[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v5 56/81] target/arm: Implement SVE2 saturating multiply (indexed
From: |
Richard Henderson |
Subject: |
[PATCH v5 56/81] target/arm: Implement SVE2 saturating multiply (indexed) |
Date: |
Fri, 16 Apr 2021 14:02:15 -0700 |
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sve.h | 5 +++++
target/arm/sve.decode | 12 ++++++++++++
target/arm/sve_helper.c | 20 ++++++++++++++++++++
target/arm/translate-sve.c | 19 +++++++++++++++----
4 files changed, 52 insertions(+), 4 deletions(-)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 08398800bd..0be0d90bee 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2688,3 +2688,8 @@ DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_s, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_sqdmlsl_idx_d, TCG_CALL_NO_RWG,
void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmull_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 8d2709d3cc..a3b9fb95f9 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -255,6 +255,12 @@
@rrx_2 ........ .. . index:2 rm:3 ...... rn:5 rd:5 &rrx_esz
@rrx_1 ........ .. . index:1 rm:4 ...... rn:5 rd:5 &rrx_esz
+# Two registers and a scalar by N-bit index, alternate
+@rrx_3a ........ .. . .. rm:3 ...... rn:5 rd:5 \
+ &rrx_esz index=%index3_19_11
+@rrx_2a ........ .. . . rm:4 ...... rn:5 rd:5 \
+ &rrx_esz index=%index2_20_11
+
# Three registers and a scalar by N-bit index
@rrxr_3 ........ .. . .. rm:3 ...... rn:5 rd:5 \
&rrxr_esz ra=%reg_movprfx index=%index3_22_19
@@ -817,6 +823,12 @@ SQDMLSLB_zzxw_d 01000100 11 1 ..... 0011.0 ..... .....
@rrxr_2a esz=3
SQDMLSLT_zzxw_s 01000100 10 1 ..... 0011.1 ..... ..... @rrxr_3a esz=2
SQDMLSLT_zzxw_d 01000100 11 1 ..... 0011.1 ..... ..... @rrxr_2a esz=3
+# SVE2 saturating multiply (indexed)
+SQDMULLB_zzx_s 01000100 10 1 ..... 1110.0 ..... ..... @rrx_3a esz=2
+SQDMULLB_zzx_d 01000100 11 1 ..... 1110.0 ..... ..... @rrx_2a esz=3
+SQDMULLT_zzx_s 01000100 10 1 ..... 1110.1 ..... ..... @rrx_3a esz=2
+SQDMULLT_zzx_d 01000100 11 1 ..... 1110.1 ..... ..... @rrx_2a esz=3
+
# SVE2 integer multiply (indexed)
MUL_zzx_h 01000100 0. 1 ..... 111110 ..... ..... @rrx_3 esz=1
MUL_zzx_s 01000100 10 1 ..... 111110 ..... ..... @rrx_2 esz=2
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index c43c38044b..e8a8425522 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1560,6 +1560,26 @@ DO_ZZXW(sve2_sqdmlsl_idx_d, int64_t, int32_t, ,
H1_4, DO_SQDMLSL_D)
#undef DO_ZZXW
+#define DO_ZZX(NAME, TYPEW, TYPEN, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, j, oprsz = simd_oprsz(desc); \
+ intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1) * sizeof(TYPEN); \
+ intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 1, 3) * sizeof(TYPEN); \
+ for (i = 0; i < oprsz; i += 16) { \
+ TYPEW mm = *(TYPEN *)(vm + i + idx); \
+ for (j = 0; j < 16; j += sizeof(TYPEW)) { \
+ TYPEW nn = *(TYPEN *)(vn + HN(i + j + sel)); \
+ *(TYPEW *)(vd + HW(i + j)) = OP(nn, mm); \
+ } \
+ } \
+}
+
+DO_ZZX(sve2_sqdmull_idx_s, int32_t, int16_t, H1_4, H1_2, do_sqdmull_s)
+DO_ZZX(sve2_sqdmull_idx_d, int64_t, int32_t, , H1_4, do_sqdmull_d)
+
+#undef DO_ZZX
+
#define DO_BITPERM(NAME, TYPE, OP) \
void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
{ \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 4c304c0124..d3fcf2e4c1 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3840,8 +3840,8 @@ DO_RRXR(trans_UDOT_zzxw_d, gen_helper_gvec_udot_idx_h)
#undef DO_RRXR
-static bool do_sve2_zzx_ool(DisasContext *s, arg_rrx_esz *a,
- gen_helper_gvec_3 *fn)
+static bool do_sve2_zzx_data(DisasContext *s, arg_rrx_esz *a,
+ gen_helper_gvec_3 *fn, int data)
{
if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
return false;
@@ -3851,14 +3851,14 @@ static bool do_sve2_zzx_ool(DisasContext *s,
arg_rrx_esz *a,
tcg_gen_gvec_3_ool(vec_full_reg_offset(s, a->rd),
vec_full_reg_offset(s, a->rn),
vec_full_reg_offset(s, a->rm),
- vsz, vsz, a->index, fn);
+ vsz, vsz, data, fn);
}
return true;
}
#define DO_SVE2_RRX(NAME, FUNC) \
static bool NAME(DisasContext *s, arg_rrx_esz *a) \
- { return do_sve2_zzx_ool(s, a, FUNC); }
+ { return do_sve2_zzx_data(s, a, FUNC, a->index); }
DO_SVE2_RRX(trans_MUL_zzx_h, gen_helper_gvec_mul_idx_h)
DO_SVE2_RRX(trans_MUL_zzx_s, gen_helper_gvec_mul_idx_s)
@@ -3866,6 +3866,17 @@ DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
#undef DO_SVE2_RRX
+#define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \
+ static bool NAME(DisasContext *s, arg_rrx_esz *a) \
+ { return do_sve2_zzx_data(s, a, FUNC, (a->index << 1) | TOP); }
+
+DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_s, gen_helper_sve2_sqdmull_idx_s, false)
+DO_SVE2_RRX_TB(trans_SQDMULLB_zzx_d, gen_helper_sve2_sqdmull_idx_d, false)
+DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_s, gen_helper_sve2_sqdmull_idx_s, true)
+DO_SVE2_RRX_TB(trans_SQDMULLT_zzx_d, gen_helper_sve2_sqdmull_idx_d, true)
+
+#undef DO_SVE2_RRX_TB
+
static bool do_sve2_zzxz_data(DisasContext *s, arg_rrxr_esz *a,
gen_helper_gvec_4 *fn, int data)
{
--
2.25.1
- [PATCH v5 52/81] target/arm: Implement SVE2 integer multiply (indexed), (continued)
- [PATCH v5 52/81] target/arm: Implement SVE2 integer multiply (indexed), Richard Henderson, 2021/04/16
- [PATCH v5 49/81] target/arm: Pass separate addend to FCMLA helpers, Richard Henderson, 2021/04/16
- [PATCH v5 48/81] target/arm: Pass separate addend to {U, S}DOT helpers, Richard Henderson, 2021/04/16
- [PATCH v5 50/81] target/arm: Split out formats for 2 vectors + 1 index, Richard Henderson, 2021/04/16
- [PATCH v5 51/81] target/arm: Split out formats for 3 vectors + 1 index, Richard Henderson, 2021/04/16
- [PATCH v5 55/81] target/arm: Implement SVE2 saturating multiply-add (indexed), Richard Henderson, 2021/04/16
- [PATCH v5 54/81] target/arm: Implement SVE2 saturating multiply-add high (indexed), Richard Henderson, 2021/04/16
- [PATCH v5 58/81] target/arm: Implement SVE2 saturating multiply high (indexed), Richard Henderson, 2021/04/16
- [PATCH v5 53/81] target/arm: Implement SVE2 integer multiply-add (indexed), Richard Henderson, 2021/04/16
- [PATCH v5 61/81] target/arm: Implement SVE2 crypto unary operations, Richard Henderson, 2021/04/16
- [PATCH v5 56/81] target/arm: Implement SVE2 saturating multiply (indexed),
Richard Henderson <=
- [PATCH v5 62/81] target/arm: Implement SVE2 crypto destructive binary operations, Richard Henderson, 2021/04/16
- [PATCH v5 59/81] target/arm: Implement SVE mixed sign dot product (indexed), Richard Henderson, 2021/04/16
- [PATCH v5 68/81] target/arm: Implement SVE2 FLOGB, Richard Henderson, 2021/04/16
- [PATCH v5 66/81] target/arm: Implement SVE2 FCVTLT, Richard Henderson, 2021/04/16
- [PATCH v5 64/81] target/arm: Implement SVE2 TBL, TBX, Richard Henderson, 2021/04/16
- [PATCH v5 60/81] target/arm: Implement SVE mixed sign dot product, Richard Henderson, 2021/04/16
- [PATCH v5 69/81] target/arm: Share table of sve load functions, Richard Henderson, 2021/04/16
- [PATCH v5 57/81] target/arm: Implement SVE2 signed saturating doubling multiply high, Richard Henderson, 2021/04/16
- [PATCH v5 70/81] target/arm: Implement SVE2 LD1RO, Richard Henderson, 2021/04/16
- [PATCH v5 67/81] target/arm: Implement SVE2 FCVTXNT, FCVTX, Richard Henderson, 2021/04/16