5-c@jia.je> (raw)
In-Reply-To: <20230901093258.942357-1-c@jia.je>

Lower the following ops:

- add_vec
- sub_vec

Signed-off-by: Jiajie Chen <c@jia.je>
---
 tcg/loongarch64/tcg-target-con-set.h |  1 +
 tcg/loongarch64/tcg-target.c.inc     | 58 ++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/tcg/loongarch64/tcg-target-con-set.h b/tcg/loongarch64/tcg-target-con-set.h
index d04916db25..eaa015e813 100644
--- a/tcg/loongarch64/tcg-target-con-set.h
+++ b/tcg/loongarch64/tcg-target-con-set.h
@@ -31,5 +31,6 @@ C_O1_I2(r, 0, rZ)
 C_O1_I2(r, rZ, ri)
 C_O1_I2(r, rZ, rJ)
 C_O1_I2(r, rZ, rZ)
+C_O1_I2(w, w, wi)
 C_O1_I2(w, w, wJ)
 C_O1_I4(r, rZ, rJ, rZ, rZ)
diff --git a/tcg/loongarch64/tcg-target.c.inc b/tcg/loongarch64/tcg-target.c.inc
index 18fe5fc148..555080f2b0 100644
--- a/tcg/loongarch64/tcg-target.c.inc
+++ b/tcg/loongarch64/tcg-target.c.inc
@@ -1641,6 +1641,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         [TCG_COND_LTU] = {OPC_VSLTI_BU, OPC_VSLTI_HU, OPC_VSLTI_WU, OPC_VSLTI_DU},
     };
     LoongArchInsn insn;
+    static const LoongArchInsn add_vec_insn[4] = {
+        OPC_VADD_B, OPC_VADD_H, OPC_VADD_W, OPC_VADD_D
+    };
+    static const LoongArchInsn add_vec_imm_insn[4] = {
+        OPC_VADDI_BU, OPC_VADDI_HU, OPC_VADDI_WU, OPC_VADDI_DU
+    };
+    static const LoongArchInsn sub_vec_insn[4] = {
+        OPC_VSUB_B, OPC_VSUB_H, OPC_VSUB_W, OPC_VSUB_D
+    };
+    static const LoongArchInsn sub_vec_imm_insn[4] = {
+        OPC_VSUBI_BU, OPC_VSUBI_HU, OPC_VSUBI_WU, OPC_VSUBI_DU
+    };
 
     a0 = args[0];
     a1 = args[1];
@@ -1707,6 +1719,46 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         }
         tcg_out32(s, encode_vdvjvk_insn(insn, a0, a1, a2));
         break;
+    case INDEX_op_add_vec:
+        if (const_args[2]) {
+            int64_t value = sextract64(a2, 0, 8 << vece);
+            /* Try vaddi/vsubi */
+            if (0 <= value && value <= 0x1f) {
+                tcg_out32(s, encode_vdvjuk5_insn(add_vec_imm_insn[vece], a0, \
+                                                 a1, value));
+                break;
+            } else if (-0x1f <= value && value < 0) {
+                tcg_out32(s, encode_vdvjuk5_insn(sub_vec_imm_insn[vece], a0, \
+                                                 a1, -value));
+                break;
+            }
+
+            /* Fallback to dupi + vadd */
+            tcg_out_dupi_vec(s, type, vece, temp_vec, a2);
+            a2 = temp_vec;
+        }
+        tcg_out32(s, encode_vdvjvk_insn(add_vec_insn[vece], a0, a1, a2));
+        break;
+    case INDEX_op_sub_vec:
+        if (const_args[2]) {
+            int64_t value = sextract64(a2, 0, 8 << vece);
+            /* Try vaddi/vsubi */
+            if (0 <= value && value <= 0x1f) {
+                tcg_out32(s, encode_vdvjuk5_insn(sub_vec_imm_insn[vece], a0, \
+                                                 a1, value));
+                break;
+            } else if (-0x1f <= value && value < 0) {
+                tcg_out32(s, encode_vdvjuk5_insn(add_vec_imm_insn[vece], a0, \
+                                                 a1, -value));
+                break;
+            }
+
+            /* Fallback to dupi + vsub */
+            tcg_out_dupi_vec(s, type, vece, temp_vec, a2);
+            a2 = temp_vec;
+        }
+        tcg_out32(s, encode_vdvjvk_insn(sub_vec_insn[vece], a0, a1, a2));
+        break;
     case INDEX_op_dupm_vec:
         tcg_out_dupm_vec(s, type, vece, a0, a1, a2);
         break;
@@ -1723,6 +1775,8 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_dup_vec:
     case INDEX_op_dupm_vec:
     case INDEX_op_cmp_vec:
+    case INDEX_op_add_vec:
+    case INDEX_op_sub_vec:
         return 1;
     default:
         return 0;
@@ -1887,6 +1941,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_cmp_vec:
         return C_O1_I2(w, w, wJ);
 
+    case INDEX_op_add_vec:
+    case INDEX_op_sub_vec:
+        return C_O1_I2(w, w, wi);
+
     default:
         g_assert_not_reached();
     }
-- 
2.42.0



  parent reply	other threads:[~2023-09-01  9:36 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-01  9:30 [PATCH v2 00/14] Lower TCG vector ops to LSX Jiajie Chen
2023-09-01  9:30 ` [PATCH v2 01/14] tcg/loongarch64: Import LSX instructions Jiajie Chen
2023-09-01 17:06   ` Richard Henderson
2023-09-01  9:30 ` [PATCH v2 02/14] tcg/loongarch64: Lower basic tcg vec ops to LSX Jiajie Chen
2023-09-01 17:05   ` Richard Henderson
2023-09-01  9:30 ` [PATCH v2 03/14] tcg/loongarch64: Lower cmp_vec to vseq/vsle/vslt Jiajie Chen
2023-09-01 17:24   ` Richard Henderson
2023-09-01 17:28     ` Jiajie Chen
2023-09-01 17:48       ` Richard Henderson
2023-09-02  1:06         ` Jiajie Chen
2023-09-01  9:30 ` Jiajie Chen [this message]
2023-09-01 17:58   ` [PATCH v2 04/14] tcg/loongarch64: Lower add/sub_vec to vadd/vsub Richard Henderson
2023-09-01  9:30 ` [PATCH v2 05/14] tcg/loongarch64: Lower vector bitwise operations Jiajie Chen
2023-09-01 17:59   ` Richard Henderson
2023-09-01  9:30 ` [PATCH v2 06/14] tcg/loongarch64: Lower neg_vec to vneg Jiajie Chen
2023-09-01  9:31 ` [PATCH v2 07/14] tcg/loongarch64: Lower mul_vec to vmul Jiajie Chen
2023-09-01  9:31 ` [PATCH v2 08/14] tcg/loongarch64: Lower vector min max ops Jiajie Chen
2023-09-01  9:31 ` [PATCH v2 09/14] tcg/loongarch64: Lower vector saturated ops Jiajie Chen
2023-09-01  9:31 ` [PATCH v2 10/14] tcg/loongarch64: Lower vector shift vector ops Jiajie Chen
2023-09-01  9:31 ` [PATCH v2 11/14] tcg/loongarch64: Lower bitsel_vec to vbitsel Jiajie Chen
2023-09-01  9:31 ` [PATCH v2 12/14] tcg/loongarch64: Lower vector shift integer ops Jiajie Chen
2023-09-01 18:01   ` Richard Henderson
2023-09-01  9:31 ` [PATCH v2 13/14] tcg/loongarch64: Lower rotv_vec ops to LSX Jiajie Chen
2023-09-01 18:02   ` Richard Henderson
2023-09-01  9:31 ` [PATCH v2 14/14] tcg/loongarch64: Lower rotli_vec to vrotri Jiajie Chen
2023-09-01 18:06   ` Richard Henderson

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=20230901093258.942357-5-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).