Merge branch 'tcg-sparc' of git://repo.or.cz/qemu/rth
* 'tcg-sparc' of git://repo.or.cz/qemu/rth:
tcg-sparc: Preserve branch destinations during retranslation
tcg-sparc: Fix and enable direct TB chaining.
tcg-sparc: Add %g/%o registers to alloc_order
tcg-sparc: Use defines for temporaries.
tcg-sparc: Mask shift immediates to avoid illegal insns.
tcg-sparc: Clean up cruft stemming from attempts to use global registers.
tcg-sparc: Change AREG0 in generated code to %i0.
tcg-sparc: Support GUEST_BASE.
tcg-sparc: Fix qemu_ld/st to handle 32-bit host.
tcg-sparc: Assume v9 cpu always, i.e. force v8plus in 32-bit mode.
tcg-sparc: Don't MAP_FIXED on top of the program
tcg-sparc: Fix ADDX opcode.
tcg-sparc: Hack in qemu_ld/st64 for 32-bit.
linux-user: Use memcpy in get_user/put_user.
diff --git a/fpu/softfloat-specialize.h b/fpu/softfloat-specialize.h
index 4902450..a1d489e 100644
--- a/fpu/softfloat-specialize.h
+++ b/fpu/softfloat-specialize.h
@@ -41,6 +41,13 @@
#define SNAN_BIT_IS_ONE 0
#endif
+#if defined(TARGET_XTENSA)
+/* Define for architectures which deviate from IEEE in not supporting
+ * signaling NaNs (so all NaNs are treated as quiet).
+ */
+#define NO_SIGNALING_NANS 1
+#endif
+
/*----------------------------------------------------------------------------
| The pattern for a default generated half-precision NaN.
*----------------------------------------------------------------------------*/
@@ -57,7 +64,8 @@
*----------------------------------------------------------------------------*/
#if defined(TARGET_SPARC)
const float32 float32_default_nan = const_float32(0x7FFFFFFF);
-#elif defined(TARGET_PPC) || defined(TARGET_ARM) || defined(TARGET_ALPHA)
+#elif defined(TARGET_PPC) || defined(TARGET_ARM) || defined(TARGET_ALPHA) || \
+ defined(TARGET_XTENSA)
const float32 float32_default_nan = const_float32(0x7FC00000);
#elif SNAN_BIT_IS_ONE
const float32 float32_default_nan = const_float32(0x7FBFFFFF);
@@ -127,6 +135,17 @@
uint64_t high, low;
} commonNaNT;
+#ifdef NO_SIGNALING_NANS
+int float16_is_quiet_nan(float16 a_)
+{
+ return float16_is_any_nan(a_);
+}
+
+int float16_is_signaling_nan(float16 a_)
+{
+ return 0;
+}
+#else
/*----------------------------------------------------------------------------
| Returns 1 if the half-precision floating-point value `a' is a quiet
| NaN; otherwise returns 0.
@@ -156,6 +175,7 @@
return (((a >> 9) & 0x3F) == 0x3E) && (a & 0x1FF);
#endif
}
+#endif
/*----------------------------------------------------------------------------
| Returns a quiet NaN if the half-precision floating point value `a' is a
@@ -217,6 +237,17 @@
}
}
+#ifdef NO_SIGNALING_NANS
+int float32_is_quiet_nan(float32 a_)
+{
+ return float32_is_any_nan(a_);
+}
+
+int float32_is_signaling_nan(float32 a_)
+{
+ return 0;
+}
+#else
/*----------------------------------------------------------------------------
| Returns 1 if the single-precision floating-point value `a' is a quiet
| NaN; otherwise returns 0.
@@ -246,6 +277,7 @@
return ( ( ( a>>22 ) & 0x1FF ) == 0x1FE ) && ( a & 0x003FFFFF );
#endif
}
+#endif
/*----------------------------------------------------------------------------
| Returns a quiet NaN if the single-precision floating point value `a' is a
@@ -372,7 +404,7 @@
return 1;
}
}
-#elif defined(TARGET_PPC)
+#elif defined(TARGET_PPC) || defined(TARGET_XTENSA)
static int pickNaN(flag aIsQNaN, flag aIsSNaN, flag bIsQNaN, flag bIsSNaN,
flag aIsLargerSignificand)
{
@@ -586,6 +618,17 @@
}
}
+#ifdef NO_SIGNALING_NANS
+int float64_is_quiet_nan(float64 a_)
+{
+ return float64_is_any_nan(a_);
+}
+
+int float64_is_signaling_nan(float64 a_)
+{
+ return 0;
+}
+#else
/*----------------------------------------------------------------------------
| Returns 1 if the double-precision floating-point value `a' is a quiet
| NaN; otherwise returns 0.
@@ -619,6 +662,7 @@
&& ( a & LIT64( 0x0007FFFFFFFFFFFF ) );
#endif
}
+#endif
/*----------------------------------------------------------------------------
| Returns a quiet NaN if the double-precision floating point value `a' is a
@@ -773,6 +817,17 @@
}
}
+#ifdef NO_SIGNALING_NANS
+int floatx80_is_quiet_nan(floatx80 a_)
+{
+ return floatx80_is_any_nan(a_);
+}
+
+int floatx80_is_signaling_nan(floatx80 a_)
+{
+ return 0;
+}
+#else
/*----------------------------------------------------------------------------
| Returns 1 if the extended double-precision floating-point value `a' is a
| quiet NaN; otherwise returns 0. This slightly differs from the same
@@ -816,6 +871,7 @@
&& ( a.low == aLow );
#endif
}
+#endif
/*----------------------------------------------------------------------------
| Returns a quiet NaN if the extended double-precision floating point value
@@ -929,6 +985,17 @@
}
}
+#ifdef NO_SIGNALING_NANS
+int float128_is_quiet_nan(float128 a_)
+{
+ return float128_is_any_nan(a_);
+}
+
+int float128_is_signaling_nan(float128 a_)
+{
+ return 0;
+}
+#else
/*----------------------------------------------------------------------------
| Returns 1 if the quadruple-precision floating-point value `a' is a quiet
| NaN; otherwise returns 0.
@@ -964,6 +1031,7 @@
&& ( a.low || ( a.high & LIT64( 0x00007FFFFFFFFFFF ) ) );
#endif
}
+#endif
/*----------------------------------------------------------------------------
| Returns a quiet NaN if the quadruple-precision floating point value `a' is
diff --git a/fpu/softfloat.h b/fpu/softfloat.h
index feec3a1..d8999b3 100644
--- a/fpu/softfloat.h
+++ b/fpu/softfloat.h
@@ -219,7 +219,7 @@
enum {
float_muladd_negate_c = 1,
float_muladd_negate_product = 2,
- float_muladd_negate_result = 3,
+ float_muladd_negate_result = 4,
};
/*----------------------------------------------------------------------------
@@ -251,6 +251,11 @@
int float16_is_signaling_nan( float16 );
float16 float16_maybe_silence_nan( float16 );
+INLINE int float16_is_any_nan(float16 a)
+{
+ return ((float16_val(a) & ~0x8000) > 0x7c00);
+}
+
/*----------------------------------------------------------------------------
| The pattern for a default generated half-precision NaN.
*----------------------------------------------------------------------------*/
diff --git a/gdbstub.c b/gdbstub.c
index a91709f..d02ec75 100644
--- a/gdbstub.c
+++ b/gdbstub.c
@@ -1696,6 +1696,10 @@
GET_REG32(env->uregs[reg->targno & 0xff]);
break;
+ case 4: /*f*/
+ GET_REG32(float32_val(env->fregs[reg->targno & 0x0f]));
+ break;
+
case 8: /*a*/
GET_REG32(env->regs[reg->targno & 0x0f]);
break;
@@ -1736,6 +1740,10 @@
env->uregs[reg->targno & 0xff] = tmp;
break;
+ case 4: /*f*/
+ env->fregs[reg->targno & 0x0f] = make_float32(tmp);
+ break;
+
case 8: /*a*/
env->regs[reg->targno & 0x0f] = tmp;
break;
diff --git a/target-xtensa/cpu.h b/target-xtensa/cpu.h
index 177094a..7348277 100644
--- a/target-xtensa/cpu.h
+++ b/target-xtensa/cpu.h
@@ -36,6 +36,7 @@
#include "config.h"
#include "qemu-common.h"
#include "cpu-defs.h"
+#include "fpu/softfloat.h"
#define TARGET_HAS_ICE 1
@@ -325,6 +326,8 @@
uint32_t sregs[256];
uint32_t uregs[256];
uint32_t phys_regs[MAX_NAREG];
+ float32 fregs[16];
+ float_status fp_status;
xtensa_tlb_entry itlb[7][MAX_TLB_WAY_SIZE];
xtensa_tlb_entry dtlb[10][MAX_TLB_WAY_SIZE];
@@ -465,6 +468,8 @@
#define XTENSA_TBFLAG_LITBASE 0x8
#define XTENSA_TBFLAG_DEBUG 0x10
#define XTENSA_TBFLAG_ICOUNT 0x20
+#define XTENSA_TBFLAG_CPENABLE_MASK 0x3fc0
+#define XTENSA_TBFLAG_CPENABLE_SHIFT 6
static inline void cpu_get_tb_cpu_state(CPUXtensaState *env, target_ulong *pc,
target_ulong *cs_base, int *flags)
@@ -488,6 +493,9 @@
*flags |= XTENSA_TBFLAG_ICOUNT;
}
}
+ if (xtensa_option_enabled(env->config, XTENSA_OPTION_COPROCESSOR)) {
+ *flags |= env->sregs[CPENABLE] << XTENSA_TBFLAG_CPENABLE_SHIFT;
+ }
}
#include "cpu-all.h"
diff --git a/target-xtensa/helper.h b/target-xtensa/helper.h
index 152fec0..4cc0088 100644
--- a/target-xtensa/helper.h
+++ b/target-xtensa/helper.h
@@ -36,4 +36,25 @@
DEF_HELPER_3(wsr_dbreaka, void, env, i32, i32)
DEF_HELPER_3(wsr_dbreakc, void, env, i32, i32)
+DEF_HELPER_2(wur_fcr, void, env, i32)
+DEF_HELPER_FLAGS_1(abs_s, TCG_CALL_CONST | TCG_CALL_PURE, f32, f32)
+DEF_HELPER_FLAGS_1(neg_s, TCG_CALL_CONST | TCG_CALL_PURE, f32, f32)
+DEF_HELPER_3(add_s, f32, env, f32, f32)
+DEF_HELPER_3(sub_s, f32, env, f32, f32)
+DEF_HELPER_3(mul_s, f32, env, f32, f32)
+DEF_HELPER_4(madd_s, f32, env, f32, f32, f32)
+DEF_HELPER_4(msub_s, f32, env, f32, f32, f32)
+DEF_HELPER_FLAGS_3(ftoi, TCG_CALL_CONST | TCG_CALL_PURE, i32, f32, i32, i32)
+DEF_HELPER_FLAGS_3(ftoui, TCG_CALL_CONST | TCG_CALL_PURE, i32, f32, i32, i32)
+DEF_HELPER_3(itof, f32, env, i32, i32)
+DEF_HELPER_3(uitof, f32, env, i32, i32)
+
+DEF_HELPER_4(un_s, void, env, i32, f32, f32)
+DEF_HELPER_4(oeq_s, void, env, i32, f32, f32)
+DEF_HELPER_4(ueq_s, void, env, i32, f32, f32)
+DEF_HELPER_4(olt_s, void, env, i32, f32, f32)
+DEF_HELPER_4(ult_s, void, env, i32, f32, f32)
+DEF_HELPER_4(ole_s, void, env, i32, f32, f32)
+DEF_HELPER_4(ule_s, void, env, i32, f32, f32)
+
#include "def-helper.h"
diff --git a/target-xtensa/op_helper.c b/target-xtensa/op_helper.c
index 2659c0e..ae0c099 100644
--- a/target-xtensa/op_helper.c
+++ b/target-xtensa/op_helper.c
@@ -771,3 +771,137 @@
}
env->sregs[DBREAKC + i] = v;
}
+
+void HELPER(wur_fcr)(CPUXtensaState *env, uint32_t v)
+{
+ static const int rounding_mode[] = {
+ float_round_nearest_even,
+ float_round_to_zero,
+ float_round_up,
+ float_round_down,
+ };
+
+ env->uregs[FCR] = v & 0xfffff07f;
+ set_float_rounding_mode(rounding_mode[v & 3], &env->fp_status);
+}
+
+float32 HELPER(abs_s)(float32 v)
+{
+ return float32_abs(v);
+}
+
+float32 HELPER(neg_s)(float32 v)
+{
+ return float32_chs(v);
+}
+
+float32 HELPER(add_s)(CPUXtensaState *env, float32 a, float32 b)
+{
+ return float32_add(a, b, &env->fp_status);
+}
+
+float32 HELPER(sub_s)(CPUXtensaState *env, float32 a, float32 b)
+{
+ return float32_sub(a, b, &env->fp_status);
+}
+
+float32 HELPER(mul_s)(CPUXtensaState *env, float32 a, float32 b)
+{
+ return float32_mul(a, b, &env->fp_status);
+}
+
+float32 HELPER(madd_s)(CPUXtensaState *env, float32 a, float32 b, float32 c)
+{
+ return float32_muladd(b, c, a, 0,
+ &env->fp_status);
+}
+
+float32 HELPER(msub_s)(CPUXtensaState *env, float32 a, float32 b, float32 c)
+{
+ return float32_muladd(b, c, a, float_muladd_negate_product,
+ &env->fp_status);
+}
+
+uint32_t HELPER(ftoi)(float32 v, uint32_t rounding_mode, uint32_t scale)
+{
+ float_status fp_status = {0};
+
+ set_float_rounding_mode(rounding_mode, &fp_status);
+ return float32_to_int32(
+ float32_scalbn(v, scale, &fp_status), &fp_status);
+}
+
+uint32_t HELPER(ftoui)(float32 v, uint32_t rounding_mode, uint32_t scale)
+{
+ float_status fp_status = {0};
+ float32 res;
+
+ set_float_rounding_mode(rounding_mode, &fp_status);
+
+ res = float32_scalbn(v, scale, &fp_status);
+
+ if (float32_is_neg(v) && !float32_is_any_nan(v)) {
+ return float32_to_int32(res, &fp_status);
+ } else {
+ return float32_to_uint32(res, &fp_status);
+ }
+}
+
+float32 HELPER(itof)(CPUXtensaState *env, uint32_t v, uint32_t scale)
+{
+ return float32_scalbn(int32_to_float32(v, &env->fp_status),
+ (int32_t)scale, &env->fp_status);
+}
+
+float32 HELPER(uitof)(CPUXtensaState *env, uint32_t v, uint32_t scale)
+{
+ return float32_scalbn(uint32_to_float32(v, &env->fp_status),
+ (int32_t)scale, &env->fp_status);
+}
+
+static inline void set_br(CPUXtensaState *env, bool v, uint32_t br)
+{
+ if (v) {
+ env->sregs[BR] |= br;
+ } else {
+ env->sregs[BR] &= ~br;
+ }
+}
+
+void HELPER(un_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ set_br(env, float32_unordered_quiet(a, b, &env->fp_status), br);
+}
+
+void HELPER(oeq_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ set_br(env, float32_eq_quiet(a, b, &env->fp_status), br);
+}
+
+void HELPER(ueq_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ int v = float32_compare_quiet(a, b, &env->fp_status);
+ set_br(env, v == float_relation_equal || v == float_relation_unordered, br);
+}
+
+void HELPER(olt_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ set_br(env, float32_lt_quiet(a, b, &env->fp_status), br);
+}
+
+void HELPER(ult_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ int v = float32_compare_quiet(a, b, &env->fp_status);
+ set_br(env, v == float_relation_less || v == float_relation_unordered, br);
+}
+
+void HELPER(ole_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ set_br(env, float32_le_quiet(a, b, &env->fp_status), br);
+}
+
+void HELPER(ule_s)(CPUXtensaState *env, uint32_t br, float32 a, float32 b)
+{
+ int v = float32_compare_quiet(a, b, &env->fp_status);
+ set_br(env, v != float_relation_greater, br);
+}
diff --git a/target-xtensa/overlay_tool.h b/target-xtensa/overlay_tool.h
index a3a5650..e395053 100644
--- a/target-xtensa/overlay_tool.h
+++ b/target-xtensa/overlay_tool.h
@@ -58,6 +58,7 @@
XCHAL_OPTION(XCHAL_HAVE_SEXT, XTENSA_OPTION_MISC_OP_SEXT) | \
XCHAL_OPTION(XCHAL_HAVE_CLAMPS, XTENSA_OPTION_MISC_OP_CLAMPS) | \
XCHAL_OPTION(XCHAL_HAVE_CP, XTENSA_OPTION_COPROCESSOR) | \
+ XCHAL_OPTION(XCHAL_HAVE_BOOLEANS, XTENSA_OPTION_BOOLEAN) | \
XCHAL_OPTION(XCHAL_HAVE_FP, XTENSA_OPTION_FP_COPROCESSOR) | \
XCHAL_OPTION(XCHAL_HAVE_RELEASE_SYNC, XTENSA_OPTION_MP_SYNCHRO) | \
XCHAL_OPTION(XCHAL_HAVE_S32C1I, XTENSA_OPTION_CONDITIONAL_STORE) | \
diff --git a/target-xtensa/translate.c b/target-xtensa/translate.c
index b6643eb..ba3ffcb 100644
--- a/target-xtensa/translate.c
+++ b/target-xtensa/translate.c
@@ -65,11 +65,14 @@
bool debug;
bool icount;
TCGv_i32 next_icount;
+
+ unsigned cpenable;
} DisasContext;
static TCGv_ptr cpu_env;
static TCGv_i32 cpu_pc;
static TCGv_i32 cpu_R[16];
+static TCGv_i32 cpu_FR[16];
static TCGv_i32 cpu_SR[256];
static TCGv_i32 cpu_UR[256];
@@ -155,6 +158,12 @@
"ar8", "ar9", "ar10", "ar11",
"ar12", "ar13", "ar14", "ar15",
};
+ static const char * const fregnames[] = {
+ "f0", "f1", "f2", "f3",
+ "f4", "f5", "f6", "f7",
+ "f8", "f9", "f10", "f11",
+ "f12", "f13", "f14", "f15",
+ };
int i;
cpu_env = tcg_global_reg_new_ptr(TCG_AREG0, "env");
@@ -167,6 +176,12 @@
regnames[i]);
}
+ for (i = 0; i < 16; i++) {
+ cpu_FR[i] = tcg_global_mem_new_i32(TCG_AREG0,
+ offsetof(CPUXtensaState, fregs[i]),
+ fregnames[i]);
+ }
+
for (i = 0; i < 256; ++i) {
if (sregnames[i]) {
cpu_SR[i] = tcg_global_mem_new_i32(TCG_AREG0,
@@ -318,6 +333,15 @@
}
}
+static void gen_check_cpenable(DisasContext *dc, unsigned cp)
+{
+ if (option_enabled(dc, XTENSA_OPTION_COPROCESSOR) &&
+ !(dc->cpenable & (1 << cp))) {
+ gen_exception_cause(dc, COPROCESSOR0_DISABLED + cp);
+ dc->is_jmp = DISAS_UPDATE;
+ }
+}
+
static void gen_jump_slot(DisasContext *dc, TCGv dest, int slot)
{
tcg_gen_mov_i32(cpu_pc, dest);
@@ -566,6 +590,13 @@
}
}
+static void gen_wsr_cpenable(DisasContext *dc, uint32_t sr, TCGv_i32 v)
+{
+ tcg_gen_andi_i32(cpu_SR[sr], v, 0xff);
+ /* This can change tb->flags, so exit tb */
+ gen_jumpi_check_loop_end(dc, -1);
+}
+
static void gen_wsr_intset(DisasContext *dc, uint32_t sr, TCGv_i32 v)
{
tcg_gen_andi_i32(cpu_SR[sr], v,
@@ -668,6 +699,7 @@
[DBREAKA + 1] = gen_wsr_dbreaka,
[DBREAKC] = gen_wsr_dbreakc,
[DBREAKC + 1] = gen_wsr_dbreakc,
+ [CPENABLE] = gen_wsr_cpenable,
[INTSET] = gen_wsr_intset,
[INTCLEAR] = gen_wsr_intclear,
[INTENABLE] = gen_wsr_intenable,
@@ -692,6 +724,23 @@
}
}
+static void gen_wur(uint32_t ur, TCGv_i32 s)
+{
+ switch (ur) {
+ case FCR:
+ gen_helper_wur_fcr(cpu_env, s);
+ break;
+
+ case FSR:
+ tcg_gen_andi_i32(cpu_UR[ur], s, 0xffffff80);
+ break;
+
+ default:
+ tcg_gen_mov_i32(cpu_UR[ur], s);
+ break;
+ }
+}
+
static void gen_load_store_alignment(DisasContext *dc, int shift,
TCGv_i32 addr, bool no_hw_alignment)
{
@@ -1761,13 +1810,11 @@
case 15: /*WUR*/
gen_window_check1(dc, RRR_T);
- {
- if (uregnames[RSR_SR]) {
- tcg_gen_mov_i32(cpu_UR[RSR_SR], cpu_R[RRR_T]);
- } else {
- qemu_log("WUR %d not implemented, ", RSR_SR);
- TBD();
- }
+ if (uregnames[RSR_SR]) {
+ gen_wur(RSR_SR, cpu_R[RRR_T]);
+ } else {
+ qemu_log("WUR %d not implemented, ", RSR_SR);
+ TBD();
}
break;
@@ -1815,8 +1862,34 @@
break;
case 8: /*LSCXp*/
- HAS_OPTION(XTENSA_OPTION_COPROCESSOR);
- TBD();
+ switch (OP2) {
+ case 0: /*LSXf*/
+ case 1: /*LSXUf*/
+ case 4: /*SSXf*/
+ case 5: /*SSXUf*/
+ HAS_OPTION(XTENSA_OPTION_FP_COPROCESSOR);
+ gen_window_check2(dc, RRR_S, RRR_T);
+ gen_check_cpenable(dc, 0);
+ {
+ TCGv_i32 addr = tcg_temp_new_i32();
+ tcg_gen_add_i32(addr, cpu_R[RRR_S], cpu_R[RRR_T]);
+ gen_load_store_alignment(dc, 2, addr, false);
+ if (OP2 & 0x4) {
+ tcg_gen_qemu_st32(cpu_FR[RRR_R], addr, dc->cring);
+ } else {
+ tcg_gen_qemu_ld32u(cpu_FR[RRR_R], addr, dc->cring);
+ }
+ if (OP2 & 0x1) {
+ tcg_gen_mov_i32(cpu_R[RRR_S], addr);
+ }
+ tcg_temp_free(addr);
+ }
+ break;
+
+ default: /*reserved*/
+ RESERVED();
+ break;
+ }
break;
case 9: /*LSC4*/
@@ -1854,12 +1927,213 @@
case 10: /*FP0*/
HAS_OPTION(XTENSA_OPTION_FP_COPROCESSOR);
- TBD();
+ switch (OP2) {
+ case 0: /*ADD.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_add_s(cpu_FR[RRR_R], cpu_env,
+ cpu_FR[RRR_S], cpu_FR[RRR_T]);
+ break;
+
+ case 1: /*SUB.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_sub_s(cpu_FR[RRR_R], cpu_env,
+ cpu_FR[RRR_S], cpu_FR[RRR_T]);
+ break;
+
+ case 2: /*MUL.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_mul_s(cpu_FR[RRR_R], cpu_env,
+ cpu_FR[RRR_S], cpu_FR[RRR_T]);
+ break;
+
+ case 4: /*MADD.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_madd_s(cpu_FR[RRR_R], cpu_env,
+ cpu_FR[RRR_R], cpu_FR[RRR_S], cpu_FR[RRR_T]);
+ break;
+
+ case 5: /*MSUB.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_msub_s(cpu_FR[RRR_R], cpu_env,
+ cpu_FR[RRR_R], cpu_FR[RRR_S], cpu_FR[RRR_T]);
+ break;
+
+ case 8: /*ROUND.Sf*/
+ case 9: /*TRUNC.Sf*/
+ case 10: /*FLOOR.Sf*/
+ case 11: /*CEIL.Sf*/
+ case 14: /*UTRUNC.Sf*/
+ gen_window_check1(dc, RRR_R);
+ gen_check_cpenable(dc, 0);
+ {
+ static const unsigned rounding_mode_const[] = {
+ float_round_nearest_even,
+ float_round_to_zero,
+ float_round_down,
+ float_round_up,
+ [6] = float_round_to_zero,
+ };
+ TCGv_i32 rounding_mode = tcg_const_i32(
+ rounding_mode_const[OP2 & 7]);
+ TCGv_i32 scale = tcg_const_i32(RRR_T);
+
+ if (OP2 == 14) {
+ gen_helper_ftoui(cpu_R[RRR_R], cpu_FR[RRR_S],
+ rounding_mode, scale);
+ } else {
+ gen_helper_ftoi(cpu_R[RRR_R], cpu_FR[RRR_S],
+ rounding_mode, scale);
+ }
+
+ tcg_temp_free(rounding_mode);
+ tcg_temp_free(scale);
+ }
+ break;
+
+ case 12: /*FLOAT.Sf*/
+ case 13: /*UFLOAT.Sf*/
+ gen_window_check1(dc, RRR_S);
+ gen_check_cpenable(dc, 0);
+ {
+ TCGv_i32 scale = tcg_const_i32(-RRR_T);
+
+ if (OP2 == 13) {
+ gen_helper_uitof(cpu_FR[RRR_R], cpu_env,
+ cpu_R[RRR_S], scale);
+ } else {
+ gen_helper_itof(cpu_FR[RRR_R], cpu_env,
+ cpu_R[RRR_S], scale);
+ }
+ tcg_temp_free(scale);
+ }
+ break;
+
+ case 15: /*FP1OP*/
+ switch (RRR_T) {
+ case 0: /*MOV.Sf*/
+ gen_check_cpenable(dc, 0);
+ tcg_gen_mov_i32(cpu_FR[RRR_R], cpu_FR[RRR_S]);
+ break;
+
+ case 1: /*ABS.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_abs_s(cpu_FR[RRR_R], cpu_FR[RRR_S]);
+ break;
+
+ case 4: /*RFRf*/
+ gen_window_check1(dc, RRR_R);
+ gen_check_cpenable(dc, 0);
+ tcg_gen_mov_i32(cpu_R[RRR_R], cpu_FR[RRR_S]);
+ break;
+
+ case 5: /*WFRf*/
+ gen_window_check1(dc, RRR_S);
+ gen_check_cpenable(dc, 0);
+ tcg_gen_mov_i32(cpu_FR[RRR_R], cpu_R[RRR_S]);
+ break;
+
+ case 6: /*NEG.Sf*/
+ gen_check_cpenable(dc, 0);
+ gen_helper_neg_s(cpu_FR[RRR_R], cpu_FR[RRR_S]);
+ break;
+
+ default: /*reserved*/
+ RESERVED();
+ break;
+ }
+ break;
+
+ default: /*reserved*/
+ RESERVED();
+ break;
+ }
break;
case 11: /*FP1*/
HAS_OPTION(XTENSA_OPTION_FP_COPROCESSOR);
- TBD();
+
+#define gen_compare(rel, br, a, b) \
+ do { \
+ TCGv_i32 bit = tcg_const_i32(1 << br); \
+ \
+ gen_check_cpenable(dc, 0); \
+ gen_helper_##rel(cpu_env, bit, cpu_FR[a], cpu_FR[b]); \
+ tcg_temp_free(bit); \
+ } while (0)
+
+ switch (OP2) {
+ case 1: /*UN.Sf*/
+ gen_compare(un_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+ case 2: /*OEQ.Sf*/
+ gen_compare(oeq_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+ case 3: /*UEQ.Sf*/
+ gen_compare(ueq_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+ case 4: /*OLT.Sf*/
+ gen_compare(olt_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+ case 5: /*ULT.Sf*/
+ gen_compare(ult_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+ case 6: /*OLE.Sf*/
+ gen_compare(ole_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+ case 7: /*ULE.Sf*/
+ gen_compare(ule_s, RRR_R, RRR_S, RRR_T);
+ break;
+
+#undef gen_compare
+
+ case 8: /*MOVEQZ.Sf*/
+ case 9: /*MOVNEZ.Sf*/
+ case 10: /*MOVLTZ.Sf*/
+ case 11: /*MOVGEZ.Sf*/
+ gen_window_check1(dc, RRR_T);
+ gen_check_cpenable(dc, 0);
+ {
+ static const TCGCond cond[] = {
+ TCG_COND_NE,
+ TCG_COND_EQ,
+ TCG_COND_GE,
+ TCG_COND_LT
+ };
+ int label = gen_new_label();
+ tcg_gen_brcondi_i32(cond[OP2 - 8], cpu_R[RRR_T], 0, label);
+ tcg_gen_mov_i32(cpu_FR[RRR_R], cpu_FR[RRR_S]);
+ gen_set_label(label);
+ }
+ break;
+
+ case 12: /*MOVF.Sf*/
+ case 13: /*MOVT.Sf*/
+ HAS_OPTION(XTENSA_OPTION_BOOLEAN);
+ gen_check_cpenable(dc, 0);
+ {
+ int label = gen_new_label();
+ TCGv_i32 tmp = tcg_temp_new_i32();
+
+ tcg_gen_andi_i32(tmp, cpu_SR[BR], 1 << RRR_T);
+ tcg_gen_brcondi_i32(
+ OP2 & 1 ? TCG_COND_EQ : TCG_COND_NE,
+ tmp, 0, label);
+ tcg_gen_mov_i32(cpu_FR[RRR_R], cpu_FR[RRR_S]);
+ gen_set_label(label);
+ tcg_temp_free(tmp);
+ }
+ break;
+
+ default: /*reserved*/
+ RESERVED();
+ break;
+ }
break;
default: /*reserved*/
@@ -2090,8 +2364,34 @@
break;
case 3: /*LSCIp*/
- HAS_OPTION(XTENSA_OPTION_COPROCESSOR);
- TBD();
+ switch (RRI8_R) {
+ case 0: /*LSIf*/
+ case 4: /*SSIf*/
+ case 8: /*LSIUf*/
+ case 12: /*SSIUf*/
+ HAS_OPTION(XTENSA_OPTION_FP_COPROCESSOR);
+ gen_window_check1(dc, RRI8_S);
+ gen_check_cpenable(dc, 0);
+ {
+ TCGv_i32 addr = tcg_temp_new_i32();
+ tcg_gen_addi_i32(addr, cpu_R[RRI8_S], RRI8_IMM8 << 2);
+ gen_load_store_alignment(dc, 2, addr, false);
+ if (RRI8_R & 0x4) {
+ tcg_gen_qemu_st32(cpu_FR[RRI8_T], addr, dc->cring);
+ } else {
+ tcg_gen_qemu_ld32u(cpu_FR[RRI8_T], addr, dc->cring);
+ }
+ if (RRI8_R & 0x8) {
+ tcg_gen_mov_i32(cpu_R[RRI8_S], addr);
+ }
+ tcg_temp_free(addr);
+ }
+ break;
+
+ default: /*reserved*/
+ RESERVED();
+ break;
+ }
break;
case 4: /*MAC16d*/
@@ -2589,6 +2889,8 @@
dc.ccount_delta = 0;
dc.debug = tb->flags & XTENSA_TBFLAG_DEBUG;
dc.icount = tb->flags & XTENSA_TBFLAG_ICOUNT;
+ dc.cpenable = (tb->flags & XTENSA_TBFLAG_CPENABLE_MASK) >>
+ XTENSA_TBFLAG_CPENABLE_SHIFT;
init_litbase(&dc);
init_sar_tracker(&dc);
@@ -2730,6 +3032,16 @@
cpu_fprintf(f, "AR%02d=%08x%c", i, env->phys_regs[i],
(i % 4) == 3 ? '\n' : ' ');
}
+
+ if (xtensa_option_enabled(env->config, XTENSA_OPTION_FP_COPROCESSOR)) {
+ cpu_fprintf(f, "\n");
+
+ for (i = 0; i < 16; ++i) {
+ cpu_fprintf(f, "F%02d=%08x (%+10.8e)%c", i,
+ float32_val(env->fregs[i]),
+ *(float *)&env->fregs[i], (i % 2) == 1 ? '\n' : ' ');
+ }
+ }
}
void restore_state_to_opc(CPUXtensaState *env, TranslationBlock *tb, int pc_pos)
diff --git a/tcg/README b/tcg/README
index d03ae05..33783ee 100644
--- a/tcg/README
+++ b/tcg/README
@@ -392,7 +392,8 @@
Exit the current TB and jump to the TB index 'index' (constant) if the
current TB was linked to this TB. Otherwise execute the next
-instructions.
+instructions. Only indices 0 and 1 are valid and tcg_gen_goto_tb may be issued
+at most once with each slot index per TB.
* qemu_ld8u t0, t1, flags
qemu_ld8s t0, t1, flags
diff --git a/tcg/arm/tcg-target.c b/tcg/arm/tcg-target.c
index aed3b53..2bad0a2 100644
--- a/tcg/arm/tcg-target.c
+++ b/tcg/arm/tcg-target.c
@@ -145,12 +145,6 @@
}
}
-/* maximum number of register used for input function arguments */
-static inline int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return 4;
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
diff --git a/tcg/hppa/tcg-target.c b/tcg/hppa/tcg-target.c
index 5385d45..2c79c10 100644
--- a/tcg/hppa/tcg-target.c
+++ b/tcg/hppa/tcg-target.c
@@ -175,12 +175,6 @@
*insn_ptr = insn;
}
-/* maximum number of register used for input function arguments */
-static inline int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return 4;
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
@@ -912,6 +906,18 @@
tcg_out_mov(s, TCG_TYPE_I32, ret, scratch);
}
+static void tcg_out_movcond(TCGContext *s, int cond, TCGArg ret,
+ TCGArg c1, TCGArg c2, int c2const,
+ TCGArg v1, int v1const)
+{
+ tcg_out_comclr(s, tcg_invert_cond(cond), TCG_REG_R0, c1, c2, c2const);
+ if (v1const) {
+ tcg_out_movi(s, TCG_TYPE_I32, ret, v1);
+ } else {
+ tcg_out_mov(s, TCG_TYPE_I32, ret, v1);
+ }
+}
+
#if defined(CONFIG_SOFTMMU)
#include "../../softmmu_defs.h"
@@ -1520,6 +1526,11 @@
args[3], const_args[3], args[4], const_args[4]);
break;
+ case INDEX_op_movcond_i32:
+ tcg_out_movcond(s, args[5], args[0], args[1], args[2], const_args[2],
+ args[3], const_args[3]);
+ break;
+
case INDEX_op_add2_i32:
tcg_out_add2(s, args[0], args[1], args[2], args[3],
args[4], args[5], const_args[4]);
@@ -1628,6 +1639,10 @@
{ INDEX_op_setcond_i32, { "r", "rZ", "rI" } },
{ INDEX_op_setcond2_i32, { "r", "rZ", "rZ", "rI", "rI" } },
+ /* ??? We can actually support a signed 14-bit arg3, but we
+ only have existing constraints for a signed 11-bit. */
+ { INDEX_op_movcond_i32, { "r", "rZ", "rI", "rI", "0" } },
+
{ INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rI", "rZ" } },
{ INDEX_op_sub2_i32, { "r", "r", "rI", "rZ", "rK", "rZ" } },
diff --git a/tcg/hppa/tcg-target.h b/tcg/hppa/tcg-target.h
index 4defd28..5351353 100644
--- a/tcg/hppa/tcg-target.h
+++ b/tcg/hppa/tcg-target.h
@@ -96,7 +96,7 @@
#define TCG_TARGET_HAS_nand_i32 0
#define TCG_TARGET_HAS_nor_i32 0
#define TCG_TARGET_HAS_deposit_i32 1
-#define TCG_TARGET_HAS_movcond_i32 0
+#define TCG_TARGET_HAS_movcond_i32 1
/* optional instructions automatically implemented */
#define TCG_TARGET_HAS_neg_i32 0 /* sub rd, 0, rs */
diff --git a/tcg/i386/tcg-target.c b/tcg/i386/tcg-target.c
index aa1fa9f..122d636 100644
--- a/tcg/i386/tcg-target.c
+++ b/tcg/i386/tcg-target.c
@@ -75,9 +75,7 @@
TCG_REG_R8,
TCG_REG_R9,
#else
- TCG_REG_EAX,
- TCG_REG_EDX,
- TCG_REG_ECX
+ /* 32 bit mode uses stack based calling convention (GCC default). */
#endif
};
@@ -88,6 +86,18 @@
#endif
};
+/* Registers used with L constraint, which are the first argument
+ registers on x86_64, and two random call clobbered registers on
+ i386. */
+#if TCG_TARGET_REG_BITS == 64
+# define TCG_REG_L0 tcg_target_call_iarg_regs[0]
+# define TCG_REG_L1 tcg_target_call_iarg_regs[1]
+# define TCG_REG_L2 tcg_target_call_iarg_regs[2]
+#else
+# define TCG_REG_L0 TCG_REG_EAX
+# define TCG_REG_L1 TCG_REG_EDX
+#endif
+
static uint8_t *tb_ret_addr;
static void patch_reloc(uint8_t *code_ptr, int type,
@@ -114,16 +124,6 @@
}
}
-/* maximum number of register used for input function arguments */
-static inline int tcg_target_get_call_iarg_regs_count(int flags)
-{
- if (TCG_TARGET_REG_BITS == 64) {
- return 6;
- }
-
- return 0;
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
@@ -179,16 +179,16 @@
/* qemu_ld/st address constraint */
case 'L':
ct->ct |= TCG_CT_REG;
- if (TCG_TARGET_REG_BITS == 64) {
+#if TCG_TARGET_REG_BITS == 64
tcg_regset_set32(ct->u.regs, 0, 0xffff);
- tcg_regset_reset_reg(ct->u.regs, tcg_target_call_iarg_regs[0]);
- tcg_regset_reset_reg(ct->u.regs, tcg_target_call_iarg_regs[1]);
- tcg_regset_reset_reg(ct->u.regs, tcg_target_call_iarg_regs[2]);
- } else {
+ tcg_regset_reset_reg(ct->u.regs, TCG_REG_L0);
+ tcg_regset_reset_reg(ct->u.regs, TCG_REG_L1);
+ tcg_regset_reset_reg(ct->u.regs, TCG_REG_L2);
+#else
tcg_regset_set32(ct->u.regs, 0, 0xff);
- tcg_regset_reset_reg(ct->u.regs, TCG_REG_EAX);
- tcg_regset_reset_reg(ct->u.regs, TCG_REG_EDX);
- }
+ tcg_regset_reset_reg(ct->u.regs, TCG_REG_L0);
+ tcg_regset_reset_reg(ct->u.regs, TCG_REG_L1);
+#endif
break;
case 'e':
@@ -1029,8 +1029,8 @@
uint8_t **label_ptr, int which)
{
const int addrlo = args[addrlo_idx];
- const int r0 = tcg_target_call_iarg_regs[0];
- const int r1 = tcg_target_call_iarg_regs[1];
+ const int r0 = TCG_REG_L0;
+ const int r1 = TCG_REG_L1;
TCGType type = TCG_TYPE_I32;
int rexw = 0;
@@ -1192,8 +1192,7 @@
label_ptr, offsetof(CPUTLBEntry, addr_read));
/* TLB Hit. */
- tcg_out_qemu_ld_direct(s, data_reg, data_reg2,
- tcg_target_call_iarg_regs[0], 0, opc);
+ tcg_out_qemu_ld_direct(s, data_reg, data_reg2, TCG_REG_L0, 0, opc);
/* jmp label2 */
tcg_out8(s, OPC_JMP_short);
@@ -1226,14 +1225,10 @@
tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[arg_idx],
mem_index);
/* XXX/FIXME: suboptimal */
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[3],
- tcg_target_call_iarg_regs[2]);
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[2],
- tcg_target_call_iarg_regs[1]);
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[1],
- tcg_target_call_iarg_regs[0]);
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[0],
- TCG_AREG0);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[3], TCG_REG_L2);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[2], TCG_REG_L1);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[1], TCG_REG_L0);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[0], TCG_AREG0);
#endif
tcg_out_calli(s, (tcg_target_long)qemu_ld_helpers[s_bits]);
@@ -1299,11 +1294,9 @@
use the ADDR32 prefix. For now, do nothing. */
if (offset != GUEST_BASE) {
- tcg_out_movi(s, TCG_TYPE_I64,
- tcg_target_call_iarg_regs[0], GUEST_BASE);
- tgen_arithr(s, ARITH_ADD + P_REXW,
- tcg_target_call_iarg_regs[0], base);
- base = tcg_target_call_iarg_regs[0];
+ tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_L0, GUEST_BASE);
+ tgen_arithr(s, ARITH_ADD + P_REXW, TCG_REG_L0, base);
+ base = TCG_REG_L0;
offset = 0;
}
}
@@ -1324,8 +1317,8 @@
/* ??? Ideally we wouldn't need a scratch register. For user-only,
we could perform the bswap twice to restore the original value
instead of moving to the scratch. But as it is, the L constraint
- means that the second argument reg is definitely free here. */
- int scratch = tcg_target_call_iarg_regs[1];
+ means that TCG_REG_L1 is definitely free here. */
+ const int scratch = TCG_REG_L1;
switch (sizeop) {
case 0:
@@ -1398,8 +1391,7 @@
label_ptr, offsetof(CPUTLBEntry, addr_write));
/* TLB Hit. */
- tcg_out_qemu_st_direct(s, data_reg, data_reg2,
- tcg_target_call_iarg_regs[0], 0, opc);
+ tcg_out_qemu_st_direct(s, data_reg, data_reg2, TCG_REG_L0, 0, opc);
/* jmp label2 */
tcg_out8(s, OPC_JMP_short);
@@ -1434,18 +1426,14 @@
stack_adjust += 4;
#else
tcg_out_mov(s, (opc == 3 ? TCG_TYPE_I64 : TCG_TYPE_I32),
- tcg_target_call_iarg_regs[1], data_reg);
- tcg_out_movi(s, TCG_TYPE_I32, tcg_target_call_iarg_regs[2], mem_index);
+ TCG_REG_L1, data_reg);
+ tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_L2, mem_index);
stack_adjust = 0;
/* XXX/FIXME: suboptimal */
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[3],
- tcg_target_call_iarg_regs[2]);
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[2],
- tcg_target_call_iarg_regs[1]);
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[1],
- tcg_target_call_iarg_regs[0]);
- tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[0],
- TCG_AREG0);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[3], TCG_REG_L2);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[2], TCG_REG_L1);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[1], TCG_REG_L0);
+ tcg_out_mov(s, TCG_TYPE_I64, tcg_target_call_iarg_regs[0], TCG_AREG0);
#endif
tcg_out_calli(s, (tcg_target_long)qemu_st_helpers[s_bits]);
@@ -1472,11 +1460,9 @@
use the ADDR32 prefix. For now, do nothing. */
if (offset != GUEST_BASE) {
- tcg_out_movi(s, TCG_TYPE_I64,
- tcg_target_call_iarg_regs[0], GUEST_BASE);
- tgen_arithr(s, ARITH_ADD + P_REXW,
- tcg_target_call_iarg_regs[0], base);
- base = tcg_target_call_iarg_regs[0];
+ tcg_out_movi(s, TCG_TYPE_I64, TCG_REG_L0, GUEST_BASE);
+ tgen_arithr(s, ARITH_ADD + P_REXW, TCG_REG_L0, base);
+ base = TCG_REG_L0;
offset = 0;
}
}
@@ -2061,15 +2047,17 @@
#if TCG_TARGET_REG_BITS == 32
tcg_out_ld(s, TCG_TYPE_PTR, TCG_AREG0, TCG_REG_ESP,
(ARRAY_SIZE(tcg_target_callee_save_regs) + 1) * 4);
- tcg_out_ld(s, TCG_TYPE_PTR, tcg_target_call_iarg_regs[1], TCG_REG_ESP,
- (ARRAY_SIZE(tcg_target_callee_save_regs) + 2) * 4);
+ tcg_out_addi(s, TCG_REG_ESP, -stack_addend);
+ /* jmp *tb. */
+ tcg_out_modrm_offset(s, OPC_GRP5, EXT5_JMPN_Ev, TCG_REG_ESP,
+ (ARRAY_SIZE(tcg_target_callee_save_regs) + 2) * 4
+ + stack_addend);
#else
tcg_out_mov(s, TCG_TYPE_PTR, TCG_AREG0, tcg_target_call_iarg_regs[0]);
-#endif
tcg_out_addi(s, TCG_REG_ESP, -stack_addend);
-
/* jmp *tb. */
tcg_out_modrm(s, OPC_GRP5, EXT5_JMPN_Ev, tcg_target_call_iarg_regs[1]);
+#endif
/* TB epilogue */
tb_ret_addr = s->code_ptr;
diff --git a/tcg/i386/tcg-target.h b/tcg/i386/tcg-target.h
index b356d76..ace63ba 100644
--- a/tcg/i386/tcg-target.h
+++ b/tcg/i386/tcg-target.h
@@ -67,7 +67,11 @@
/* used for function call generation */
#define TCG_REG_CALL_STACK TCG_REG_ESP
#define TCG_TARGET_STACK_ALIGN 16
+#if defined(_WIN64)
+#define TCG_TARGET_CALL_STACK_OFFSET 32
+#else
#define TCG_TARGET_CALL_STACK_OFFSET 0
+#endif
/* optional instructions */
#define TCG_TARGET_HAS_div2_i32 1
diff --git a/tcg/ia64/tcg-target.c b/tcg/ia64/tcg-target.c
index 1745038..dc9c12c 100644
--- a/tcg/ia64/tcg-target.c
+++ b/tcg/ia64/tcg-target.c
@@ -176,12 +176,6 @@
TCG_REG_R8
};
-/* maximum number of register used for input function arguments */
-static inline int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return 8;
-}
-
/*
* opcode formation
*/
diff --git a/tcg/mips/tcg-target.c b/tcg/mips/tcg-target.c
index 74db83d..f70910a 100644
--- a/tcg/mips/tcg-target.c
+++ b/tcg/mips/tcg-target.c
@@ -68,7 +68,7 @@
#endif
/* check if we really need so many registers :P */
-static const int tcg_target_reg_alloc_order[] = {
+static const TCGReg tcg_target_reg_alloc_order[] = {
TCG_REG_S0,
TCG_REG_S1,
TCG_REG_S2,
@@ -94,14 +94,14 @@
TCG_REG_V1
};
-static const int tcg_target_call_iarg_regs[4] = {
+static const TCGReg tcg_target_call_iarg_regs[4] = {
TCG_REG_A0,
TCG_REG_A1,
TCG_REG_A2,
TCG_REG_A3
};
-static const int tcg_target_call_oarg_regs[2] = {
+static const TCGReg tcg_target_call_oarg_regs[2] = {
TCG_REG_V0,
TCG_REG_V1
};
@@ -185,12 +185,6 @@
}
}
-/* maximum number of register used for input function arguments */
-static inline int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return 4;
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
@@ -278,6 +272,8 @@
enum {
OPC_BEQ = 0x04 << 26,
OPC_BNE = 0x05 << 26,
+ OPC_BLEZ = 0x06 << 26,
+ OPC_BGTZ = 0x07 << 26,
OPC_ADDIU = 0x09 << 26,
OPC_SLTI = 0x0A << 26,
OPC_SLTIU = 0x0B << 26,
@@ -298,12 +294,16 @@
OPC_SPECIAL = 0x00 << 26,
OPC_SLL = OPC_SPECIAL | 0x00,
OPC_SRL = OPC_SPECIAL | 0x02,
+ OPC_ROTR = OPC_SPECIAL | (0x01 << 21) | 0x02,
OPC_SRA = OPC_SPECIAL | 0x03,
OPC_SLLV = OPC_SPECIAL | 0x04,
OPC_SRLV = OPC_SPECIAL | 0x06,
+ OPC_ROTRV = OPC_SPECIAL | (0x01 << 6) | 0x06,
OPC_SRAV = OPC_SPECIAL | 0x07,
OPC_JR = OPC_SPECIAL | 0x08,
OPC_JALR = OPC_SPECIAL | 0x09,
+ OPC_MOVZ = OPC_SPECIAL | 0x0A,
+ OPC_MOVN = OPC_SPECIAL | 0x0B,
OPC_MFHI = OPC_SPECIAL | 0x10,
OPC_MFLO = OPC_SPECIAL | 0x12,
OPC_MULT = OPC_SPECIAL | 0x18,
@@ -319,7 +319,13 @@
OPC_SLT = OPC_SPECIAL | 0x2A,
OPC_SLTU = OPC_SPECIAL | 0x2B,
+ OPC_REGIMM = 0x01 << 26,
+ OPC_BLTZ = OPC_REGIMM | (0x00 << 16),
+ OPC_BGEZ = OPC_REGIMM | (0x01 << 16),
+
OPC_SPECIAL3 = 0x1f << 26,
+ OPC_INS = OPC_SPECIAL3 | 0x004,
+ OPC_WSBH = OPC_SPECIAL3 | 0x0a0,
OPC_SEB = OPC_SPECIAL3 | 0x420,
OPC_SEH = OPC_SPECIAL3 | 0x620,
};
@@ -327,7 +333,8 @@
/*
* Type reg
*/
-static inline void tcg_out_opc_reg(TCGContext *s, int opc, int rd, int rs, int rt)
+static inline void tcg_out_opc_reg(TCGContext *s, int opc,
+ TCGReg rd, TCGReg rs, TCGReg rt)
{
int32_t inst;
@@ -341,7 +348,8 @@
/*
* Type immediate
*/
-static inline void tcg_out_opc_imm(TCGContext *s, int opc, int rt, int rs, int imm)
+static inline void tcg_out_opc_imm(TCGContext *s, int opc,
+ TCGReg rt, TCGReg rs, TCGArg imm)
{
int32_t inst;
@@ -355,7 +363,8 @@
/*
* Type branch
*/
-static inline void tcg_out_opc_br(TCGContext *s, int opc, int rt, int rs)
+static inline void tcg_out_opc_br(TCGContext *s, int opc,
+ TCGReg rt, TCGReg rs)
{
/* We pay attention here to not modify the branch target by reading
the existing value and using it again. This ensure that caches and
@@ -368,7 +377,8 @@
/*
* Type sa
*/
-static inline void tcg_out_opc_sa(TCGContext *s, int opc, int rd, int rt, int sa)
+static inline void tcg_out_opc_sa(TCGContext *s, int opc,
+ TCGReg rd, TCGReg rt, TCGArg sa)
{
int32_t inst;
@@ -407,38 +417,47 @@
}
}
-static inline void tcg_out_bswap16(TCGContext *s, int ret, int arg)
+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, int ret, int arg)
+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, int ret, int arg)
+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();
@@ -456,9 +475,10 @@
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, int ret, int arg)
+static inline void tcg_out_ext8s(TCGContext *s, TCGReg ret, TCGReg arg)
{
#ifdef _MIPS_ARCH_MIPS32R2
tcg_out_opc_reg(s, OPC_SEB, ret, 0, arg);
@@ -468,7 +488,7 @@
#endif
}
-static inline void tcg_out_ext16s(TCGContext *s, int ret, int arg)
+static inline void tcg_out_ext16s(TCGContext *s, TCGReg ret, TCGReg arg)
{
#ifdef _MIPS_ARCH_MIPS32R2
tcg_out_opc_reg(s, OPC_SEH, ret, 0, arg);
@@ -478,8 +498,8 @@
#endif
}
-static inline void tcg_out_ldst(TCGContext *s, int opc, int arg,
- int arg1, tcg_target_long arg2)
+static inline void tcg_out_ldst(TCGContext *s, int opc, TCGArg arg,
+ TCGReg arg1, TCGArg arg2)
{
if (arg2 == (int16_t) arg2) {
tcg_out_opc_imm(s, opc, arg, arg1, arg2);
@@ -502,7 +522,7 @@
tcg_out_ldst(s, OPC_SW, arg, arg1, arg2);
}
-static inline void tcg_out_addi(TCGContext *s, int reg, tcg_target_long val)
+static inline void tcg_out_addi(TCGContext *s, TCGReg reg, TCGArg val)
{
if (val == (int16_t)val) {
tcg_out_opc_imm(s, OPC_ADDIU, reg, reg, val);
@@ -543,7 +563,7 @@
#undef DEFINE_TCG_OUT_CALL_IARG_GET_ARG
#define DEFINE_TCG_OUT_CALL_IARG_GET_ARG(A) \
tcg_out_movi(s, TCG_TYPE_I32, A, arg);
-DEFINE_TCG_OUT_CALL_IARG(tcg_out_call_iarg_imm32, uint32_t arg)
+DEFINE_TCG_OUT_CALL_IARG(tcg_out_call_iarg_imm32, TCGArg arg)
#undef DEFINE_TCG_OUT_CALL_IARG_GET_ARG
/* We don't use the macro for this one to avoid an unnecessary reg-reg
@@ -573,8 +593,8 @@
#endif
}
-static void tcg_out_brcond(TCGContext *s, TCGCond cond, int arg1,
- int arg2, int label_index)
+static void tcg_out_brcond(TCGContext *s, TCGCond cond, TCGArg arg1,
+ TCGArg arg2, int label_index)
{
TCGLabel *l = &s->labels[label_index];
@@ -586,32 +606,48 @@
tcg_out_opc_br(s, OPC_BNE, arg1, arg2);
break;
case TCG_COND_LT:
- tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg1, arg2);
- tcg_out_opc_br(s, OPC_BNE, TCG_REG_AT, TCG_REG_ZERO);
+ if (arg2 == 0) {
+ tcg_out_opc_br(s, OPC_BLTZ, 0, arg1);
+ } else {
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg1, arg2);
+ tcg_out_opc_br(s, OPC_BNE, TCG_REG_AT, TCG_REG_ZERO);
+ }
break;
case TCG_COND_LTU:
tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, arg1, arg2);
tcg_out_opc_br(s, OPC_BNE, TCG_REG_AT, TCG_REG_ZERO);
break;
case TCG_COND_GE:
- tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg1, arg2);
- tcg_out_opc_br(s, OPC_BEQ, TCG_REG_AT, TCG_REG_ZERO);
+ if (arg2 == 0) {
+ tcg_out_opc_br(s, OPC_BGEZ, 0, arg1);
+ } else {
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg1, arg2);
+ tcg_out_opc_br(s, OPC_BEQ, TCG_REG_AT, TCG_REG_ZERO);
+ }
break;
case TCG_COND_GEU:
tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, arg1, arg2);
tcg_out_opc_br(s, OPC_BEQ, TCG_REG_AT, TCG_REG_ZERO);
break;
case TCG_COND_LE:
- tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg2, arg1);
- tcg_out_opc_br(s, OPC_BEQ, TCG_REG_AT, TCG_REG_ZERO);
+ if (arg2 == 0) {
+ tcg_out_opc_br(s, OPC_BLEZ, 0, arg1);
+ } else {
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg2, arg1);
+ tcg_out_opc_br(s, OPC_BEQ, TCG_REG_AT, TCG_REG_ZERO);
+ }
break;
case TCG_COND_LEU:
tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, arg2, arg1);
tcg_out_opc_br(s, OPC_BEQ, TCG_REG_AT, TCG_REG_ZERO);
break;
case TCG_COND_GT:
- tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg2, arg1);
- tcg_out_opc_br(s, OPC_BNE, TCG_REG_AT, TCG_REG_ZERO);
+ if (arg2 == 0) {
+ tcg_out_opc_br(s, OPC_BGTZ, 0, arg1);
+ } else {
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, arg2, arg1);
+ tcg_out_opc_br(s, OPC_BNE, TCG_REG_AT, TCG_REG_ZERO);
+ }
break;
case TCG_COND_GTU:
tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, arg2, arg1);
@@ -631,8 +667,9 @@
/* XXX: we implement it at the target level to avoid having to
handle cross basic blocks temporaries */
-static void tcg_out_brcond2(TCGContext *s, TCGCond cond, int arg1,
- int arg2, int arg3, int arg4, int label_index)
+static void tcg_out_brcond2(TCGContext *s, TCGCond cond, TCGArg arg1,
+ TCGArg arg2, TCGArg arg3, TCGArg arg4,
+ int label_index)
{
void *label_ptr;
@@ -694,8 +731,70 @@
reloc_pc16(label_ptr, (tcg_target_long) s->code_ptr);
}
-static void tcg_out_setcond(TCGContext *s, TCGCond cond, int ret,
- int arg1, int arg2)
+static void tcg_out_movcond(TCGContext *s, TCGCond cond, TCGReg ret,
+ TCGArg c1, TCGArg c2, TCGArg v)
+{
+ switch (cond) {
+ case TCG_COND_EQ:
+ if (c1 == 0) {
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, c2);
+ } else if (c2 == 0) {
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, c1);
+ } else {
+ tcg_out_opc_reg(s, OPC_XOR, TCG_REG_AT, c1, c2);
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, TCG_REG_AT);
+ }
+ break;
+ case TCG_COND_NE:
+ if (c1 == 0) {
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, c2);
+ } else if (c2 == 0) {
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, c1);
+ } else {
+ tcg_out_opc_reg(s, OPC_XOR, TCG_REG_AT, c1, c2);
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, TCG_REG_AT);
+ }
+ break;
+ case TCG_COND_LT:
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, c1, c2);
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_LTU:
+ tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, c1, c2);
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_GE:
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, c1, c2);
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_GEU:
+ tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, c1, c2);
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_LE:
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, c2, c1);
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_LEU:
+ tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, c2, c1);
+ tcg_out_opc_reg(s, OPC_MOVZ, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_GT:
+ tcg_out_opc_reg(s, OPC_SLT, TCG_REG_AT, c2, c1);
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, TCG_REG_AT);
+ break;
+ case TCG_COND_GTU:
+ tcg_out_opc_reg(s, OPC_SLTU, TCG_REG_AT, c2, c1);
+ tcg_out_opc_reg(s, OPC_MOVN, ret, v, TCG_REG_AT);
+ break;
+ default:
+ tcg_abort();
+ break;
+ }
+}
+
+static void tcg_out_setcond(TCGContext *s, TCGCond cond, TCGReg ret,
+ TCGArg arg1, TCGArg arg2)
{
switch (cond) {
case TCG_COND_EQ:
@@ -754,8 +853,8 @@
/* XXX: we implement it at the target level to avoid having to
handle cross basic blocks temporaries */
-static void tcg_out_setcond2(TCGContext *s, TCGCond cond, int ret,
- int arg1, int arg2, int arg3, int arg4)
+static void tcg_out_setcond2(TCGContext *s, TCGCond cond, TCGReg ret,
+ TCGArg arg1, TCGArg arg2, TCGArg arg3, TCGArg arg4)
{
switch (cond) {
case TCG_COND_EQ:
@@ -842,18 +941,17 @@
static void tcg_out_qemu_ld(TCGContext *s, const TCGArg *args,
int opc)
{
- int addr_regl, addr_meml;
- int data_regl, data_regh, data_reg1, data_reg2;
- int mem_index, s_bits;
+ TCGReg addr_regl, data_regl, data_regh, data_reg1, data_reg2;
#if defined(CONFIG_SOFTMMU)
void *label1_ptr, *label2_ptr;
int arg_num;
-#endif
-#if TARGET_LONG_BITS == 64
-# if defined(CONFIG_SOFTMMU)
+ int mem_index, s_bits;
+ int addr_meml;
+# if TARGET_LONG_BITS == 64
uint8_t *label3_ptr;
+ TCGReg addr_regh;
+ int addr_memh;
# endif
- int addr_regh, addr_memh;
#endif
data_regl = *args++;
if (opc == 3)
@@ -861,11 +959,22 @@
else
data_regh = 0;
addr_regl = *args++;
-#if TARGET_LONG_BITS == 64
+#if defined(CONFIG_SOFTMMU)
+# if TARGET_LONG_BITS == 64
addr_regh = *args++;
-#endif
+# if defined(TCG_TARGET_WORDS_BIGENDIAN)
+ addr_memh = 0;
+ addr_meml = 4;
+# else
+ addr_memh = 4;
+ addr_meml = 0;
+# endif
+# else
+ addr_meml = 0;
+# endif
mem_index = *args;
s_bits = opc & 3;
+#endif
if (opc == 3) {
#if defined(TCG_TARGET_WORDS_BIGENDIAN)
@@ -879,18 +988,6 @@
data_reg1 = data_regl;
data_reg2 = 0;
}
-#if TARGET_LONG_BITS == 64
-# if defined(TCG_TARGET_WORDS_BIGENDIAN)
- addr_memh = 0;
- addr_meml = 4;
-# else
- addr_memh = 4;
- addr_meml = 0;
-# endif
-#else
- addr_meml = 0;
-#endif
-
#if defined(CONFIG_SOFTMMU)
tcg_out_opc_sa(s, OPC_SRL, TCG_REG_A0, addr_regl, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
tcg_out_opc_imm(s, OPC_ANDI, TCG_REG_A0, TCG_REG_A0, (CPU_TLB_SIZE - 1) << CPU_TLB_ENTRY_BITS);
@@ -1029,23 +1126,45 @@
static void tcg_out_qemu_st(TCGContext *s, const TCGArg *args,
int opc)
{
- int addr_regl, addr_meml;
- int data_regl, data_regh, data_reg1, data_reg2;
- int mem_index, s_bits;
+ TCGReg addr_regl, data_regl, data_regh, data_reg1, data_reg2;
#if defined(CONFIG_SOFTMMU)
uint8_t *label1_ptr, *label2_ptr;
int arg_num;
+ int mem_index, s_bits;
+ int addr_meml;
#endif
#if TARGET_LONG_BITS == 64
# if defined(CONFIG_SOFTMMU)
uint8_t *label3_ptr;
+ TCGReg addr_regh;
+ int addr_memh;
# endif
- int addr_regh, addr_memh;
#endif
-
data_regl = *args++;
if (opc == 3) {
data_regh = *args++;
+ } else {
+ data_regh = 0;
+ }
+ addr_regl = *args++;
+#if defined(CONFIG_SOFTMMU)
+# if TARGET_LONG_BITS == 64
+ addr_regh = *args++;
+# if defined(TCG_TARGET_WORDS_BIGENDIAN)
+ addr_memh = 0;
+ addr_meml = 4;
+# else
+ addr_memh = 4;
+ addr_meml = 0;
+# endif
+# else
+ addr_meml = 0;
+# endif
+ mem_index = *args;
+ s_bits = opc;
+#endif
+
+ if (opc == 3) {
#if defined(TCG_TARGET_WORDS_BIGENDIAN)
data_reg1 = data_regh;
data_reg2 = data_regl;
@@ -1056,23 +1175,7 @@
} else {
data_reg1 = data_regl;
data_reg2 = 0;
- data_regh = 0;
}
- addr_regl = *args++;
-#if TARGET_LONG_BITS == 64
- addr_regh = *args++;
-# if defined(TCG_TARGET_WORDS_BIGENDIAN)
- addr_memh = 0;
- addr_meml = 4;
-# else
- addr_memh = 4;
- addr_meml = 0;
-# endif
-#else
- addr_meml = 0;
-#endif
- mem_index = *args;
- s_bits = opc;
#if defined(CONFIG_SOFTMMU)
tcg_out_opc_sa(s, OPC_SRL, TCG_REG_A0, addr_regl, TARGET_PAGE_BITS - CPU_TLB_ENTRY_BITS);
@@ -1157,7 +1260,8 @@
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);
@@ -1377,6 +1481,31 @@
tcg_out_opc_reg(s, OPC_SRLV, args[0], args[2], args[1]);
}
break;
+ case INDEX_op_rotl_i32:
+ if (const_args[2]) {
+ tcg_out_opc_sa(s, OPC_ROTR, args[0], args[1], 0x20 - args[2]);
+ } else {
+ tcg_out_movi(s, TCG_TYPE_I32, TCG_REG_AT, 32);
+ tcg_out_opc_reg(s, OPC_SUBU, TCG_REG_AT, TCG_REG_AT, args[2]);
+ tcg_out_opc_reg(s, OPC_ROTRV, args[0], TCG_REG_AT, args[1]);
+ }
+ break;
+ case INDEX_op_rotr_i32:
+ if (const_args[2]) {
+ tcg_out_opc_sa(s, OPC_ROTR, args[0], args[1], args[2]);
+ } else {
+ tcg_out_opc_reg(s, OPC_ROTRV, args[0], args[2], args[1]);
+ }
+ 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]);
@@ -1385,6 +1514,11 @@
tcg_out_ext16s(s, args[0], args[1]);
break;
+ case INDEX_op_deposit_i32:
+ tcg_out_opc_imm(s, OPC_INS, args[0], args[2],
+ ((args[3] + args[4] - 1) << 11) | (args[3] << 6));
+ break;
+
case INDEX_op_brcond_i32:
tcg_out_brcond(s, args[2], args[0], args[1], args[3]);
break;
@@ -1392,6 +1526,10 @@
tcg_out_brcond2(s, args[4], args[0], args[1], args[2], args[3], args[5]);
break;
+ case INDEX_op_movcond_i32:
+ tcg_out_movcond(s, args[5], args[0], args[1], args[2], args[3]);
+ break;
+
case INDEX_op_setcond_i32:
tcg_out_setcond(s, args[3], args[0], args[1], args[2]);
break;
@@ -1453,34 +1591,42 @@
{ INDEX_op_st16_i32, { "rZ", "r" } },
{ INDEX_op_st_i32, { "rZ", "r" } },
- { INDEX_op_add_i32, { "r", "rZ", "rJZ" } },
+ { INDEX_op_add_i32, { "r", "rZ", "rJ" } },
{ INDEX_op_mul_i32, { "r", "rZ", "rZ" } },
{ INDEX_op_mulu2_i32, { "r", "r", "rZ", "rZ" } },
{ INDEX_op_div_i32, { "r", "rZ", "rZ" } },
{ INDEX_op_divu_i32, { "r", "rZ", "rZ" } },
{ INDEX_op_rem_i32, { "r", "rZ", "rZ" } },
{ INDEX_op_remu_i32, { "r", "rZ", "rZ" } },
- { INDEX_op_sub_i32, { "r", "rZ", "rJZ" } },
+ { INDEX_op_sub_i32, { "r", "rZ", "rJ" } },
- { INDEX_op_and_i32, { "r", "rZ", "rIZ" } },
+ { INDEX_op_and_i32, { "r", "rZ", "rI" } },
{ INDEX_op_nor_i32, { "r", "rZ", "rZ" } },
{ INDEX_op_not_i32, { "r", "rZ" } },
{ INDEX_op_or_i32, { "r", "rZ", "rIZ" } },
{ INDEX_op_xor_i32, { "r", "rZ", "rIZ" } },
- { INDEX_op_shl_i32, { "r", "rZ", "riZ" } },
- { INDEX_op_shr_i32, { "r", "rZ", "riZ" } },
- { INDEX_op_sar_i32, { "r", "rZ", "riZ" } },
+ { INDEX_op_shl_i32, { "r", "rZ", "ri" } },
+ { INDEX_op_shr_i32, { "r", "rZ", "ri" } },
+ { INDEX_op_sar_i32, { "r", "rZ", "ri" } },
+ { INDEX_op_rotr_i32, { "r", "rZ", "ri" } },
+ { INDEX_op_rotl_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" } },
+ { INDEX_op_deposit_i32, { "r", "0", "rZ" } },
+
{ INDEX_op_brcond_i32, { "rZ", "rZ" } },
+ { INDEX_op_movcond_i32, { "r", "rZ", "rZ", "rZ", "0" } },
{ INDEX_op_setcond_i32, { "r", "rZ", "rZ" } },
{ INDEX_op_setcond2_i32, { "r", "rZ", "rZ", "rZ", "rZ" } },
- { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rJZ", "rJZ" } },
- { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rJZ", "rJZ" } },
+ { INDEX_op_add2_i32, { "r", "r", "rZ", "rZ", "rJ", "rJ" } },
+ { INDEX_op_sub2_i32, { "r", "r", "rZ", "rZ", "rJ", "rJ" } },
{ INDEX_op_brcond2_i32, { "rZ", "rZ", "rZ", "rZ" } },
#if TARGET_LONG_BITS == 32
@@ -1520,7 +1666,6 @@
TCG_REG_S5,
TCG_REG_S6,
TCG_REG_S7,
- TCG_REG_GP,
TCG_REG_FP,
TCG_REG_RA, /* should be last for ABI compliance */
};
@@ -1530,11 +1675,15 @@
{
int i, frame_size;
- /* reserve some stack space */
+ /* reserve some stack space, also for TCG temps. */
frame_size = ARRAY_SIZE(tcg_target_callee_save_regs) * 4
- + TCG_STATIC_CALL_ARGS_SIZE;
+ + TCG_STATIC_CALL_ARGS_SIZE
+ + CPU_TEMP_BUF_NLONGS * sizeof(long);
frame_size = (frame_size + TCG_TARGET_STACK_ALIGN - 1) &
~(TCG_TARGET_STACK_ALIGN - 1);
+ tcg_set_frame(s, TCG_REG_SP, ARRAY_SIZE(tcg_target_callee_save_regs) * 4
+ + TCG_STATIC_CALL_ARGS_SIZE,
+ CPU_TEMP_BUF_NLONGS * sizeof(long));
/* TB prologue */
tcg_out_addi(s, TCG_REG_SP, -frame_size);
@@ -1586,8 +1735,7 @@
tcg_regset_set_reg(s->reserved_regs, TCG_REG_T0); /* internal use */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_RA); /* return address */
tcg_regset_set_reg(s->reserved_regs, TCG_REG_SP); /* stack pointer */
+ tcg_regset_set_reg(s->reserved_regs, TCG_REG_GP); /* global pointer */
tcg_add_target_add_op_defs(mips_op_defs);
- tcg_set_frame(s, TCG_AREG0, offsetof(CPUArchState, temp_buf),
- CPU_TEMP_BUF_NLONGS * sizeof(long));
}
diff --git a/tcg/mips/tcg-target.h b/tcg/mips/tcg-target.h
index 9c68a32..d147e70 100644
--- a/tcg/mips/tcg-target.h
+++ b/tcg/mips/tcg-target.h
@@ -80,17 +80,34 @@
#define TCG_TARGET_HAS_div_i32 1
#define TCG_TARGET_HAS_not_i32 1
#define TCG_TARGET_HAS_nor_i32 1
-#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
#define TCG_TARGET_HAS_nand_i32 0
-#define TCG_TARGET_HAS_deposit_i32 0
+
+/* optional instructions only implemented on MIPS4, MIPS32 and Loongson 2 */
+#if defined(_MIPS_ARCH_MIPS4) || defined(_MIPS_ARCH_MIPS32) || \
+ defined(_MIPS_ARCH_MIPS32R2) || defined(_MIPS_ARCH_LOONGSON2E) || \
+ defined(_MIPS_ARCH_LOONGSON2F)
+#define TCG_TARGET_HAS_movcond_i32 1
+#else
#define TCG_TARGET_HAS_movcond_i32 0
+#endif
+
+/* optional instructions only implemented on MIPS32R2 */
+#ifdef _MIPS_ARCH_MIPS32R2
+#define TCG_TARGET_HAS_bswap16_i32 1
+#define TCG_TARGET_HAS_bswap32_i32 1
+#define TCG_TARGET_HAS_rot_i32 1
+#define TCG_TARGET_HAS_deposit_i32 1
+#else
+#define TCG_TARGET_HAS_bswap16_i32 0
+#define TCG_TARGET_HAS_bswap32_i32 0
+#define TCG_TARGET_HAS_rot_i32 0
+#define TCG_TARGET_HAS_deposit_i32 0
+#endif
/* optional instructions automatically implemented */
#define TCG_TARGET_HAS_neg_i32 0 /* sub rd, zero, rt */
diff --git a/tcg/optimize.c b/tcg/optimize.c
index 1be7631..35532a1 100644
--- a/tcg/optimize.c
+++ b/tcg/optimize.c
@@ -39,8 +39,6 @@
TCG_TEMP_UNDEF = 0,
TCG_TEMP_CONST,
TCG_TEMP_COPY,
- TCG_TEMP_HAS_COPY,
- TCG_TEMP_ANY
} tcg_temp_state;
struct tcg_temp_info {
@@ -52,39 +50,19 @@
static struct tcg_temp_info temps[TCG_MAX_TEMPS];
-/* Reset TEMP's state to TCG_TEMP_ANY. If TEMP was a representative of some
- class of equivalent temp's, a new representative should be chosen in this
- class. */
-static void reset_temp(TCGArg temp, int nb_temps, int nb_globals)
+/* Reset TEMP's state to TCG_TEMP_UNDEF. If TEMP only had one copy, remove
+ the copy flag from the left temp. */
+static void reset_temp(TCGArg temp)
{
- int i;
- TCGArg new_base = (TCGArg)-1;
- if (temps[temp].state == TCG_TEMP_HAS_COPY) {
- for (i = temps[temp].next_copy; i != temp; i = temps[i].next_copy) {
- if (i >= nb_globals) {
- temps[i].state = TCG_TEMP_HAS_COPY;
- new_base = i;
- break;
- }
+ if (temps[temp].state == TCG_TEMP_COPY) {
+ if (temps[temp].prev_copy == temps[temp].next_copy) {
+ temps[temps[temp].next_copy].state = TCG_TEMP_UNDEF;
+ } else {
+ temps[temps[temp].next_copy].prev_copy = temps[temp].prev_copy;
+ temps[temps[temp].prev_copy].next_copy = temps[temp].next_copy;
}
- for (i = temps[temp].next_copy; i != temp; i = temps[i].next_copy) {
- if (new_base == (TCGArg)-1) {
- temps[i].state = TCG_TEMP_ANY;
- } else {
- temps[i].val = new_base;
- }
- }
- temps[temps[temp].next_copy].prev_copy = temps[temp].prev_copy;
- temps[temps[temp].prev_copy].next_copy = temps[temp].next_copy;
- } else if (temps[temp].state == TCG_TEMP_COPY) {
- temps[temps[temp].next_copy].prev_copy = temps[temp].prev_copy;
- temps[temps[temp].prev_copy].next_copy = temps[temp].next_copy;
- new_base = temps[temp].val;
}
- temps[temp].state = TCG_TEMP_ANY;
- if (new_base != (TCGArg)-1 && temps[new_base].next_copy == new_base) {
- temps[new_base].state = TCG_TEMP_ANY;
- }
+ temps[temp].state = TCG_TEMP_UNDEF;
}
static int op_bits(TCGOpcode op)
@@ -107,33 +85,83 @@
}
}
-static void tcg_opt_gen_mov(TCGArg *gen_args, TCGArg dst, TCGArg src,
- int nb_temps, int nb_globals)
+static TCGArg find_better_copy(TCGContext *s, TCGArg temp)
{
- reset_temp(dst, nb_temps, nb_globals);
- assert(temps[src].state != TCG_TEMP_COPY);
- if (src >= nb_globals) {
- assert(temps[src].state != TCG_TEMP_CONST);
- if (temps[src].state != TCG_TEMP_HAS_COPY) {
- temps[src].state = TCG_TEMP_HAS_COPY;
+ TCGArg i;
+
+ /* If this is already a global, we can't do better. */
+ if (temp < s->nb_globals) {
+ return temp;
+ }
+
+ /* Search for a global first. */
+ for (i = temps[temp].next_copy ; i != temp ; i = temps[i].next_copy) {
+ if (i < s->nb_globals) {
+ return i;
+ }
+ }
+
+ /* If it is a temp, search for a temp local. */
+ if (!s->temps[temp].temp_local) {
+ for (i = temps[temp].next_copy ; i != temp ; i = temps[i].next_copy) {
+ if (s->temps[i].temp_local) {
+ return i;
+ }
+ }
+ }
+
+ /* Failure to find a better representation, return the same temp. */
+ return temp;
+}
+
+static bool temps_are_copies(TCGArg arg1, TCGArg arg2)
+{
+ TCGArg i;
+
+ if (arg1 == arg2) {
+ return true;
+ }
+
+ if (temps[arg1].state != TCG_TEMP_COPY
+ || temps[arg2].state != TCG_TEMP_COPY) {
+ return false;
+ }
+
+ for (i = temps[arg1].next_copy ; i != arg1 ; i = temps[i].next_copy) {
+ if (i == arg2) {
+ return true;
+ }
+ }
+
+ return false;
+}
+
+static void tcg_opt_gen_mov(TCGContext *s, TCGArg *gen_args,
+ TCGArg dst, TCGArg src)
+{
+ reset_temp(dst);
+ assert(temps[src].state != TCG_TEMP_CONST);
+
+ if (s->temps[src].type == s->temps[dst].type) {
+ if (temps[src].state != TCG_TEMP_COPY) {
+ temps[src].state = TCG_TEMP_COPY;
temps[src].next_copy = src;
temps[src].prev_copy = src;
}
temps[dst].state = TCG_TEMP_COPY;
- temps[dst].val = src;
temps[dst].next_copy = temps[src].next_copy;
temps[dst].prev_copy = src;
temps[temps[dst].next_copy].prev_copy = dst;
temps[src].next_copy = dst;
}
+
gen_args[0] = dst;
gen_args[1] = src;
}
-static void tcg_opt_gen_movi(TCGArg *gen_args, TCGArg dst, TCGArg val,
- int nb_temps, int nb_globals)
+static void tcg_opt_gen_movi(TCGArg *gen_args, TCGArg dst, TCGArg val)
{
- reset_temp(dst, nb_temps, nb_globals);
+ reset_temp(dst);
temps[dst].state = TCG_TEMP_CONST;
temps[dst].val = val;
gen_args[0] = dst;
@@ -264,58 +292,88 @@
return res;
}
+/* Return 2 if the condition can't be simplified, and the result
+ of the condition (0 or 1) if it can */
static TCGArg do_constant_folding_cond(TCGOpcode op, TCGArg x,
TCGArg y, TCGCond c)
{
- switch (op_bits(op)) {
- case 32:
- switch (c) {
- case TCG_COND_EQ:
- return (uint32_t)x == (uint32_t)y;
- case TCG_COND_NE:
- return (uint32_t)x != (uint32_t)y;
- case TCG_COND_LT:
- return (int32_t)x < (int32_t)y;
- case TCG_COND_GE:
- return (int32_t)x >= (int32_t)y;
- case TCG_COND_LE:
- return (int32_t)x <= (int32_t)y;
- case TCG_COND_GT:
- return (int32_t)x > (int32_t)y;
- case TCG_COND_LTU:
- return (uint32_t)x < (uint32_t)y;
- case TCG_COND_GEU:
- return (uint32_t)x >= (uint32_t)y;
- case TCG_COND_LEU:
- return (uint32_t)x <= (uint32_t)y;
- case TCG_COND_GTU:
- return (uint32_t)x > (uint32_t)y;
+ if (temps[x].state == TCG_TEMP_CONST && temps[y].state == TCG_TEMP_CONST) {
+ switch (op_bits(op)) {
+ case 32:
+ switch (c) {
+ case TCG_COND_EQ:
+ return (uint32_t)temps[x].val == (uint32_t)temps[y].val;
+ case TCG_COND_NE:
+ return (uint32_t)temps[x].val != (uint32_t)temps[y].val;
+ case TCG_COND_LT:
+ return (int32_t)temps[x].val < (int32_t)temps[y].val;
+ case TCG_COND_GE:
+ return (int32_t)temps[x].val >= (int32_t)temps[y].val;
+ case TCG_COND_LE:
+ return (int32_t)temps[x].val <= (int32_t)temps[y].val;
+ case TCG_COND_GT:
+ return (int32_t)temps[x].val > (int32_t)temps[y].val;
+ case TCG_COND_LTU:
+ return (uint32_t)temps[x].val < (uint32_t)temps[y].val;
+ case TCG_COND_GEU:
+ return (uint32_t)temps[x].val >= (uint32_t)temps[y].val;
+ case TCG_COND_LEU:
+ return (uint32_t)temps[x].val <= (uint32_t)temps[y].val;
+ case TCG_COND_GTU:
+ return (uint32_t)temps[x].val > (uint32_t)temps[y].val;
+ }
+ break;
+ case 64:
+ switch (c) {
+ case TCG_COND_EQ:
+ return (uint64_t)temps[x].val == (uint64_t)temps[y].val;
+ case TCG_COND_NE:
+ return (uint64_t)temps[x].val != (uint64_t)temps[y].val;
+ case TCG_COND_LT:
+ return (int64_t)temps[x].val < (int64_t)temps[y].val;
+ case TCG_COND_GE:
+ return (int64_t)temps[x].val >= (int64_t)temps[y].val;
+ case TCG_COND_LE:
+ return (int64_t)temps[x].val <= (int64_t)temps[y].val;
+ case TCG_COND_GT:
+ return (int64_t)temps[x].val > (int64_t)temps[y].val;
+ case TCG_COND_LTU:
+ return (uint64_t)temps[x].val < (uint64_t)temps[y].val;
+ case TCG_COND_GEU:
+ return (uint64_t)temps[x].val >= (uint64_t)temps[y].val;
+ case TCG_COND_LEU:
+ return (uint64_t)temps[x].val <= (uint64_t)temps[y].val;
+ case TCG_COND_GTU:
+ return (uint64_t)temps[x].val > (uint64_t)temps[y].val;
+ }
+ break;
}
- break;
- case 64:
+ } else if (temps_are_copies(x, y)) {
switch (c) {
- case TCG_COND_EQ:
- return (uint64_t)x == (uint64_t)y;
- case TCG_COND_NE:
- return (uint64_t)x != (uint64_t)y;
- case TCG_COND_LT:
- return (int64_t)x < (int64_t)y;
- case TCG_COND_GE:
- return (int64_t)x >= (int64_t)y;
- case TCG_COND_LE:
- return (int64_t)x <= (int64_t)y;
case TCG_COND_GT:
- return (int64_t)x > (int64_t)y;
case TCG_COND_LTU:
- return (uint64_t)x < (uint64_t)y;
- case TCG_COND_GEU:
- return (uint64_t)x >= (uint64_t)y;
- case TCG_COND_LEU:
- return (uint64_t)x <= (uint64_t)y;
+ case TCG_COND_LT:
case TCG_COND_GTU:
- return (uint64_t)x > (uint64_t)y;
+ case TCG_COND_NE:
+ return 0;
+ case TCG_COND_GE:
+ case TCG_COND_GEU:
+ case TCG_COND_LE:
+ case TCG_COND_LEU:
+ case TCG_COND_EQ:
+ return 1;
}
- break;
+ } else if (temps[y].state == TCG_TEMP_CONST && temps[y].val == 0) {
+ switch (c) {
+ case TCG_COND_LTU:
+ return 0;
+ case TCG_COND_GEU:
+ return 1;
+ default:
+ return 2;
+ }
+ } else {
+ return 2;
}
fprintf(stderr,
@@ -324,7 +382,6 @@
tcg_abort();
}
-
/* Propagate constants and copies, fold constant expressions. */
static TCGArg *tcg_constant_folding(TCGContext *s, uint16_t *tcg_opc_ptr,
TCGArg *args, TCGOpDef *tcg_op_defs)
@@ -338,10 +395,8 @@
/* Array VALS has an element for each temp.
If this temp holds a constant then its value is kept in VALS' element.
- If this temp is a copy of other ones then this equivalence class'
- representative is kept in VALS' element.
- If this temp is neither copy nor constant then corresponding VALS'
- element is unused. */
+ If this temp is a copy of other ones then the other copies are
+ available through the doubly linked circular list. */
nb_temps = s->nb_temps;
nb_globals = s->nb_globals;
@@ -353,11 +408,18 @@
op = gen_opc_buf[op_index];
def = &tcg_op_defs[op];
/* Do copy propagation */
- if (!(def->flags & (TCG_OPF_CALL_CLOBBER | TCG_OPF_SIDE_EFFECTS))) {
- assert(op != INDEX_op_call);
+ if (op == INDEX_op_call) {
+ int nb_oargs = args[0] >> 16;
+ int nb_iargs = args[0] & 0xffff;
+ for (i = nb_oargs + 1; i < nb_oargs + nb_iargs + 1; i++) {
+ if (temps[args[i]].state == TCG_TEMP_COPY) {
+ args[i] = find_better_copy(s, args[i]);
+ }
+ }
+ } else {
for (i = def->nb_oargs; i < def->nb_oargs + def->nb_iargs; i++) {
if (temps[args[i]].state == TCG_TEMP_COPY) {
- args[i] = temps[args[i]].val;
+ args[i] = find_better_copy(s, args[i]);
}
}
}
@@ -372,7 +434,10 @@
CASE_OP_32_64(eqv):
CASE_OP_32_64(nand):
CASE_OP_32_64(nor):
- if (temps[args[1]].state == TCG_TEMP_CONST) {
+ /* Prefer the constant in second argument, and then the form
+ op a, a, b, which is better handled on non-RISC hosts. */
+ if (temps[args[1]].state == TCG_TEMP_CONST || (args[0] == args[2]
+ && temps[args[2]].state != TCG_TEMP_CONST)) {
tmp = args[1];
args[1] = args[2];
args[2] = tmp;
@@ -429,7 +494,7 @@
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[1]].val == 0) {
gen_opc_buf[op_index] = op_to_movi(op);
- tcg_opt_gen_movi(gen_args, args[0], 0, nb_temps, nb_globals);
+ tcg_opt_gen_movi(gen_args, args[0], 0);
args += 3;
gen_args += 2;
continue;
@@ -456,14 +521,11 @@
}
if (temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[2]].val == 0) {
- if ((temps[args[0]].state == TCG_TEMP_COPY
- && temps[args[0]].val == args[1])
- || args[0] == args[1]) {
+ if (temps_are_copies(args[0], args[1])) {
gen_opc_buf[op_index] = INDEX_op_nop;
} else {
gen_opc_buf[op_index] = op_to_mov(op);
- tcg_opt_gen_mov(gen_args, args[0], args[1],
- nb_temps, nb_globals);
+ tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
gen_args += 2;
}
args += 3;
@@ -481,7 +543,7 @@
if ((temps[args[2]].state == TCG_TEMP_CONST
&& temps[args[2]].val == 0)) {
gen_opc_buf[op_index] = op_to_movi(op);
- tcg_opt_gen_movi(gen_args, args[0], 0, nb_temps, nb_globals);
+ tcg_opt_gen_movi(gen_args, args[0], 0);
args += 3;
gen_args += 2;
continue;
@@ -495,13 +557,12 @@
switch (op) {
CASE_OP_32_64(or):
CASE_OP_32_64(and):
- if (args[1] == args[2]) {
- if (args[1] == args[0]) {
+ if (temps_are_copies(args[1], args[2])) {
+ if (temps_are_copies(args[0], args[1])) {
gen_opc_buf[op_index] = INDEX_op_nop;
} else {
gen_opc_buf[op_index] = op_to_mov(op);
- tcg_opt_gen_mov(gen_args, args[0], args[1], nb_temps,
- nb_globals);
+ tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
gen_args += 2;
}
args += 3;
@@ -512,21 +573,34 @@
break;
}
+ /* Simplify expression for "op r, a, a => movi r, 0" cases */
+ switch (op) {
+ CASE_OP_32_64(sub):
+ CASE_OP_32_64(xor):
+ if (temps_are_copies(args[1], args[2])) {
+ gen_opc_buf[op_index] = op_to_movi(op);
+ tcg_opt_gen_movi(gen_args, args[0], 0);
+ gen_args += 2;
+ args += 3;
+ continue;
+ }
+ break;
+ default:
+ break;
+ }
+
/* Propagate constants through copy operations and do constant
folding. Constants will be substituted to arguments by register
allocator where needed and possible. Also detect copies. */
switch (op) {
CASE_OP_32_64(mov):
- if ((temps[args[1]].state == TCG_TEMP_COPY
- && temps[args[1]].val == args[0])
- || args[0] == args[1]) {
+ if (temps_are_copies(args[0], args[1])) {
args += 2;
gen_opc_buf[op_index] = INDEX_op_nop;
break;
}
if (temps[args[1]].state != TCG_TEMP_CONST) {
- tcg_opt_gen_mov(gen_args, args[0], args[1],
- nb_temps, nb_globals);
+ tcg_opt_gen_mov(s, gen_args, args[0], args[1]);
gen_args += 2;
args += 2;
break;
@@ -538,7 +612,7 @@
args[1] = temps[args[1]].val;
/* fallthrough */
CASE_OP_32_64(movi):
- tcg_opt_gen_movi(gen_args, args[0], args[1], nb_temps, nb_globals);
+ tcg_opt_gen_movi(gen_args, args[0], args[1]);
gen_args += 2;
args += 2;
break;
@@ -553,9 +627,9 @@
if (temps[args[1]].state == TCG_TEMP_CONST) {
gen_opc_buf[op_index] = op_to_movi(op);
tmp = do_constant_folding(op, temps[args[1]].val, 0);
- tcg_opt_gen_movi(gen_args, args[0], tmp, nb_temps, nb_globals);
+ tcg_opt_gen_movi(gen_args, args[0], tmp);
} else {
- reset_temp(args[0], nb_temps, nb_globals);
+ reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[1];
}
@@ -583,10 +657,10 @@
gen_opc_buf[op_index] = op_to_movi(op);
tmp = do_constant_folding(op, temps[args[1]].val,
temps[args[2]].val);
- tcg_opt_gen_movi(gen_args, args[0], tmp, nb_temps, nb_globals);
+ tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
} else {
- reset_temp(args[0], nb_temps, nb_globals);
+ reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[1];
gen_args[2] = args[2];
@@ -594,16 +668,34 @@
}
args += 3;
break;
- CASE_OP_32_64(setcond):
+ CASE_OP_32_64(deposit):
if (temps[args[1]].state == TCG_TEMP_CONST
&& temps[args[2]].state == TCG_TEMP_CONST) {
gen_opc_buf[op_index] = op_to_movi(op);
- tmp = do_constant_folding_cond(op, temps[args[1]].val,
- temps[args[2]].val, args[3]);
- tcg_opt_gen_movi(gen_args, args[0], tmp, nb_temps, nb_globals);
+ tmp = ((1ull << args[4]) - 1);
+ tmp = (temps[args[1]].val & ~(tmp << args[3]))
+ | ((temps[args[2]].val & tmp) << args[3]);
+ tcg_opt_gen_movi(gen_args, args[0], tmp);
gen_args += 2;
} else {
- reset_temp(args[0], nb_temps, nb_globals);
+ reset_temp(args[0]);
+ gen_args[0] = args[0];
+ gen_args[1] = args[1];
+ gen_args[2] = args[2];
+ gen_args[3] = args[3];
+ gen_args[4] = args[4];
+ gen_args += 5;
+ }
+ args += 5;
+ break;
+ CASE_OP_32_64(setcond):
+ tmp = do_constant_folding_cond(op, args[1], args[2], args[3]);
+ if (tmp != 2) {
+ gen_opc_buf[op_index] = op_to_movi(op);
+ tcg_opt_gen_movi(gen_args, args[0], tmp);
+ gen_args += 2;
+ } else {
+ reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[1];
gen_args[2] = args[2];
@@ -613,10 +705,9 @@
args += 4;
break;
CASE_OP_32_64(brcond):
- if (temps[args[0]].state == TCG_TEMP_CONST
- && temps[args[1]].state == TCG_TEMP_CONST) {
- if (do_constant_folding_cond(op, temps[args[0]].val,
- temps[args[1]].val, args[2])) {
+ tmp = do_constant_folding_cond(op, args[0], args[1], args[2]);
+ if (tmp != 2) {
+ if (tmp) {
memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
gen_opc_buf[op_index] = INDEX_op_br;
gen_args[0] = args[3];
@@ -626,7 +717,7 @@
}
} else {
memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
- reset_temp(args[0], nb_temps, nb_globals);
+ reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[1];
gen_args[2] = args[2];
@@ -636,27 +727,21 @@
args += 4;
break;
CASE_OP_32_64(movcond):
- if (temps[args[1]].state == TCG_TEMP_CONST
- && temps[args[2]].state == TCG_TEMP_CONST) {
- tmp = do_constant_folding_cond(op, temps[args[1]].val,
- temps[args[2]].val, args[5]);
- if (args[0] == args[4-tmp]
- || (temps[args[4-tmp]].state == TCG_TEMP_COPY
- && temps[args[4-tmp]].val == args[0])) {
+ tmp = do_constant_folding_cond(op, args[1], args[2], args[5]);
+ if (tmp != 2) {
+ if (temps_are_copies(args[0], args[4-tmp])) {
gen_opc_buf[op_index] = INDEX_op_nop;
} else if (temps[args[4-tmp]].state == TCG_TEMP_CONST) {
gen_opc_buf[op_index] = op_to_movi(op);
- tcg_opt_gen_movi(gen_args, args[0], temps[args[4-tmp]].val,
- nb_temps, nb_globals);
+ tcg_opt_gen_movi(gen_args, args[0], temps[args[4-tmp]].val);
gen_args += 2;
} else {
gen_opc_buf[op_index] = op_to_mov(op);
- tcg_opt_gen_mov(gen_args, args[0], args[4-tmp],
- nb_temps, nb_globals);
+ tcg_opt_gen_mov(s, gen_args, args[0], args[4-tmp]);
gen_args += 2;
}
} else {
- reset_temp(args[0], nb_temps, nb_globals);
+ reset_temp(args[0]);
gen_args[0] = args[0];
gen_args[1] = args[1];
gen_args[2] = args[2];
@@ -671,11 +756,11 @@
nb_call_args = (args[0] >> 16) + (args[0] & 0xffff);
if (!(args[nb_call_args + 1] & (TCG_CALL_CONST | TCG_CALL_PURE))) {
for (i = 0; i < nb_globals; i++) {
- reset_temp(i, nb_temps, nb_globals);
+ reset_temp(i);
}
}
for (i = 0; i < (args[0] >> 16); i++) {
- reset_temp(args[i + 1], nb_temps, nb_globals);
+ reset_temp(args[i + 1]);
}
i = nb_call_args + 3;
while (i) {
@@ -694,7 +779,7 @@
memset(temps, 0, nb_temps * sizeof(struct tcg_temp_info));
} else {
for (i = 0; i < def->nb_oargs; i++) {
- reset_temp(args[i], nb_temps, nb_globals);
+ reset_temp(args[i]);
}
}
for (i = 0; i < def->nb_args; i++) {
diff --git a/tcg/ppc/tcg-target.c b/tcg/ppc/tcg-target.c
index 26c4b33..90c275d 100644
--- a/tcg/ppc/tcg-target.c
+++ b/tcg/ppc/tcg-target.c
@@ -221,12 +221,6 @@
}
}
-/* maximum number of register used for input function arguments */
-static int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return ARRAY_SIZE (tcg_target_call_iarg_regs);
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
@@ -390,6 +384,7 @@
#define ORC XO31(412)
#define EQV XO31(284)
#define NAND XO31(476)
+#define ISEL XO31( 15)
#define LBZX XO31( 87)
#define LHZX XO31(279)
@@ -1269,6 +1264,72 @@
);
}
+static void tcg_out_movcond (TCGContext *s, TCGCond cond,
+ TCGArg dest,
+ TCGArg c1, TCGArg c2,
+ TCGArg v1, TCGArg v2,
+ int const_c2)
+{
+ tcg_out_cmp (s, cond, c1, c2, const_c2, 7);
+
+ if (1) {
+ /* At least here on 7747A bit twiddling hacks are outperformed
+ by jumpy code (the testing was not scientific) */
+ if (dest == v2) {
+ cond = tcg_invert_cond (cond);
+ v2 = v1;
+ }
+ else {
+ if (dest != v1) {
+ tcg_out_mov (s, TCG_TYPE_I32, dest, v1);
+ }
+ }
+ /* Branch forward over one insn */
+ tcg_out32 (s, tcg_to_bc[cond] | 8);
+ tcg_out_mov (s, TCG_TYPE_I32, dest, v2);
+ }
+ else {
+ /* isel version, "if (1)" above should be replaced once a way
+ to figure out availability of isel on the underlying
+ hardware is found */
+ int tab, bc;
+
+ switch (cond) {
+ case TCG_COND_EQ:
+ tab = TAB (dest, v1, v2);
+ bc = CR_EQ;
+ break;
+ case TCG_COND_NE:
+ tab = TAB (dest, v2, v1);
+ bc = CR_EQ;
+ break;
+ case TCG_COND_LTU:
+ case TCG_COND_LT:
+ tab = TAB (dest, v1, v2);
+ bc = CR_LT;
+ break;
+ case TCG_COND_GEU:
+ case TCG_COND_GE:
+ tab = TAB (dest, v2, v1);
+ bc = CR_LT;
+ break;
+ case TCG_COND_LEU:
+ case TCG_COND_LE:
+ tab = TAB (dest, v2, v1);
+ bc = CR_GT;
+ break;
+ case TCG_COND_GTU:
+ case TCG_COND_GT:
+ tab = TAB (dest, v1, v2);
+ bc = CR_GT;
+ break;
+ default:
+ tcg_abort ();
+ }
+ tcg_out32 (s, ISEL | tab | ((bc + 28) << 6));
+ }
+}
+
static void tcg_out_brcond (TCGContext *s, TCGCond cond,
TCGArg arg1, TCGArg arg2, int const_arg2,
int label_index)
@@ -1826,6 +1887,13 @@
);
break;
+ case INDEX_op_movcond_i32:
+ tcg_out_movcond (s, args[5], args[0],
+ args[1], args[2],
+ args[3], args[4],
+ const_args[2]);
+ break;
+
default:
tcg_dump_ops (s);
tcg_abort ();
@@ -1922,6 +1990,7 @@
{ INDEX_op_ext16u_i32, { "r", "r" } },
{ INDEX_op_deposit_i32, { "r", "0", "r" } },
+ { INDEX_op_movcond_i32, { "r", "r", "ri", "r", "r" } },
{ -1 },
};
diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 177eea1..3259d89 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -92,7 +92,7 @@
#define TCG_TARGET_HAS_nand_i32 1
#define TCG_TARGET_HAS_nor_i32 1
#define TCG_TARGET_HAS_deposit_i32 1
-#define TCG_TARGET_HAS_movcond_i32 0
+#define TCG_TARGET_HAS_movcond_i32 1
#define TCG_AREG0 TCG_REG_R27
diff --git a/tcg/ppc64/tcg-target.c b/tcg/ppc64/tcg-target.c
index 337cd41..19944bc 100644
--- a/tcg/ppc64/tcg-target.c
+++ b/tcg/ppc64/tcg-target.c
@@ -208,12 +208,6 @@
}
}
-/* maximum number of register used for input function arguments */
-static int tcg_target_get_call_iarg_regs_count (int flags)
-{
- return ARRAY_SIZE (tcg_target_call_iarg_regs);
-}
-
/* parse target specific constraints */
static int target_parse_constraint (TCGArgConstraint *ct, const char **pct_str)
{
diff --git a/tcg/s390/tcg-target.c b/tcg/s390/tcg-target.c
index aac11d9..3b90605 100644
--- a/tcg/s390/tcg-target.c
+++ b/tcg/s390/tcg-target.c
@@ -356,11 +356,6 @@
}
}
-static int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return sizeof(tcg_target_call_iarg_regs) / sizeof(int);
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
diff --git a/tcg/sparc/tcg-target.c b/tcg/sparc/tcg-target.c
index 876da4f..8fd7f86 100644
--- a/tcg/sparc/tcg-target.c
+++ b/tcg/sparc/tcg-target.c
@@ -155,12 +155,6 @@
}
}
-/* maximum number of register used for input function arguments */
-static inline int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return 6;
-}
-
/* parse target specific constraints */
static int target_parse_constraint(TCGArgConstraint *ct, const char **pct_str)
{
diff --git a/tcg/tcg.c b/tcg/tcg.c
index 45a26f2..b3c2650 100644
--- a/tcg/tcg.c
+++ b/tcg/tcg.c
@@ -89,7 +89,6 @@
tcg_target_long arg2);
static int tcg_target_const_match(tcg_target_long val,
const TCGArgConstraint *arg_ct);
-static int tcg_target_get_call_iarg_regs_count(int flags);
TCGOpDef tcg_op_defs[] = {
#define DEF(s, oargs, iargs, cargs, flags) { #s, oargs, iargs, cargs, iargs + oargs + cargs, flags },
@@ -937,11 +936,7 @@
args[nb_oargs + i]));
}
}
- } else if (c == INDEX_op_movi_i32
-#if TCG_TARGET_REG_BITS == 64
- || c == INDEX_op_movi_i64
-#endif
- ) {
+ } else if (c == INDEX_op_movi_i32 || c == INDEX_op_movi_i64) {
tcg_target_ulong val;
TCGHelperInfo *th;
@@ -993,14 +988,11 @@
case INDEX_op_brcond_i32:
case INDEX_op_setcond_i32:
case INDEX_op_movcond_i32:
-#if TCG_TARGET_REG_BITS == 32
case INDEX_op_brcond2_i32:
case INDEX_op_setcond2_i32:
-#else
case INDEX_op_brcond_i64:
case INDEX_op_setcond_i64:
case INDEX_op_movcond_i64:
-#endif
if (args[k] < ARRAY_SIZE(cond_name) && cond_name[args[k]]) {
qemu_log(",%s", cond_name[args[k++]]);
} else {
@@ -1861,7 +1853,7 @@
flags = args[nb_oargs + nb_iargs];
- nb_regs = tcg_target_get_call_iarg_regs_count(flags);
+ nb_regs = ARRAY_SIZE(tcg_target_call_iarg_regs);
if (nb_regs > nb_params)
nb_regs = nb_params;
@@ -2103,16 +2095,12 @@
#endif
switch(opc) {
case INDEX_op_mov_i32:
-#if TCG_TARGET_REG_BITS == 64
case INDEX_op_mov_i64:
-#endif
dead_args = s->op_dead_args[op_index];
tcg_reg_alloc_mov(s, def, args, dead_args);
break;
case INDEX_op_movi_i32:
-#if TCG_TARGET_REG_BITS == 64
case INDEX_op_movi_i64:
-#endif
tcg_reg_alloc_movi(s, args);
break;
case INDEX_op_debug_insn_start:
diff --git a/tcg/tci/tcg-target.c b/tcg/tci/tcg-target.c
index 003244c..3f4a24b 100644
--- a/tcg/tci/tcg-target.c
+++ b/tcg/tci/tcg-target.c
@@ -863,12 +863,6 @@
return arg_ct->ct & TCG_CT_CONST;
}
-/* Maximum number of register used for input function arguments. */
-static int tcg_target_get_call_iarg_regs_count(int flags)
-{
- return ARRAY_SIZE(tcg_target_call_iarg_regs);
-}
-
static void tcg_target_init(TCGContext *s)
{
#if defined(CONFIG_DEBUG_TCG_INTERPRETER)
