qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Kirill Batuzov <batuzovk@ispras.ru>
To: qemu-devel@nongnu.org
Cc: "Richard Henderson" <rth@twiddle.net>,
	"Paolo Bonzini" <pbonzini@redhat.com>,
	"Peter Crosthwaite" <crosthwaite.peter@gmail.com>,
	"Peter Maydell" <peter.maydell@linaro.org>,
	"Andrzej Zaborowski" <balrogg@gmail.com>,
	"Alex Bennée" <alex.bennee@linaro.org>,
	"Kirill Batuzov" <batuzovk@ispras.ru>
Subject: [Qemu-devel] [PATCH v2.1 13/21] tcg/i386: support remaining vector addition operations
Date: Thu,  2 Feb 2017 17:34:51 +0300	[thread overview]
Message-ID: <1486046099-17726-14-git-send-email-batuzovk@ispras.ru> (raw)
In-Reply-To: <1486046099-17726-1-git-send-email-batuzovk@ispras.ru>

Signed-off-by: Kirill Batuzov <batuzovk@ispras.ru>
---

I believe checkpatch warning here to be false-positive.

---
 tcg/i386/tcg-target.h     | 10 +++++++++
 tcg/i386/tcg-target.inc.c | 54 +++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 62 insertions(+), 2 deletions(-)

diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index 755ebaa..bd6cfe1 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -172,7 +172,17 @@ extern bool have_popcnt;
 #endif
 
 #ifdef TCG_TARGET_HAS_REG128
+#define TCG_TARGET_HAS_add_i8x16        1
+#define TCG_TARGET_HAS_add_i16x8        1
 #define TCG_TARGET_HAS_add_i32x4        1
+#define TCG_TARGET_HAS_add_i64x2        1
+#endif
+
+#ifdef TCG_TARGET_HAS_REGV64
+#define TCG_TARGET_HAS_add_i8x8         1
+#define TCG_TARGET_HAS_add_i16x4        1
+#define TCG_TARGET_HAS_add_i32x2        1
+#define TCG_TARGET_HAS_add_i64x1        1
 #endif
 
 #define TCG_TARGET_deposit_i32_valid(ofs, len) \
diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index 208bb81..d8f0d81 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -168,6 +168,11 @@ static bool have_lzcnt;
 #else
 # define have_lzcnt 0
 #endif
+#if defined(CONFIG_CPUID_H) && defined(bit_AVX) && defined(bit_OSXSAVE)
+static bool have_avx;
+#else
+# define have_avx 0
+#endif
 
 static tcg_insn_unit *tb_ret_addr;
 
@@ -393,7 +398,10 @@ static inline int tcg_target_const_match(tcg_target_long val, TCGType type,
 #define OPC_MOVQ_M2R    (0x7e | P_SSE_F30F)
 #define OPC_MOVQ_R2M    (0xd6 | P_SSE_660F)
 #define OPC_MOVQ_R2R    (0x7e | P_SSE_F30F)
+#define OPC_PADDB       (0xfc | P_SSE_660F)
+#define OPC_PADDW       (0xfd | P_SSE_660F)
 #define OPC_PADDD       (0xfe | P_SSE_660F)
+#define OPC_PADDQ       (0xd4 | P_SSE_660F)
 
 /* Group 1 opcode extensions for 0x80-0x83.
    These are also used as modifiers for OPC_ARITH.  */
@@ -1963,6 +1971,19 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     TCGArg a0, a1, a2;
     int c, const_a2, vexop, rexw = 0;
 
+    static const int vect_binop[] = {
+        [INDEX_op_add_i8x16] = OPC_PADDB,
+        [INDEX_op_add_i16x8] = OPC_PADDW,
+        [INDEX_op_add_i32x4] = OPC_PADDD,
+        [INDEX_op_add_i64x2] = OPC_PADDQ,
+
+        [INDEX_op_add_i8x8]  = OPC_PADDB,
+        [INDEX_op_add_i16x4] = OPC_PADDW,
+        [INDEX_op_add_i32x2] = OPC_PADDD,
+        [INDEX_op_add_i64x1] = OPC_PADDQ,
+    };
+
+
 #if TCG_TARGET_REG_BITS == 64
 # define OP_32_64(x) \
         case glue(glue(INDEX_op_, x), _i64): \
@@ -1972,6 +1993,17 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
 # define OP_32_64(x) \
         case glue(glue(INDEX_op_, x), _i32)
 #endif
+#define OP_V128_ALL(x) \
+        case glue(glue(INDEX_op_, x), _i8x16): \
+        case glue(glue(INDEX_op_, x), _i16x8): \
+        case glue(glue(INDEX_op_, x), _i32x4): \
+        case glue(glue(INDEX_op_, x), _i64x2)
+
+#define OP_V64_ALL(x) \
+        case glue(glue(INDEX_op_, x), _i8x8):  \
+        case glue(glue(INDEX_op_, x), _i16x4): \
+        case glue(glue(INDEX_op_, x), _i32x2): \
+        case glue(glue(INDEX_op_, x), _i64x1)
 
     /* Hoist the loads of the most common arguments.  */
     a0 = args[0];
@@ -2369,8 +2401,13 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         tcg_out_mb(s, a0);
         break;
 
-    case INDEX_op_add_i32x4:
-        tcg_out_modrm(s, OPC_PADDD, args[0], args[2]);
+    OP_V128_ALL(add):
+    OP_V64_ALL(add):
+        if (have_avx) {
+            tcg_out_vex_modrm(s, vect_binop[opc], args[0], args[1], args[2]);
+        } else {
+            tcg_out_modrm(s, vect_binop[opc], args[0], args[2]);
+        }
         break;
 
     case INDEX_op_mov_i32:  /* Always emitted via tcg_out_mov.  */
@@ -2383,6 +2420,8 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     }
 
 #undef OP_32_64
+#undef OP_V128_ALL
+#undef OP_V64_ALL
 }
 
 static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
@@ -2613,7 +2652,14 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
             return &s2;
         }
 
+    case INDEX_op_add_i8x16:
+    case INDEX_op_add_i16x8:
     case INDEX_op_add_i32x4:
+    case INDEX_op_add_i64x2:
+    case INDEX_op_add_i8x8:
+    case INDEX_op_add_i16x4:
+    case INDEX_op_add_i32x2:
+    case INDEX_op_add_i64x1:
         return &V_0_V;
 
     default:
@@ -2728,6 +2774,10 @@ static void tcg_target_init(TCGContext *s)
 #ifdef bit_POPCNT
         have_popcnt = (c & bit_POPCNT) != 0;
 #endif
+#if defined(bit_AVX) && defined(bit_OSXSAVE)
+        have_avx = (c & (bit_AVX | bit_OSXSAVE)) == (bit_AVX | bit_OSXSAVE);
+#endif
+
     }
 
     if (max >= 7) {
-- 
2.1.4

  parent reply	other threads:[~2017-02-02 14:35 UTC|newest]

Thread overview: 28+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-02-02 14:34 [Qemu-devel] [PATCH v2.1 00/20] Emulate guest vector operations with host vector operations Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 01/21] tcg: add support for 128bit vector type Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 02/21] tcg: add support for 64bit " Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 03/21] tcg: support representing vector type with smaller vector or scalar types Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 04/21] tcg: add ld_v128, ld_v64, st_v128 and st_v64 opcodes Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 05/21] tcg: add simple alias analysis Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 06/21] tcg: use results of alias analysis in liveness analysis Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 07/21] tcg: allow globals to overlap Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 08/21] tcg: add vector addition operations Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 09/21] target/arm: support access to vector guest registers as globals Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 10/21] target/arm: use vector opcode to handle vadd.<size> instruction Kirill Batuzov
2017-02-09 13:19   ` Philippe Mathieu-Daudé
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 11/21] tcg/i386: add support for vector opcodes Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 12/21] tcg/i386: support 64-bit vector operations Kirill Batuzov
2017-02-02 14:34 ` Kirill Batuzov [this message]
     [not found]   ` <2089cbe3-0e9b-fae2-0e35-224f2765dc28@amsat.org>
     [not found]     ` <32a902a1-e8c7-c2f7-ac66-148e02ee0b2d@amsat.org>
2017-02-21 13:29       ` [Qemu-devel] [PATCH v2.1 13/21] tcg/i386: support remaining vector addition operations Kirill Batuzov
2017-02-21 16:21         ` Alex Bennée
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 14/21] tcg: do not rely on exact values of MO_BSWAP or MO_SIGN in backend Kirill Batuzov
2017-05-05 13:59   ` Alex Bennée
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 15/21] target/aarch64: do not check for non-existent TCGMemOp Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 16/21] tcg: introduce new TCGMemOp - MO_128 Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 17/21] tcg: introduce qemu_ld_v128 and qemu_st_v128 opcodes Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 18/21] softmmu: create helpers for vector loads Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 19/21] tcg/i386: add support for qemu_ld_v128/qemu_st_v128 ops Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 20/21] target/arm: load two consecutive 64-bits vector regs as a 128-bit vector reg Kirill Batuzov
2017-02-02 14:34 ` [Qemu-devel] [PATCH v2.1 21/21] tcg/README: update README to include information about vector opcodes Kirill Batuzov
2017-02-02 15:25 ` [Qemu-devel] [PATCH v2.1 00/20] Emulate guest vector operations with host vector operations no-reply
2017-02-21 12:19 ` Kirill Batuzov

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=1486046099-17726-14-git-send-email-batuzovk@ispras.ru \
    --to=batuzovk@ispras.ru \
    --cc=alex.bennee@linaro.org \
    --cc=balrogg@gmail.com \
    --cc=crosthwaite.peter@gmail.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=rth@twiddle.net \
    /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).