aboutsummaryrefslogtreecommitdiff
path: root/target/openrisc
diff options
context:
space:
mode:
authorRichard Henderson <rth@twiddle.net>2016-04-05 19:43:40 -0700
committerRichard Henderson <rth@twiddle.net>2017-02-14 08:15:00 +1100
commit6597c28d618a3d16d468770b7c30a0237a8c8ea9 (patch)
tree45f88af4cf649ce36afadd421965ae88d5173ea6 /target/openrisc
parenta01deb36a685365b4a3117112da3cc4f0f79e955 (diff)
downloadqemu-6597c28d618a3d16d468770b7c30a0237a8c8ea9.zip
qemu-6597c28d618a3d16d468770b7c30a0237a8c8ea9.tar.gz
qemu-6597c28d618a3d16d468770b7c30a0237a8c8ea9.tar.bz2
target/openrisc: Optimize for r0 being zero
The HW does not special-case r0, but the ABI specifies that r0 should contain 0. If we expose this fact to the optimizer, we can simplify a lot of the generated code. We must of course verify that r0==0, but that is trivial to do with a TB flag. Signed-off-by: Richard Henderson <rth@twiddle.net>
Diffstat (limited to 'target/openrisc')
-rw-r--r--target/openrisc/cpu.h5
-rw-r--r--target/openrisc/exception_helper.c1
-rw-r--r--target/openrisc/translate.c83
3 files changed, 66 insertions, 23 deletions
diff --git a/target/openrisc/cpu.h b/target/openrisc/cpu.h
index 50a36ba..418a0e6 100644
--- a/target/openrisc/cpu.h
+++ b/target/openrisc/cpu.h
@@ -389,6 +389,7 @@ int cpu_openrisc_get_phys_data(OpenRISCCPU *cpu,
#include "exec/cpu-all.h"
#define TB_FLAGS_DFLAG 1
+#define TB_FLAGS_R0_0 2
#define TB_FLAGS_OVE SR_OVE
static inline void cpu_get_tb_cpu_state(CPUOpenRISCState *env,
@@ -397,7 +398,9 @@ static inline void cpu_get_tb_cpu_state(CPUOpenRISCState *env,
{
*pc = env->pc;
*cs_base = 0;
- *flags = env->dflag | (env->sr & SR_OVE);
+ *flags = (env->dflag
+ | (env->gpr[0] == 0 ? TB_FLAGS_R0_0 : 0)
+ | (env->sr & SR_OVE));
}
static inline int cpu_mmu_index(CPUOpenRISCState *env, bool ifetch)
diff --git a/target/openrisc/exception_helper.c b/target/openrisc/exception_helper.c
index 1536053..a8a5f69 100644
--- a/target/openrisc/exception_helper.c
+++ b/target/openrisc/exception_helper.c
@@ -19,6 +19,7 @@
#include "qemu/osdep.h"
#include "cpu.h"
+#include "exec/exec-all.h"
#include "exec/helper-proto.h"
#include "exec/exec-all.h"
#include "exception.h"
diff --git a/target/openrisc/translate.c b/target/openrisc/translate.c
index 313dae2..7c4cbf2 100644
--- a/target/openrisc/translate.c
+++ b/target/openrisc/translate.c
@@ -50,6 +50,7 @@ typedef struct DisasContext {
static TCGv_env cpu_env;
static TCGv cpu_sr;
static TCGv cpu_R[32];
+static TCGv cpu_R0;
static TCGv cpu_pc;
static TCGv jmp_pc; /* l.jr/l.jalr temp pc */
static TCGv cpu_ppc;
@@ -109,6 +110,7 @@ void openrisc_translate_init(void)
offsetof(CPUOpenRISCState, gpr[i]),
regnames[i]);
}
+ cpu_R0 = cpu_R[0];
}
static void gen_exception(DisasContext *dc, unsigned int excp)
@@ -149,6 +151,15 @@ static void check_ov64s(DisasContext *dc)
}
#endif*/
+/* We're about to write to REG. On the off-chance that the user is
+ writing to R0, re-instate the architectural register. */
+#define check_r0_write(reg) \
+ do { \
+ if (unlikely(reg == 0)) { \
+ cpu_R[0] = cpu_R0; \
+ } \
+ } while (0)
+
static inline bool use_goto_tb(DisasContext *dc, target_ulong dest)
{
if (unlikely(dc->singlestep_enabled)) {
@@ -496,7 +507,7 @@ static void gen_lwa(DisasContext *dc, TCGv rd, TCGv ra, int32_t ofs)
tcg_temp_free(ea);
}
-static void gen_swa(DisasContext *dc, TCGv rb, TCGv ra, int32_t ofs)
+static void gen_swa(DisasContext *dc, int b, TCGv ra, int32_t ofs)
{
TCGv ea, val;
TCGLabel *lab_fail, *lab_done;
@@ -504,6 +515,12 @@ static void gen_swa(DisasContext *dc, TCGv rb, TCGv ra, int32_t ofs)
ea = tcg_temp_new();
tcg_gen_addi_tl(ea, ra, ofs);
+ /* For TB_FLAGS_R0_0, the branch below invalidates the temporary assigned
+ to cpu_R[0]. Since l.swa is quite often immediately followed by a
+ branch, don't bother reallocating; finish the TB using the "real" R0.
+ This also takes care of RB input across the branch. */
+ cpu_R[0] = cpu_R0;
+
lab_fail = gen_new_label();
lab_done = gen_new_label();
tcg_gen_brcond_tl(TCG_COND_NE, ea, cpu_lock_addr, lab_fail);
@@ -511,7 +528,7 @@ static void gen_swa(DisasContext *dc, TCGv rb, TCGv ra, int32_t ofs)
val = tcg_temp_new();
tcg_gen_atomic_cmpxchg_tl(val, cpu_lock_addr, cpu_lock_value,
- rb, dc->mem_idx, MO_TEUL);
+ cpu_R[b], dc->mem_idx, MO_TEUL);
tcg_gen_setcond_tl(TCG_COND_EQ, cpu_sr_f, val, cpu_lock_value);
tcg_temp_free(val);
@@ -781,6 +798,7 @@ static void dec_misc(DisasContext *dc, uint32_t insn)
case 0x1b: /* l.lwa */
LOG_DIS("l.lwa r%d, r%d, %d\n", rd, ra, I16);
+ check_r0_write(rd);
gen_lwa(dc, cpu_R[rd], cpu_R[ra], I16);
break;
@@ -856,16 +874,16 @@ static void dec_misc(DisasContext *dc, uint32_t insn)
goto do_load;
do_load:
- {
- TCGv t0 = tcg_temp_new();
- tcg_gen_addi_tl(t0, cpu_R[ra], I16);
- tcg_gen_qemu_ld_tl(cpu_R[rd], t0, dc->mem_idx, mop);
- tcg_temp_free(t0);
- }
+ check_r0_write(rd);
+ t0 = tcg_temp_new();
+ tcg_gen_addi_tl(t0, cpu_R[ra], I16);
+ tcg_gen_qemu_ld_tl(cpu_R[rd], t0, dc->mem_idx, mop);
+ tcg_temp_free(t0);
break;
case 0x27: /* l.addi */
LOG_DIS("l.addi r%d, r%d, %d\n", rd, ra, I16);
+ check_r0_write(rd);
t0 = tcg_const_tl(I16);
gen_add(dc, cpu_R[rd], cpu_R[ra], t0);
tcg_temp_free(t0);
@@ -873,6 +891,7 @@ static void dec_misc(DisasContext *dc, uint32_t insn)
case 0x28: /* l.addic */
LOG_DIS("l.addic r%d, r%d, %d\n", rd, ra, I16);
+ check_r0_write(rd);
t0 = tcg_const_tl(I16);
gen_addc(dc, cpu_R[rd], cpu_R[ra], t0);
tcg_temp_free(t0);
@@ -880,21 +899,25 @@ static void dec_misc(DisasContext *dc, uint32_t insn)
case 0x29: /* l.andi */
LOG_DIS("l.andi r%d, r%d, %d\n", rd, ra, K16);
+ check_r0_write(rd);
tcg_gen_andi_tl(cpu_R[rd], cpu_R[ra], K16);
break;
case 0x2a: /* l.ori */
LOG_DIS("l.ori r%d, r%d, %d\n", rd, ra, K16);
+ check_r0_write(rd);
tcg_gen_ori_tl(cpu_R[rd], cpu_R[ra], K16);
break;
case 0x2b: /* l.xori */
LOG_DIS("l.xori r%d, r%d, %d\n", rd, ra, I16);
+ check_r0_write(rd);
tcg_gen_xori_tl(cpu_R[rd], cpu_R[ra], I16);
break;
case 0x2c: /* l.muli */
LOG_DIS("l.muli r%d, r%d, %d\n", rd, ra, I16);
+ check_r0_write(rd);
t0 = tcg_const_tl(I16);
gen_mul(dc, cpu_R[rd], cpu_R[ra], t0);
tcg_temp_free(t0);
@@ -902,6 +925,7 @@ static void dec_misc(DisasContext *dc, uint32_t insn)
case 0x2d: /* l.mfspr */
LOG_DIS("l.mfspr r%d, r%d, %d\n", rd, ra, K16);
+ check_r0_write(rd);
{
#if defined(CONFIG_USER_ONLY)
return;
@@ -936,7 +960,7 @@ static void dec_misc(DisasContext *dc, uint32_t insn)
case 0x33: /* l.swa */
LOG_DIS("l.swa r%d, r%d, %d\n", ra, rb, I5_11);
- gen_swa(dc, cpu_R[rb], cpu_R[ra], I5_11);
+ gen_swa(dc, rb, cpu_R[ra], I5_11);
break;
/* not used yet, open it when we need or64. */
@@ -1023,6 +1047,7 @@ static void dec_logic(DisasContext *dc, uint32_t insn)
L6 = extract32(insn, 0, 6);
S6 = L6 & (TARGET_LONG_BITS - 1);
+ check_r0_write(rd);
switch (op0) {
case 0x00: /* l.slli */
LOG_DIS("l.slli r%d, r%d, %d\n", rd, ra, L6);
@@ -1059,6 +1084,7 @@ static void dec_M(DisasContext *dc, uint32_t insn)
rd = extract32(insn, 21, 5);
K16 = extract32(insn, 0, 16);
+ check_r0_write(rd);
switch (op0) {
case 0x0: /* l.movhi */
LOG_DIS("l.movhi r%d, %d\n", rd, K16);
@@ -1266,47 +1292,49 @@ static void dec_float(DisasContext *dc, uint32_t insn)
switch (op0) {
case 0x00: /* lf.add.s */
LOG_DIS("lf.add.s r%d, r%d, r%d\n", rd, ra, rb);
+ check_r0_write(rd);
gen_helper_float_add_s(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x01: /* lf.sub.s */
LOG_DIS("lf.sub.s r%d, r%d, r%d\n", rd, ra, rb);
+ check_r0_write(rd);
gen_helper_float_sub_s(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
-
case 0x02: /* lf.mul.s */
LOG_DIS("lf.mul.s r%d, r%d, r%d\n", rd, ra, rb);
- if (ra != 0 && rb != 0) {
- gen_helper_float_mul_s(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
- } else {
- tcg_gen_ori_tl(fpcsr, fpcsr, FPCSR_ZF);
- tcg_gen_movi_i32(cpu_R[rd], 0x0);
- }
+ check_r0_write(rd);
+ gen_helper_float_mul_s(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x03: /* lf.div.s */
LOG_DIS("lf.div.s r%d, r%d, r%d\n", rd, ra, rb);
+ check_r0_write(rd);
gen_helper_float_div_s(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x04: /* lf.itof.s */
LOG_DIS("lf.itof r%d, r%d\n", rd, ra);
+ check_r0_write(rd);
gen_helper_itofs(cpu_R[rd], cpu_env, cpu_R[ra]);
break;
case 0x05: /* lf.ftoi.s */
LOG_DIS("lf.ftoi r%d, r%d\n", rd, ra);
+ check_r0_write(rd);
gen_helper_ftois(cpu_R[rd], cpu_env, cpu_R[ra]);
break;
case 0x06: /* lf.rem.s */
LOG_DIS("lf.rem.s r%d, r%d, r%d\n", rd, ra, rb);
+ check_r0_write(rd);
gen_helper_float_rem_s(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x07: /* lf.madd.s */
LOG_DIS("lf.madd.s r%d, r%d, r%d\n", rd, ra, rb);
+ check_r0_write(rd);
gen_helper_float_madd_s(cpu_R[rd], cpu_env, cpu_R[rd],
cpu_R[ra], cpu_R[rb]);
break;
@@ -1346,53 +1374,56 @@ static void dec_float(DisasContext *dc, uint32_t insn)
case 0x10: lf.add.d
LOG_DIS("lf.add.d r%d, r%d, r%d\n", rd, ra, rb);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_float_add_d(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x11: lf.sub.d
LOG_DIS("lf.sub.d r%d, r%d, r%d\n", rd, ra, rb);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_float_sub_d(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x12: lf.mul.d
LOG_DIS("lf.mul.d r%d, r%d, r%d\n", rd, ra, rb);
check_of64s(dc);
- if (ra != 0 && rb != 0) {
- gen_helper_float_mul_d(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
- } else {
- tcg_gen_ori_tl(fpcsr, fpcsr, FPCSR_ZF);
- tcg_gen_movi_i64(cpu_R[rd], 0x0);
- }
+ check_r0_write(rd);
+ gen_helper_float_mul_d(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x13: lf.div.d
LOG_DIS("lf.div.d r%d, r%d, r%d\n", rd, ra, rb);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_float_div_d(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x14: lf.itof.d
LOG_DIS("lf.itof r%d, r%d\n", rd, ra);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_itofd(cpu_R[rd], cpu_env, cpu_R[ra]);
break;
case 0x15: lf.ftoi.d
LOG_DIS("lf.ftoi r%d, r%d\n", rd, ra);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_ftoid(cpu_R[rd], cpu_env, cpu_R[ra]);
break;
case 0x16: lf.rem.d
LOG_DIS("lf.rem.d r%d, r%d, r%d\n", rd, ra, rb);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_float_rem_d(cpu_R[rd], cpu_env, cpu_R[ra], cpu_R[rb]);
break;
case 0x17: lf.madd.d
LOG_DIS("lf.madd.d r%d, r%d, r%d\n", rd, ra, rb);
check_of64s(dc);
+ check_r0_write(rd);
gen_helper_float_madd_d(cpu_R[rd], cpu_env, cpu_R[rd],
cpu_R[ra], cpu_R[rb]);
break;
@@ -1526,6 +1557,14 @@ void gen_intermediate_code(CPUOpenRISCState *env, struct TranslationBlock *tb)
gen_tb_start(tb);
+ /* Allow the TCG optimizer to see that R0 == 0,
+ when it's true, which is the common case. */
+ if (dc->tb_flags & TB_FLAGS_R0_0) {
+ cpu_R[0] = tcg_const_tl(0);
+ } else {
+ cpu_R[0] = cpu_R0;
+ }
+
do {
tcg_gen_insn_start(dc->pc, (dc->delayed_branch ? 1 : 0)
| (num_insns ? 2 : 0));