rpms/qemu
3
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
d9f9605999
qemu/0064-tcg-mips-optimize-bswap-16-16s-32-on-MIPS32R2.patch
Cole Robinson 5544c1b492 Pull patches queued for qemu 1.2.1
2012-10-28 14:05:07 -04:00

162 lines
5.7 KiB
Diff
Raw Blame History

From 879794c3d3974b1206bbc52011c8f2525709f396 Mon Sep 17 00:00:00 2001
From: Aurelien Jarno <aurelien@aurel32.net>
Date: Fri, 21 Sep 2012 18:20:26 +0200
Subject: [PATCH] tcg/mips: optimize bswap{16,16s,32} on MIPS32R2
bswap operations can be optimized on MIPS32 Release 2 using the ROTR,
WSBH and SEH instructions. We can't use the non-R2 code to implement the
ops due to registers constraints, so don't define the corresponding
TCG_TARGET_HAS_bswap* values.
Also bswap16* operations are supposed to be called with the 16 high bits
zeroed. This is the case everywhere (including for TCG by definition)
except when called from the store helper. Remove the AND instructions from
bswap16* and move it there.
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
tcg/mips/tcg-target.c | 34 +++++++++++++++++++++++++++++-----
tcg/mips/tcg-target.h | 11 +++++++++--
2 files changed, 38 insertions(+), 7 deletions(-)
diff --git a/tcg/mips/tcg-target.c b/tcg/mips/tcg-target.c
index 6aa4527..8b2f9fc 100644
--- a/tcg/mips/tcg-target.c
+++ b/tcg/mips/tcg-target.c
@@ -326,6 +326,7 @@ enum {
OPC_BGEZ = OPC_REGIMM | (0x01 << 16),
OPC_SPECIAL3 = 0x1f << 26,
+ OPC_WSBH = OPC_SPECIAL3 | 0x0a0,
OPC_SEB = OPC_SPECIAL3 | 0x420,
OPC_SEH = OPC_SPECIAL3 | 0x620,
};
@@ -419,36 +420,45 @@ static inline void tcg_out_movi(TCGContext *s, TCGType type,
static inline void tcg_out_bswap16(TCGContext *s, TCGReg ret, TCGReg arg)
{
+#ifdef _MIPS_ARCH_MIPS32R2
+ tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
+#else
/* ret and arg can't be register at */
if (ret == TCG_REG_AT || arg == TCG_REG_AT) {
tcg_abort();
}
tcg_out_opc_sa(s, OPC_SRL, TCG_REG_AT, arg, 8);
- tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_AT, TCG_REG_AT, 0x00ff);
-
tcg_out_opc_sa(s, OPC_SLL, ret, arg, 8);
tcg_out_opc_imm(s, OPC_ANDI, ret, ret, 0xff00);
tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_REG_AT);
+#endif
}
static inline void tcg_out_bswap16s(TCGContext *s, TCGReg ret, TCGReg arg)
{
+#ifdef _MIPS_ARCH_MIPS32R2
+ tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
+ tcg_out_opc_reg(s, OPC_SEH, ret, 0, ret);
+#else
/* ret and arg can't be register at */
if (ret == TCG_REG_AT || arg == TCG_REG_AT) {
tcg_abort();
}
tcg_out_opc_sa(s, OPC_SRL, TCG_REG_AT, arg, 8);
- tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_AT, TCG_REG_AT, 0xff);
-
tcg_out_opc_sa(s, OPC_SLL, ret, arg, 24);
tcg_out_opc_sa(s, OPC_SRA, ret, ret, 16);
tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_REG_AT);
+#endif
}
static inline void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg)
{
+#ifdef _MIPS_ARCH_MIPS32R2
+ tcg_out_opc_reg(s, OPC_WSBH, ret, 0, arg);
+ tcg_out_opc_sa(s, OPC_ROTR, ret, ret, 16);
+#else
/* ret and arg must be different and can't be register at */
if (ret == arg || ret == TCG_REG_AT || arg == TCG_REG_AT) {
tcg_abort();
@@ -466,6 +476,7 @@ static inline void tcg_out_bswap32(TCGContext *s, TCGReg ret, TCGReg arg)
tcg_out_opc_sa(s, OPC_SRL, TCG_REG_AT, arg, 8);
tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_AT, TCG_REG_AT, 0xff00);
tcg_out_opc_reg(s, OPC_OR, ret, ret, TCG_REG_AT);
+#endif
}
static inline void tcg_out_ext8s(TCGContext *s, TCGReg ret, TCGReg arg)
@@ -1188,7 +1199,8 @@ static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args,
break;
case 1:
if (TCG_NEED_BSWAP) {
- tcg_out_bswap16(s, TCG_REG_T0, data_reg1);
+ tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_T0, data_reg1, 0xffff);
+ tcg_out_bswap16(s, TCG_REG_T0, TCG_REG_T0);
tcg_out_opc_imm(s, OPC_SH, TCG_REG_T0, TCG_REG_A0, 0);
} else {
tcg_out_opc_imm(s, OPC_SH, data_reg1, TCG_REG_A0, 0);
@@ -1409,6 +1421,15 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
}
break;
+ /* The bswap routines do not work on non-R2 CPU. In that case
+ we let TCG generating the corresponding code. */
+ case INDEX_op_bswap16_i32:
+ tcg_out_bswap16(s, args[0], args[1]);
+ break;
+ case INDEX_op_bswap32_i32:
+ tcg_out_bswap32(s, args[0], args[1]);
+ break;
+
case INDEX_op_ext8s_i32:
tcg_out_ext8s(s, args[0], args[1]);
break;
@@ -1503,6 +1524,9 @@ static const TCGTargetOpDef mips_op_defs[] = {
{ INDEX_op_shr_i32, { "r", "rZ", "ri" } },
{ INDEX_op_sar_i32, { "r", "rZ", "ri" } },
+ { INDEX_op_bswap16_i32, { "r", "r" } },
+ { INDEX_op_bswap32_i32, { "r", "r" } },
+
{ INDEX_op_ext8s_i32, { "r", "rZ" } },
{ INDEX_op_ext16s_i32, { "r", "rZ" } },
diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h
index 9c68a32..c5c13f7 100644
--- a/tcg/mips/tcg-target.h
+++ b/tcg/mips/tcg-target.h
@@ -83,8 +83,6 @@ typedef enum {
#define TCG_TARGET_HAS_rot_i32 0
#define TCG_TARGET_HAS_ext8s_i32 1
#define TCG_TARGET_HAS_ext16s_i32 1
-#define TCG_TARGET_HAS_bswap32_i32 0
-#define TCG_TARGET_HAS_bswap16_i32 0
#define TCG_TARGET_HAS_andc_i32 0
#define TCG_TARGET_HAS_orc_i32 0
#define TCG_TARGET_HAS_eqv_i32 0
@@ -92,6 +90,15 @@ typedef enum {
#define TCG_TARGET_HAS_deposit_i32 0
#define TCG_TARGET_HAS_movcond_i32 0
+/* optional instructions only implemented on MIPS32R2 */
+#ifdef _MIPS_ARCH_MIPS32R2
+#define TCG_TARGET_HAS_bswap16_i32 1
+#define TCG_TARGET_HAS_bswap32_i32 1
+#else
+#define TCG_TARGET_HAS_bswap16_i32 0
+#define TCG_TARGET_HAS_bswap32_i32 0
+#endif
+
/* optional instructions automatically implemented */
#define TCG_TARGET_HAS_neg_i32 0 /* sub rd, zero, rt */
#define TCG_TARGET_HAS_ext8u_i32 0 /* andi rt, rs, 0xff */
--
1.7.12.1
Reference in New Issue View Git Blame Copy Permalink