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 19/21] tcg/i386: add support for qemu_ld_v128/qemu_st_v128 ops
Date: Thu,  2 Feb 2017 17:34:57 +0300	[thread overview]
Message-ID: <1486046099-17726-20-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>
---
 tcg/i386/tcg-target.inc.c | 68 ++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 61 insertions(+), 7 deletions(-)

diff --git a/tcg/i386/tcg-target.inc.c b/tcg/i386/tcg-target.inc.c
index 1e6edc0..4647e97 100644
--- a/tcg/i386/tcg-target.inc.c
+++ b/tcg/i386/tcg-target.inc.c
@@ -1342,6 +1342,7 @@ static void * const qemu_ld_helpers[] = {
     [MO_BEUW] = helper_be_lduw_mmu,
     [MO_BEUL] = helper_be_ldul_mmu,
     [MO_BEQ]  = helper_be_ldq_mmu,
+    [MO_128]  = helper_te_ldv128_mmu,
 };
 
 /* helper signature: helper_ret_st_mmu(CPUState *env, target_ulong addr,
@@ -1355,6 +1356,7 @@ static void * const qemu_st_helpers[] = {
     [MO_BEUW] = helper_be_stw_mmu,
     [MO_BEUL] = helper_be_stl_mmu,
     [MO_BEQ]  = helper_be_stq_mmu,
+    [MO_128]  = helper_te_stv128_mmu,
 };
 
 /* Perform the TLB load and compare.
@@ -1521,12 +1523,30 @@ static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
         ofs += 4;
 
         tcg_out_sti(s, TCG_TYPE_PTR, (uintptr_t)l->raddr, TCG_REG_ESP, ofs);
+
+        if ((opc & MO_SSIZE) == MO_128) {
+            ofs += 4;
+            tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_EAX, TCG_REG_ESP);
+            tcg_out_addi(s, TCG_REG_EAX, TCG_STATIC_CALL_ARGS_SIZE - 16);
+            tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_EAX, TCG_REG_ESP, ofs);
+        }
     } else {
         tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
         /* The second argument is already loaded with addrlo.  */
         tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[2], oi);
         tcg_out_movi(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[3],
                      (uintptr_t)l->raddr);
+        if ((opc & MO_SSIZE) == MO_128) {
+            tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_EAX, TCG_REG_ESP);
+            tcg_out_addi(s, TCG_REG_EAX, TCG_STATIC_CALL_ARGS_SIZE - 16);
+            if (ARRAY_SIZE(tcg_target_call_iarg_regs) > 4) {
+                tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[4],
+                            TCG_REG_EAX);
+            } else {
+                tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_EAX,
+                            TCG_REG_ESP, TCG_TARGET_CALL_STACK_OFFSET);
+            }
+        }
     }
 
     tcg_out_call(s, qemu_ld_helpers[opc & (MO_BSWAP | MO_SIZE)]);
@@ -1562,6 +1582,11 @@ static void tcg_out_qemu_ld_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
             tcg_out_mov(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_EDX);
         }
         break;
+    case MO_128:
+        tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_EAX, TCG_REG_ESP);
+        tcg_out_addi(s, TCG_REG_EAX, TCG_STATIC_CALL_ARGS_SIZE - 16);
+        tcg_out_ld(s, TCG_TYPE_V128, l->datalo_reg, TCG_REG_EAX, 0);
+        break;
     default:
         tcg_abort();
     }
@@ -1601,12 +1626,20 @@ static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
             ofs += 4;
         }
 
-        tcg_out_st(s, TCG_TYPE_I32, l->datalo_reg, TCG_REG_ESP, ofs);
-        ofs += 4;
-
-        if (s_bits == MO_64) {
-            tcg_out_st(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_ESP, ofs);
+        if (s_bits == MO_128) {
+            tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_EAX, TCG_REG_ESP);
+            tcg_out_addi(s, TCG_REG_EAX, TCG_STATIC_CALL_ARGS_SIZE - 16);
+            tcg_out_st(s, TCG_TYPE_V128, l->datalo_reg, TCG_REG_EAX, 0);
+            tcg_out_st(s, TCG_TYPE_PTR, TCG_REG_EAX, TCG_REG_ESP, ofs);
             ofs += 4;
+        } else {
+            tcg_out_st(s, TCG_TYPE_I32, l->datalo_reg, TCG_REG_ESP, ofs);
+            ofs += 4;
+
+            if (s_bits == MO_64) {
+                tcg_out_st(s, TCG_TYPE_I32, l->datahi_reg, TCG_REG_ESP, ofs);
+                ofs += 4;
+            }
         }
 
         tcg_out_sti(s, TCG_TYPE_I32, oi, TCG_REG_ESP, ofs);
@@ -1618,8 +1651,16 @@ static void tcg_out_qemu_st_slow_path(TCGContext *s, TCGLabelQemuLdst *l)
     } else {
         tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[0], TCG_AREG0);
         /* The second argument is already loaded with addrlo.  */
-        tcg_out_mov(s, (s_bits == MO_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
-                    tcg_target_call_iarg_regs[2], l->datalo_reg);
+        if (s_bits == MO_128) {
+            tcg_out_mov(s, TCG_TYPE_PTR, TCG_REG_RAX, TCG_REG_ESP);
+            tcg_out_addi(s, TCG_REG_RAX, TCG_STATIC_CALL_ARGS_SIZE - 16);
+            tcg_out_st(s, TCG_TYPE_V128, l->datalo_reg, TCG_REG_RAX, 0);
+            tcg_out_mov(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[2],
+                        TCG_REG_RAX);
+        } else {
+            tcg_out_mov(s, (s_bits == MO_64 ? TCG_TYPE_I64 : TCG_TYPE_I32),
+                        tcg_target_call_iarg_regs[2], l->datalo_reg);
+        }
         tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[3], oi);
 
         if (ARRAY_SIZE(tcg_target_call_iarg_regs) > 4) {
@@ -1751,6 +1792,10 @@ static void tcg_out_qemu_ld_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
             }
         }
         break;
+    case MO_128:
+        tcg_out_modrm_sib_offset(s, OPC_MOVDQU_M2R + seg, datalo,
+                                 base, index, 0, ofs);
+        break;
     default:
         tcg_abort();
     }
@@ -1894,6 +1939,9 @@ static void tcg_out_qemu_st_direct(TCGContext *s, TCGReg datalo, TCGReg datahi,
             tcg_out_modrm_offset(s, movop + seg, datahi, base, ofs+4);
         }
         break;
+    case MO_128:
+        tcg_out_modrm_offset(s, OPC_MOVDQU_R2M + seg, datalo, base, ofs);
+        break;
     default:
         tcg_abort();
     }
@@ -2264,12 +2312,18 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_qemu_ld_i64:
         tcg_out_qemu_ld(s, args, 1);
         break;
+    case INDEX_op_qemu_ld_v128:
+        tcg_out_qemu_ld(s, args, 0);
+        break;
     case INDEX_op_qemu_st_i32:
         tcg_out_qemu_st(s, args, 0);
         break;
     case INDEX_op_qemu_st_i64:
         tcg_out_qemu_st(s, args, 1);
         break;
+    case INDEX_op_qemu_st_v128:
+        tcg_out_qemu_st(s, args, 0);
+        break;
 
     OP_32_64(mulu2):
         tcg_out_modrm(s, OPC_GRP3_Ev + rexw, EXT3_MUL, args[3]);
-- 
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 ` [Qemu-devel] [PATCH v2.1 13/21] tcg/i386: support remaining vector addition operations Kirill Batuzov
     [not found]   ` <2089cbe3-0e9b-fae2-0e35-224f2765dc28@amsat.org>
     [not found]     ` <32a902a1-e8c7-c2f7-ac66-148e02ee0b2d@amsat.org>
2017-02-21 13:29       ` 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 ` Kirill Batuzov [this message]
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=1486046099-17726-20-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).