@@ -616,16 +616,16 @@ DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlah, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlah_idx, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlas, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
-DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG,
- void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
@@ -703,6 +703,22 @@ static void gen_gvec_op4_ool(DisasContext *s, bool is_q, int rd, int rn,
is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
}
+/* Expand a 4-operand + fpstatus pointer + simd data value operation using
+ * an out-of-line helper.
+ */
+static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn,
+ int rm, int ra, bool is_fp16, int data,
+ gen_helper_gvec_4_ptr *fn)
+{
+ TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR);
+ tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd),
+ vec_full_reg_offset(s, rn),
+ vec_full_reg_offset(s, rm),
+ vec_full_reg_offset(s, ra), fpst,
+ is_q ? 16 : 8, vec_full_reg_size(s), data, fn);
+ tcg_temp_free_ptr(fpst);
+}
+
/* Set ZF and NF based on a 64 bit result. This is alas fiddlier
* than the 32 bit equivalent.
*/
@@ -12224,15 +12240,15 @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn)
rot = extract32(opcode, 0, 2);
switch (size) {
case 1:
- gen_gvec_op3_fpst(s, is_q, rd, rn, rm, true, rot,
+ gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, true, rot,
gen_helper_gvec_fcmlah);
break;
case 2:
- gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot,
+ gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot,
gen_helper_gvec_fcmlas);
break;
case 3:
- gen_gvec_op3_fpst(s, is_q, rd, rn, rm, false, rot,
+ gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot,
gen_helper_gvec_fcmlad);
break;
default:
@@ -13483,9 +13499,10 @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn)
{
int rot = extract32(insn, 13, 2);
int data = (index << 2) | rot;
- tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
+ tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd),
vec_full_reg_offset(s, rn),
- vec_full_reg_offset(s, rm), fpst,
+ vec_full_reg_offset(s, rm),
+ vec_full_reg_offset(s, rd), fpst,
is_q ? 16 : 8, vec_full_reg_size(s), data,
size == MO_64
? gen_helper_gvec_fcmlas_idx
@@ -4387,7 +4387,7 @@ static bool trans_FCMLA_zpzzz(DisasContext *s, arg_FCMLA_zpzzz *a)
static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a)
{
- static gen_helper_gvec_3_ptr * const fns[2] = {
+ static gen_helper_gvec_4_ptr * const fns[2] = {
gen_helper_gvec_fcmlah_idx,
gen_helper_gvec_fcmlas_idx,
};
@@ -4397,9 +4397,10 @@ static bool trans_FCMLA_zzxz(DisasContext *s, arg_FCMLA_zzxz *a)
if (sve_access_check(s)) {
unsigned vsz = vec_full_reg_size(s);
TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR);
- tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd),
+ tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
vec_full_reg_offset(s, a->rn),
vec_full_reg_offset(s, a->rm),
+ vec_full_reg_offset(s, a->ra),
status, vsz, vsz,
a->index * 4 + a->rot,
fns[a->esz - 1]);
@@ -657,13 +657,11 @@ void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm,
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, void *va,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
- float16 *d = vd;
- float16 *n = vn;
- float16 *m = vm;
+ float16 *d = vd, *n = vn, *m = vm, *a = va;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -680,19 +678,17 @@ void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm,
float16 e4 = e2;
float16 e3 = m[H2(i + 1 - flip)] ^ neg_imag;
- d[H2(i)] = float16_muladd(e2, e1, d[H2(i)], 0, fpst);
- d[H2(i + 1)] = float16_muladd(e4, e3, d[H2(i + 1)], 0, fpst);
+ d[H2(i)] = float16_muladd(e2, e1, a[H2(i)], 0, fpst);
+ d[H2(i + 1)] = float16_muladd(e4, e3, a[H2(i + 1)], 0, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
- float16 *d = vd;
- float16 *n = vn;
- float16 *m = vm;
+ float16 *d = vd, *n = vn, *m = vm, *a = va;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -716,20 +712,18 @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm,
float16 e2 = n[H2(j + flip)];
float16 e4 = e2;
- d[H2(j)] = float16_muladd(e2, e1, d[H2(j)], 0, fpst);
- d[H2(j + 1)] = float16_muladd(e4, e3, d[H2(j + 1)], 0, fpst);
+ d[H2(j)] = float16_muladd(e2, e1, a[H2(j)], 0, fpst);
+ d[H2(j + 1)] = float16_muladd(e4, e3, a[H2(j + 1)], 0, fpst);
}
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, void *va,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
- float32 *d = vd;
- float32 *n = vn;
- float32 *m = vm;
+ float32 *d = vd, *n = vn, *m = vm, *a = va;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -746,19 +740,17 @@ void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm,
float32 e4 = e2;
float32 e3 = m[H4(i + 1 - flip)] ^ neg_imag;
- d[H4(i)] = float32_muladd(e2, e1, d[H4(i)], 0, fpst);
- d[H4(i + 1)] = float32_muladd(e4, e3, d[H4(i + 1)], 0, fpst);
+ d[H4(i)] = float32_muladd(e2, e1, a[H4(i)], 0, fpst);
+ d[H4(i + 1)] = float32_muladd(e4, e3, a[H4(i + 1)], 0, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
- float32 *d = vd;
- float32 *n = vn;
- float32 *m = vm;
+ float32 *d = vd, *n = vn, *m = vm, *a = va;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -782,20 +774,18 @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm,
float32 e2 = n[H4(j + flip)];
float32 e4 = e2;
- d[H4(j)] = float32_muladd(e2, e1, d[H4(j)], 0, fpst);
- d[H4(j + 1)] = float32_muladd(e4, e3, d[H4(j + 1)], 0, fpst);
+ d[H4(j)] = float32_muladd(e2, e1, a[H4(j)], 0, fpst);
+ d[H4(j + 1)] = float32_muladd(e4, e3, a[H4(j + 1)], 0, fpst);
}
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
-void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
+void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, void *va,
void *vfpst, uint32_t desc)
{
uintptr_t opr_sz = simd_oprsz(desc);
- float64 *d = vd;
- float64 *n = vn;
- float64 *m = vm;
+ float64 *d = vd, *n = vn, *m = vm, *a = va;
float_status *fpst = vfpst;
intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1);
uint64_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1);
@@ -812,8 +802,8 @@ void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm,
float64 e4 = e2;
float64 e3 = m[i + 1 - flip] ^ neg_imag;
- d[i] = float64_muladd(e2, e1, d[i], 0, fpst);
- d[i + 1] = float64_muladd(e4, e3, d[i + 1], 0, fpst);
+ d[i] = float64_muladd(e2, e1, a[i], 0, fpst);
+ d[i + 1] = float64_muladd(e4, e3, a[i + 1], 0, fpst);
}
clear_tail(d, opr_sz, simd_maxsz(desc));
}
@@ -165,7 +165,7 @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
{
int opr_sz;
TCGv_ptr fpst;
- gen_helper_gvec_3_ptr *fn_gvec_ptr;
+ gen_helper_gvec_4_ptr *fn_gvec_ptr;
if (!dc_isar_feature(aa32_vcma, s)
|| (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s))) {
@@ -190,9 +190,10 @@ static bool trans_VCMLA(DisasContext *s, arg_VCMLA *a)
fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
fn_gvec_ptr = (a->size == MO_16) ?
gen_helper_gvec_fcmlah : gen_helper_gvec_fcmlas;
- tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
+ tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd),
vfp_reg_offset(1, a->vn),
vfp_reg_offset(1, a->vm),
+ vfp_reg_offset(1, a->vd),
fpst, opr_sz, opr_sz, a->rot,
fn_gvec_ptr);
tcg_temp_free_ptr(fpst);
@@ -303,7 +304,7 @@ static bool trans_VFML(DisasContext *s, arg_VFML *a)
static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
{
- gen_helper_gvec_3_ptr *fn_gvec_ptr;
+ gen_helper_gvec_4_ptr *fn_gvec_ptr;
int opr_sz;
TCGv_ptr fpst;
@@ -332,9 +333,10 @@ static bool trans_VCMLA_scalar(DisasContext *s, arg_VCMLA_scalar *a)
gen_helper_gvec_fcmlah_idx : gen_helper_gvec_fcmlas_idx;
opr_sz = (1 + a->q) * 8;
fpst = fpstatus_ptr(a->size == MO_16 ? FPST_STD_F16 : FPST_STD);
- tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd),
+ tcg_gen_gvec_4_ptr(vfp_reg_offset(1, a->vd),
vfp_reg_offset(1, a->vn),
vfp_reg_offset(1, a->vm),
+ vfp_reg_offset(1, a->vd),
fpst, opr_sz, opr_sz,
(a->index << 2) | a->rot, fn_gvec_ptr);
tcg_temp_free_ptr(fpst);
For SVE, we potentially have a 4th argument coming from the movprfx instruction. Currently we do not optimize movprfx, so the problem is not visible. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper.h | 20 ++++++------- target/arm/translate-a64.c | 27 ++++++++++++++---- target/arm/translate-sve.c | 5 ++-- target/arm/vec_helper.c | 50 +++++++++++++-------------------- target/arm/translate-neon.c.inc | 10 ++++--- 5 files changed, 61 insertions(+), 51 deletions(-)