[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PULL 13/26] tcg/aarch64: Implement goto_ptr
From: |
Richard Henderson |
Subject: |
[Qemu-devel] [PULL 13/26] tcg/aarch64: Implement goto_ptr |
Date: |
Mon, 5 Jun 2017 09:52:20 -0700 |
Measurements:
SPECint06 (test set), x86_64-linux-user. Host: APM 64-bit
ARMv8 (Atlas/A57) @ 2.4 GHz
1.45x
+-+-------------------------------------------------------------------------------------------------------------+-+
| *****
|
| +++ * *
+goto-ptr |
1.4x
+-+...*****............................*...*....................................................................+-+
| *+++* * *
+++ |
1.35x
+-+...*...*............................*...*...........................*****....................................+-+
| * * * *
*+++* |
| * * * * *
* |
1.3x
+-+...*...*............................*...*...........................*...*....................................+-+
| * * * * *
* |
| * * * * *
* ***** |
1.25x
+-+...*...*...........*****............*...*...........................*...*............*****...*...*...........+-+
| * * * * * * *
* *+++* * * |
1.2x
+-+...*...*...........*...*............*...*...........................*...*............*...*...*...*...........+-+
| * * * * * * *
* * * * * |
| * * * * * * *
* * * * * ***** |
1.15x
+-+...*...*...........*...*............*...*...........................*...*............*...*...*...*...*...*...+-+
| * * * * * * *
* +++ * * * * * * |
| * * * * * * *
* ***** * * * * * * |
1.1x
+-+...*...*...........*...*....*****...*...*...*****...................*...*...*...*....*...*...*...*...*...*...+-+
| * * * * * * * * * * *
* * * * * * * * * |
1.05x
+-+...*...*...........*...*....*...*...*...*...*...*...................*...*...*...*....*...*...*...*...*...*...+-+
| * * ***** * * * * * * * * *
* * * * * * * * * |
| * * * * * * * * * * * * ***** ***** *
* * * * * * * * * |
1x
+-+---*****---*****---*****----*****---*****---*****---*****---*****---*****---*****----*****---*****---*****---+-+
astar bzip2 gcc gobmk h264ref hmmlibquantum mcf
omnetpperlbench sjenxalancbmk hmean
png: http://imgur.com/en9HE8L
Tested-by: Emilio G. Cota <address@hidden>
Reviewed-by: Aurelien Jarno <address@hidden>
Signed-off-by: Richard Henderson <address@hidden>
---
tcg/aarch64/tcg-target.h | 2 +-
tcg/aarch64/tcg-target.inc.c | 22 ++++++++++++++++++++--
2 files changed, 21 insertions(+), 3 deletions(-)
diff --git a/tcg/aarch64/tcg-target.h b/tcg/aarch64/tcg-target.h
index b82eac4..55a46ac 100644
--- a/tcg/aarch64/tcg-target.h
+++ b/tcg/aarch64/tcg-target.h
@@ -77,7 +77,7 @@ typedef enum {
#define TCG_TARGET_HAS_mulsh_i32 0
#define TCG_TARGET_HAS_extrl_i64_i32 0
#define TCG_TARGET_HAS_extrh_i64_i32 0
-#define TCG_TARGET_HAS_goto_ptr 0
+#define TCG_TARGET_HAS_goto_ptr 1
#define TCG_TARGET_HAS_div_i64 1
#define TCG_TARGET_HAS_rem_i64 1
diff --git a/tcg/aarch64/tcg-target.inc.c b/tcg/aarch64/tcg-target.inc.c
index 290de6d..5f18545 100644
--- a/tcg/aarch64/tcg-target.inc.c
+++ b/tcg/aarch64/tcg-target.inc.c
@@ -1357,8 +1357,13 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
switch (opc) {
case INDEX_op_exit_tb:
- tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
- tcg_out_goto(s, tb_ret_addr);
+ /* Reuse the zeroing that exists for goto_ptr. */
+ if (a0 == 0) {
+ tcg_out_goto(s, s->code_gen_epilogue);
+ } else {
+ tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_X0, a0);
+ tcg_out_goto(s, tb_ret_addr);
+ }
break;
case INDEX_op_goto_tb:
@@ -1374,6 +1379,10 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
s->tb_jmp_reset_offset[a0] = tcg_current_code_size(s);
break;
+ case INDEX_op_goto_ptr:
+ tcg_out_insn(s, 3207, BR, a0);
+ break;
+
case INDEX_op_br:
tcg_out_goto_label(s, arg_label(a0));
break;
@@ -1735,6 +1744,7 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
{ INDEX_op_exit_tb, { } },
{ INDEX_op_goto_tb, { } },
{ INDEX_op_br, { } },
+ { INDEX_op_goto_ptr, { "r" } },
{ INDEX_op_ld8u_i32, { "r", "r" } },
{ INDEX_op_ld8s_i32, { "r", "r" } },
@@ -1942,6 +1952,14 @@ static void tcg_target_qemu_prologue(TCGContext *s)
tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
tcg_out_insn(s, 3207, BR, tcg_target_call_iarg_regs[1]);
+ /*
+ * Return path for goto_ptr. Set return value to 0, a-la exit_tb,
+ * and fall through to the rest of the epilogue.
+ */
+ s->code_gen_epilogue = s->code_ptr;
+ tcg_out_movi(s, TCG_TYPE_REG, TCG_REG_X0, 0);
+
+ /* TB epilogue */
tb_ret_addr = s->code_ptr;
/* Remove TCG locals stack space. */
--
2.9.4
- [Qemu-devel] [PULL 03/26] qemu/atomic: Loosen restrictions for 64-bit ILP32 hosts, (continued)
- [Qemu-devel] [PULL 03/26] qemu/atomic: Loosen restrictions for 64-bit ILP32 hosts, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 04/26] tcg: Introduce goto_ptr opcode and tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 06/26] target/arm: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 05/26] tcg/i386: implement goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 08/26] target/i386: introduce gen_jr helper to generate lookup_and_goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 09/26] target/i386: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 07/26] target/arm: optimize indirect branches, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 10/26] target/i386: optimize indirect branches, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 12/26] tcg/ppc: Implement goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 14/26] tcg/sparc: Implement goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 13/26] tcg/aarch64: Implement goto_ptr,
Richard Henderson <=
- [Qemu-devel] [PULL 11/26] tb-hash: improve tb_jmp_cache hash function in user mode, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 15/26] tcg/s390: Implement goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 17/26] tcg/arm: Implement goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 20/26] target/hppa: Use tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 21/26] target/aarch64: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 16/26] tcg/arm: Clarify tcg_out_bx for arm4 host, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 19/26] target/s390: Use tcg_gen_lookup_and_goto_ptr, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 23/26] target/mips: optimize cross-page direct jumps in softmmu, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 24/26] target/mips: optimize indirect branches, Richard Henderson, 2017/06/05
- [Qemu-devel] [PULL 22/26] target/aarch64: optimize indirect branches, Richard Henderson, 2017/06/05