@@ -350,17 +350,14 @@ DEF_HELPER_1(neon_qneg_s8, i32, i32)
DEF_HELPER_1(neon_qneg_s16, i32, i32)
DEF_HELPER_1(neon_qneg_s32, i32, i32)
-DEF_HELPER_2(neon_min_f32, i32, i32, i32)
-DEF_HELPER_2(neon_max_f32, i32, i32, i32)
-DEF_HELPER_2(neon_abd_f32, i32, i32, i32)
-DEF_HELPER_2(neon_add_f32, i32, i32, i32)
-DEF_HELPER_2(neon_sub_f32, i32, i32, i32)
-DEF_HELPER_2(neon_mul_f32, i32, i32, i32)
-DEF_HELPER_2(neon_ceq_f32, i32, i32, i32)
-DEF_HELPER_2(neon_cge_f32, i32, i32, i32)
-DEF_HELPER_2(neon_cgt_f32, i32, i32, i32)
-DEF_HELPER_2(neon_acge_f32, i32, i32, i32)
-DEF_HELPER_2(neon_acgt_f32, i32, i32, i32)
+DEF_HELPER_3(neon_min_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_max_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_abd_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr)
+DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr)
/* iwmmxt_helper.c */
DEF_HELPER_2(iwmmxt_maddsq, i64, i64, i64)
@@ -18,8 +18,6 @@
#define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] = CPSR_Q
-#define NFS (&env->vfp.standard_fp_status)
-
#define NEON_TYPE1(name, type) \
typedef struct \
{ \
@@ -1770,69 +1768,62 @@ uint32_t HELPER(neon_qneg_s32)(uint32_t x)
}
/* NEON Float helpers. */
-uint32_t HELPER(neon_min_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_min_f32)(uint32_t a, uint32_t b, void *fpstp)
{
- return float32_val(float32_min(make_float32(a), make_float32(b), NFS));
+ float_status *fpst = fpstp;
+ return float32_val(float32_min(make_float32(a), make_float32(b), fpst));
}
-uint32_t HELPER(neon_max_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_max_f32)(uint32_t a, uint32_t b, void *fpstp)
{
- return float32_val(float32_max(make_float32(a), make_float32(b), NFS));
+ float_status *fpst = fpstp;
+ return float32_val(float32_max(make_float32(a), make_float32(b), fpst));
}
-uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b, void *fpstp)
{
+ float_status *fpst = fpstp;
float32 f0 = make_float32(a);
float32 f1 = make_float32(b);
- return float32_val(float32_abs(float32_sub(f0, f1, NFS)));
-}
-
-uint32_t HELPER(neon_add_f32)(uint32_t a, uint32_t b)
-{
- return float32_val(float32_add(make_float32(a), make_float32(b), NFS));
-}
-
-uint32_t HELPER(neon_sub_f32)(uint32_t a, uint32_t b)
-{
- return float32_val(float32_sub(make_float32(a), make_float32(b), NFS));
-}
-
-uint32_t HELPER(neon_mul_f32)(uint32_t a, uint32_t b)
-{
- return float32_val(float32_mul(make_float32(a), make_float32(b), NFS));
+ return float32_val(float32_abs(float32_sub(f0, f1, fpst)));
}
/* Floating point comparisons produce an integer result.
* Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do.
* Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires.
*/
-uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b, void *fpstp)
{
- return -float32_eq_quiet(make_float32(a), make_float32(b), NFS);
+ float_status *fpst = fpstp;
+ return -float32_eq_quiet(make_float32(a), make_float32(b), fpst);
}
-uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b, void *fpstp)
{
- return -float32_le(make_float32(b), make_float32(a), NFS);
+ float_status *fpst = fpstp;
+ return -float32_le(make_float32(b), make_float32(a), fpst);
}
-uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b, void *fpstp)
{
- return -float32_lt(make_float32(b), make_float32(a), NFS);
+ float_status *fpst = fpstp;
+ return -float32_lt(make_float32(b), make_float32(a), fpst);
}
-uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b, void *fpstp)
{
+ float_status *fpst = fpstp;
float32 f0 = float32_abs(make_float32(a));
float32 f1 = float32_abs(make_float32(b));
- return -float32_le(f1, f0, NFS);
+ return -float32_le(f1, f0, fpst);
}
-uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b)
+uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, void *fpstp)
{
+ float_status *fpst = fpstp;
float32 f0 = float32_abs(make_float32(a));
float32 f1 = float32_abs(make_float32(b));
- return -float32_lt(f1, f0, NFS);
+ return -float32_lt(f1, f0, fpst);
}
#define ELEM(V, N, SIZE) (((V) >> ((N) * (SIZE))) & ((1ull << (SIZE)) - 1))
@@ -4857,57 +4857,78 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
}
break;
case NEON_3R_FLOAT_ARITH: /* Floating point arithmetic. */
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
switch ((u << 2) | size) {
case 0: /* VADD */
- gen_helper_neon_add_f32(tmp, tmp, tmp2);
+ case 4: /* VPADD */
+ gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
break;
case 2: /* VSUB */
- gen_helper_neon_sub_f32(tmp, tmp, tmp2);
- break;
- case 4: /* VPADD */
- gen_helper_neon_add_f32(tmp, tmp, tmp2);
+ gen_helper_vfp_subs(tmp, tmp, tmp2, fpstatus);
break;
case 6: /* VABD */
- gen_helper_neon_abd_f32(tmp, tmp, tmp2);
+ gen_helper_neon_abd_f32(tmp, tmp, tmp2, fpstatus);
break;
default:
abort();
}
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_3R_FLOAT_MULTIPLY:
- gen_helper_neon_mul_f32(tmp, tmp, tmp2);
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+ gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus);
if (!u) {
tcg_temp_free_i32(tmp2);
tmp2 = neon_load_reg(rd, pass);
if (size == 0) {
- gen_helper_neon_add_f32(tmp, tmp, tmp2);
+ gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
} else {
- gen_helper_neon_sub_f32(tmp, tmp2, tmp);
+ gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus);
}
}
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_3R_FLOAT_CMP:
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
if (!u) {
- gen_helper_neon_ceq_f32(tmp, tmp, tmp2);
+ gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus);
} else {
- if (size == 0)
- gen_helper_neon_cge_f32(tmp, tmp, tmp2);
- else
- gen_helper_neon_cgt_f32(tmp, tmp, tmp2);
+ if (size == 0) {
+ gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus);
+ } else {
+ gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus);
+ }
}
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_3R_FLOAT_ACMP:
- if (size == 0)
- gen_helper_neon_acge_f32(tmp, tmp, tmp2);
- else
- gen_helper_neon_acgt_f32(tmp, tmp, tmp2);
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+ if (size == 0) {
+ gen_helper_neon_acge_f32(tmp, tmp, tmp2, fpstatus);
+ } else {
+ gen_helper_neon_acgt_f32(tmp, tmp, tmp2, fpstatus);
+ }
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_3R_FLOAT_MINMAX:
- if (size == 0)
- gen_helper_neon_max_f32(tmp, tmp, tmp2);
- else
- gen_helper_neon_min_f32(tmp, tmp, tmp2);
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+ if (size == 0) {
+ gen_helper_neon_max_f32(tmp, tmp, tmp2, fpstatus);
+ } else {
+ gen_helper_neon_min_f32(tmp, tmp, tmp2, fpstatus);
+ }
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_3R_VRECPS_VRSQRTS:
if (size == 0)
gen_helper_recps_f32(tmp, tmp, tmp2, cpu_env);
@@ -5606,7 +5627,9 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
gen_helper_neon_qrdmulh_s32(tmp, tmp, tmp2);
}
} else if (op & 1) {
- gen_helper_neon_mul_f32(tmp, tmp, tmp2);
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+ gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus);
+ tcg_temp_free_ptr(fpstatus);
} else {
switch (size) {
case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break;
@@ -5624,14 +5647,22 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
gen_neon_add(size, tmp, tmp2);
break;
case 1:
- gen_helper_neon_add_f32(tmp, tmp, tmp2);
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+ gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case 4:
gen_neon_rsb(size, tmp, tmp2);
break;
case 5:
- gen_helper_neon_sub_f32(tmp, tmp2, tmp);
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
+ gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
default:
abort();
}
@@ -6029,30 +6060,50 @@ static int disas_neon_data_insn(CPUState * env, DisasContext *s, uint32_t insn)
tcg_temp_free(tmp2);
break;
case NEON_2RM_VCGT0_F:
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
tmp2 = tcg_const_i32(0);
- gen_helper_neon_cgt_f32(tmp, tmp, tmp2);
+ gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus);
tcg_temp_free(tmp2);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_2RM_VCGE0_F:
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
tmp2 = tcg_const_i32(0);
- gen_helper_neon_cge_f32(tmp, tmp, tmp2);
+ gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus);
tcg_temp_free(tmp2);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_2RM_VCEQ0_F:
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
tmp2 = tcg_const_i32(0);
- gen_helper_neon_ceq_f32(tmp, tmp, tmp2);
+ gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus);
tcg_temp_free(tmp2);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_2RM_VCLE0_F:
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
tmp2 = tcg_const_i32(0);
- gen_helper_neon_cge_f32(tmp, tmp2, tmp);
+ gen_helper_neon_cge_f32(tmp, tmp2, tmp, fpstatus);
tcg_temp_free(tmp2);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_2RM_VCLT0_F:
+ {
+ TCGv_ptr fpstatus = get_fpstatus_ptr(1);
tmp2 = tcg_const_i32(0);
- gen_helper_neon_cgt_f32(tmp, tmp2, tmp);
+ gen_helper_neon_cgt_f32(tmp, tmp2, tmp, fpstatus);
tcg_temp_free(tmp2);
+ tcg_temp_free_ptr(fpstatus);
break;
+ }
case NEON_2RM_VABS_F:
gen_vfp_abs(0);
break;
Make the Neon helpers for various floating point operations take an explicit pointer to the float_status they use, so they don't rely on the global environment pointer any more. This also allows us to drop the mul/sub/add helpers completely and just use the vfp versions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target-arm/helper.h | 19 +++----- target-arm/neon_helper.c | 57 ++++++++++-------------- target-arm/translate.c | 111 +++++++++++++++++++++++++++++++++------------ 3 files changed, 113 insertions(+), 74 deletions(-)