[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[Qemu-devel] [PATCH v3 11/29] tcg-aarch64: Handle constant operands to a
From: |
Richard Henderson |
Subject: |
[Qemu-devel] [PATCH v3 11/29] tcg-aarch64: Handle constant operands to and, or, xor |
Date: |
Mon, 2 Sep 2013 10:54:45 -0700 |
Handle a simplified set of logical immediates for the moment.
The way gcc and binutils do it, with 52k worth of tables, and
a binary search depth of log2(5334) = 13, seems slow for the
most common cases.
Signed-off-by: Richard Henderson <address@hidden>
---
tcg/aarch64/tcg-target.c | 148 +++++++++++++++++++++++++++++++----------------
1 file changed, 99 insertions(+), 49 deletions(-)
diff --git a/tcg/aarch64/tcg-target.c b/tcg/aarch64/tcg-target.c
index dbb1c45..9324185 100644
--- a/tcg/aarch64/tcg-target.c
+++ b/tcg/aarch64/tcg-target.c
@@ -108,6 +108,7 @@ static inline void patch_reloc(uint8_t *code_ptr, int type,
#define TCG_CT_CONST_IS32 0x100
#define TCG_CT_CONST_AIMM 0x200
+#define TCG_CT_CONST_LIMM 0x400
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct,
@@ -138,6 +139,9 @@ static int target_parse_constraint(TCGArgConstraint *ct,
case 'A': /* Valid for arithmetic immediate (positive or negative). */
ct->ct |= TCG_CT_CONST_AIMM;
break;
+ case 'L': /* Valid for logical immediate. */
+ ct->ct |= TCG_CT_CONST_LIMM;
+ break;
default:
return -1;
}
@@ -152,6 +156,26 @@ static inline bool is_aimm(uint64_t val)
return (val & ~0xfff) == 0 || (val & ~0xfff000) == 0;
}
+static inline bool is_limm(uint64_t val)
+{
+ /* Taking a simplified view of the logical immediates for now, ignoring
+ the replication that can happen across the field. Match bit patterns
+ of the forms
+ 0....01....1
+ 0..01..10..0
+ and their inverses. */
+
+ /* Make things easier below, by testing the form with msb clear. */
+ if ((int64_t)val < 0) {
+ val = ~val;
+ }
+ if (val == 0) {
+ return false;
+ }
+ val += val & -val;
+ return (val & (val - 1)) == 0;
+}
+
static int tcg_target_const_match(tcg_target_long val,
const TCGArgConstraint *arg_ct)
{
@@ -166,6 +190,9 @@ static int tcg_target_const_match(tcg_target_long val,
if ((ct & TCG_CT_CONST_AIMM) && (is_aimm(val) || is_aimm(-val))) {
return 1;
}
+ if ((ct & TCG_CT_CONST_LIMM) && is_limm(val)) {
+ return 1;
+ }
return 0;
}
@@ -220,6 +247,11 @@ enum aarch64_ldst_op_type { /* type of operation */
};
typedef enum {
+ /* Logical immediate instructions */
+ INSN_ANDI = 0x12000000,
+ INSN_ORRI = 0x32000000,
+ INSN_EORI = 0x52000000,
+
/* Logical shifted register instructions */
INSN_AND = 0x0a000000,
INSN_ORR = 0x2a000000,
@@ -359,6 +391,41 @@ static inline void tcg_fmt_Rdn_aimm(TCGContext *s,
AArch64Insn insn, bool ext,
tcg_out32(s, insn | ext << 31 | aimm << 10 | rn << 5 | rd);
}
+static inline void tcg_fmt_Rdn_r_s(TCGContext *s, AArch64Insn insn, bool ext,
+ TCGReg rd, TCGReg rn, int r, int m)
+{
+ tcg_out32(s, insn | ext * 0x80400000 | r << 16 | m << 10 | rn << 5 | rd);
+}
+
+static void tcg_fmt_Rdn_limm(TCGContext *s, AArch64Insn insn, bool ext,
+ TCGReg rd, TCGReg rn, uint64_t limm)
+{
+ unsigned h, l, r, c;
+
+ /* See is_limm comment about simplified logical immediates. */
+ assert(is_limm(limm));
+
+ h = clz64(limm);
+ l = ctz64(limm);
+ if (l == 0) {
+ r = 0; /* form 0....01....1 */
+ c = ctz64(~limm) - 1;
+ if (h == 0) {
+ r = clz64(~limm); /* form 1..10..01..1 */
+ c += r;
+ }
+ } else {
+ r = 64 - l; /* form 1....10....0 or 0..01..10..0 */
+ c = r - h - 1;
+ }
+ if (!ext) {
+ r &= 31;
+ c &= 31;
+ }
+
+ tcg_fmt_Rdn_r_s(s, insn, ext, rd, rn, r, c);
+}
+
static inline void tcg_out_ldst_9(TCGContext *s,
enum aarch64_ldst_op_data op_data,
enum aarch64_ldst_op_type op_type,
@@ -665,40 +732,6 @@ static inline void tcg_out_call(TCGContext *s,
tcg_target_long target)
}
}
-/* encode a logical immediate, mapping user parameter
- M=set bits pattern length to S=M-1 */
-static inline unsigned int
-aarch64_limm(unsigned int m, unsigned int r)
-{
- assert(m > 0);
- return r << 16 | (m - 1) << 10;
-}
-
-/* test a register against an immediate bit pattern made of
- M set bits rotated right by R.
- Examples:
- to test a 32/64 reg against 0x00000007, pass M = 3, R = 0.
- to test a 32/64 reg against 0x000000ff, pass M = 8, R = 0.
- to test a 32bit reg against 0xff000000, pass M = 8, R = 8.
- to test a 32bit reg against 0xff0000ff, pass M = 16, R = 8.
- */
-static inline void tcg_out_tst(TCGContext *s, bool ext, TCGReg rn,
- unsigned int m, unsigned int r)
-{
- /* using TST alias of ANDS XZR, Xn,#bimm64 0x7200001f */
- unsigned int base = ext ? 0xf240001f : 0x7200001f;
- tcg_out32(s, base | aarch64_limm(m, r) | rn << 5);
-}
-
-/* and a register with a bit pattern, similarly to TST, no flags change */
-static inline void tcg_out_andi(TCGContext *s, bool ext, TCGReg rd, TCGReg rn,
- unsigned int m, unsigned int r)
-{
- /* using AND 0x12000000 */
- unsigned int base = ext ? 0x92400000 : 0x12000000;
- tcg_out32(s, base | aarch64_limm(m, r) | rn << 5 | rd);
-}
-
static inline void tcg_out_ret(TCGContext *s)
{
/* emit RET { LR } */
@@ -901,9 +934,8 @@ static void tcg_out_tlb_read(TCGContext *s, TCGReg addr_reg,
/* Store the page mask part of the address and the low s_bits into X3.
Later this allows checking for equality and alignment at the same time.
X3 = addr_reg & (PAGE_MASK | ((1 << s_bits) - 1)) */
- tcg_out_andi(s, (TARGET_LONG_BITS == 64), TCG_REG_X3, addr_reg,
- (TARGET_LONG_BITS - TARGET_PAGE_BITS) + s_bits,
- (TARGET_LONG_BITS - TARGET_PAGE_BITS));
+ tcg_fmt_Rdn_limm(s, INSN_ANDI, TARGET_LONG_BITS == 64, TCG_REG_X3,
+ addr_reg, TARGET_PAGE_MASK | ((1 << s_bits) - 1));
/* Add any "high bits" from the tlb offset to the env address into X2,
to take advantage of the LSL12 form of the ADDI instruction.
X2 = env + (tlb_offset & 0xfff000) */
@@ -1207,19 +1239,37 @@ static void tcg_out_op(TCGContext *s, TCGOpcode opc,
}
break;
- case INDEX_op_and_i64:
case INDEX_op_and_i32:
- tcg_fmt_Rdnm(s, INSN_AND, ext, a0, a1, a2);
+ a2 = (int32_t)a2;
+ /* FALLTHRU */
+ case INDEX_op_and_i64:
+ if (c2) {
+ tcg_fmt_Rdn_limm(s, INSN_ANDI, ext, a0, a1, a2);
+ } else {
+ tcg_fmt_Rdnm(s, INSN_AND, ext, a0, a1, a2);
+ }
break;
- case INDEX_op_or_i64:
case INDEX_op_or_i32:
- tcg_fmt_Rdnm(s, INSN_ORR, ext, a0, a1, a2);
+ a2 = (int32_t)a2;
+ /* FALLTHRU */
+ case INDEX_op_or_i64:
+ if (c2) {
+ tcg_fmt_Rdn_limm(s, INSN_ORRI, ext, a0, a1, a2);
+ } else {
+ tcg_fmt_Rdnm(s, INSN_ORR, ext, a0, a1, a2);
+ }
break;
- case INDEX_op_xor_i64:
case INDEX_op_xor_i32:
- tcg_fmt_Rdnm(s, INSN_EOR, ext, a0, a1, a2);
+ a2 = (int32_t)a2;
+ /* FALLTHRU */
+ case INDEX_op_xor_i64:
+ if (c2) {
+ tcg_fmt_Rdn_limm(s, INSN_EORI, ext, a0, a1, a2);
+ } else {
+ tcg_fmt_Rdnm(s, INSN_EOR, ext, a0, a1, a2);
+ }
break;
case INDEX_op_mul_i64:
@@ -1412,12 +1462,12 @@ static const TCGTargetOpDef aarch64_op_defs[] = {
{ INDEX_op_sub_i64, { "r", "r", "rA" } },
{ INDEX_op_mul_i32, { "r", "r", "r" } },
{ INDEX_op_mul_i64, { "r", "r", "r" } },
- { INDEX_op_and_i32, { "r", "r", "r" } },
- { INDEX_op_and_i64, { "r", "r", "r" } },
- { INDEX_op_or_i32, { "r", "r", "r" } },
- { INDEX_op_or_i64, { "r", "r", "r" } },
- { INDEX_op_xor_i32, { "r", "r", "r" } },
- { INDEX_op_xor_i64, { "r", "r", "r" } },
+ { INDEX_op_and_i32, { "r", "r", "rwL" } },
+ { INDEX_op_and_i64, { "r", "r", "rL" } },
+ { INDEX_op_or_i32, { "r", "r", "rwL" } },
+ { INDEX_op_or_i64, { "r", "r", "rL" } },
+ { INDEX_op_xor_i32, { "r", "r", "rwL" } },
+ { INDEX_op_xor_i64, { "r", "r", "rL" } },
{ INDEX_op_shl_i32, { "r", "r", "ri" } },
{ INDEX_op_shr_i32, { "r", "r", "ri" } },
--
1.8.3.1
- [Qemu-devel] [PATCH v3 04/29] tcg-aarch64: Hoist common argument loads in tcg_out_op, (continued)
- [Qemu-devel] [PATCH v3 07/29] tcg-aarch64: Introduce tcg_fmt_* functions, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 06/29] tcg-aarch64: Merge enum aarch64_srr_opc with AArch64Insn, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 08/29] tcg-aarch64: Introduce tcg_fmt_Rdn_aimm, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 09/29] tcg-aarch64: Implement mov with tcg_fmt_* functions, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 10/29] tcg-aarch64: Handle constant operands to add, sub, and compare, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 11/29] tcg-aarch64: Handle constant operands to and, or, xor,
Richard Henderson <=
- [Qemu-devel] [PATCH v3 13/29] tcg-aarch64: Handle zero as first argument to sub, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 12/29] tcg-aarch64: Support andc, orc, eqv, not, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 15/29] tcg-aarch64: Support deposit, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 14/29] tcg-aarch64: Support movcond, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 16/29] tcg-aarch64: Support add2, sub2, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 17/29] tcg-aarch64: Support muluh, mulsh, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 18/29] tcg-aarch64: Support div, rem, Richard Henderson, 2013/09/02
- [Qemu-devel] [PATCH v3 19/29] tcg-aarch64: Introduce tcg_fmt_Rd_uimm_s, Richard Henderson, 2013/09/02