[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v3 57/81] target/arm: Implement SVE2 saturating multiply-add high
From: |
Richard Henderson |
Subject: |
[PATCH v3 57/81] target/arm: Implement SVE2 saturating multiply-add high (indexed) |
Date: |
Fri, 18 Sep 2020 11:37:27 -0700 |
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper-sve.h | 14 +++++++++++++
target/arm/sve.decode | 8 ++++++++
target/arm/sve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 8 ++++++++
4 files changed, 70 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 2c6d3431ec..4ff7298f67 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2665,3 +2665,17 @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d,
TCG_CALL_NO_RWG,
DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr,
i32)
DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr,
i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_sqrdmlsh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 467a93052f..5fc76b7fc3 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -793,6 +793,14 @@ MLS_zzxz_h 01000100 .. 1 ..... 000011 ..... .....
@rrxr_h
MLS_zzxz_s 01000100 .. 1 ..... 000011 ..... ..... @rrxr_s
MLS_zzxz_d 01000100 .. 1 ..... 000011 ..... ..... @rrxr_d
+# SVE2 saturating multiply-add high (indexed)
+SQRDMLAH_zzxz_h 01000100 .. 1 ..... 000100 ..... ..... @rrxr_h
+SQRDMLAH_zzxz_s 01000100 .. 1 ..... 000100 ..... ..... @rrxr_s
+SQRDMLAH_zzxz_d 01000100 .. 1 ..... 000100 ..... ..... @rrxr_d
+SQRDMLSH_zzxz_h 01000100 .. 1 ..... 000101 ..... ..... @rrxr_h
+SQRDMLSH_zzxz_s 01000100 .. 1 ..... 000101 ..... ..... @rrxr_s
+SQRDMLSH_zzxz_d 01000100 .. 1 ..... 000101 ..... ..... @rrxr_d
+
# SVE2 integer multiply (indexed)
MUL_zzx_h 01000100 .. 1 ..... 111110 ..... ..... @rrx_h
MUL_zzx_s 01000100 .. 1 ..... 111110 ..... ..... @rrx_s
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index aaf336118b..1facec8ce0 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1487,9 +1487,49 @@ DO_CMLA(sve2_sqrdcmlah_zzzz_h, int16_t, H2,
DO_SQRDMLAH_H)
DO_CMLA(sve2_sqrdcmlah_zzzz_s, int32_t, H4, DO_SQRDMLAH_S)
DO_CMLA(sve2_sqrdcmlah_zzzz_d, int64_t, , DO_SQRDMLAH_D)
+#undef DO_SQRDMLAH_B
+#undef DO_SQRDMLAH_H
+#undef DO_SQRDMLAH_S
+#undef DO_SQRDMLAH_D
#undef do_cmla
#undef DO_CMLA
+#define DO_ZZXZ(NAME, TYPE, H, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \
+{ \
+ intptr_t oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \
+ intptr_t i, j, idx = simd_data(desc); \
+ TYPE *d = vd, *a = va, *n = vn, *m = (TYPE *)vm + H(idx); \
+ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \
+ TYPE mm = m[i]; \
+ for (j = 0; j < segment; j++) { \
+ d[i + j] = OP(n[i + j], mm, a[i + j]); \
+ } \
+ } \
+}
+
+#define DO_SQRDMLAH_H(N, M, A) \
+ ({ uint32_t discard; do_sqrdmlah_h(N, M, A, false, true, &discard); })
+#define DO_SQRDMLAH_S(N, M, A) \
+ ({ uint32_t discard; do_sqrdmlah_s(N, M, A, false, true, &discard); })
+#define DO_SQRDMLAH_D(N, M, A) do_sqrdmlah_d(N, M, A, false, true)
+
+DO_ZZXZ(sve2_sqrdmlah_idx_h, int16_t, H2, DO_SQRDMLAH_H)
+DO_ZZXZ(sve2_sqrdmlah_idx_s, int32_t, H4, DO_SQRDMLAH_S)
+DO_ZZXZ(sve2_sqrdmlah_idx_d, int64_t, , DO_SQRDMLAH_D)
+
+#define DO_SQRDMLSH_H(N, M, A) \
+ ({ uint32_t discard; do_sqrdmlah_h(N, M, A, true, true, &discard); })
+#define DO_SQRDMLSH_S(N, M, A) \
+ ({ uint32_t discard; do_sqrdmlah_s(N, M, A, true, true, &discard); })
+#define DO_SQRDMLSH_D(N, M, A) do_sqrdmlah_d(N, M, A, true, true)
+
+DO_ZZXZ(sve2_sqrdmlsh_idx_h, int16_t, H2, DO_SQRDMLSH_H)
+DO_ZZXZ(sve2_sqrdmlsh_idx_s, int32_t, H4, DO_SQRDMLSH_S)
+DO_ZZXZ(sve2_sqrdmlsh_idx_d, int64_t, , DO_SQRDMLSH_D)
+
+#undef DO_ZZXZ
+
#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 a6235d78d5..1dd03ae21e 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3891,6 +3891,14 @@ DO_SVE2_RRXR(trans_MLS_zzxz_h, gen_helper_gvec_mls_idx_h)
DO_SVE2_RRXR(trans_MLS_zzxz_s, gen_helper_gvec_mls_idx_s)
DO_SVE2_RRXR(trans_MLS_zzxz_d, gen_helper_gvec_mls_idx_d)
+DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_h, gen_helper_sve2_sqrdmlah_idx_h)
+DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_s, gen_helper_sve2_sqrdmlah_idx_s)
+DO_SVE2_RRXR(trans_SQRDMLAH_zzxz_d, gen_helper_sve2_sqrdmlah_idx_d)
+
+DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_h, gen_helper_sve2_sqrdmlsh_idx_h)
+DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_s, gen_helper_sve2_sqrdmlsh_idx_s)
+DO_SVE2_RRXR(trans_SQRDMLSH_zzxz_d, gen_helper_sve2_sqrdmlsh_idx_d)
+
#undef DO_SVE2_RRXR
/*
--
2.25.1
- [PATCH v3 59/81] target/arm: Implement SVE2 integer multiply long (indexed), (continued)
- [PATCH v3 59/81] target/arm: Implement SVE2 integer multiply long (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 55/81] target/arm: Implement SVE2 integer multiply (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 60/81] target/arm: Implement SVE2 saturating multiply (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 63/81] target/arm: Implement SVE2 multiply-add long (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 65/81] target/arm: Implement SVE mixed sign dot product (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 64/81] target/arm: Implement SVE2 complex integer multiply-add (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 67/81] target/arm: Implement SVE2 crypto unary operations, Richard Henderson, 2020/09/18
- [PATCH v3 70/81] target/arm: Implement SVE2 TBL, TBX, Richard Henderson, 2020/09/18
- [PATCH v3 44/81] target/arm: Implement SVE2 RSUBHNB, RSUBHNT, Richard Henderson, 2020/09/18
- [PATCH v3 54/81] target/arm: Split out formats for 3 vectors + 1 index, Richard Henderson, 2020/09/18
- [PATCH v3 57/81] target/arm: Implement SVE2 saturating multiply-add high (indexed),
Richard Henderson <=
- [PATCH v3 62/81] target/arm: Implement SVE2 saturating multiply high (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 58/81] target/arm: Implement SVE2 saturating multiply-add (indexed), Richard Henderson, 2020/09/18
- [PATCH v3 61/81] target/arm: Implement SVE2 signed saturating doubling multiply high, Richard Henderson, 2020/09/18
- [PATCH v3 69/81] target/arm: Implement SVE2 crypto constructive binary operations, Richard Henderson, 2020/09/18
- [PATCH v3 73/81] target/arm: Implement SVE2 FCVTXNT, FCVTX, Richard Henderson, 2020/09/18
- [PATCH v3 68/81] target/arm: Implement SVE2 crypto destructive binary operations, Richard Henderson, 2020/09/18
- [PATCH v3 77/81] target/arm: Implement 128-bit ZIP, UZP, TRN, Richard Henderson, 2020/09/18
- [PATCH v3 66/81] target/arm: Implement SVE mixed sign dot product, Richard Henderson, 2020/09/18
- [PATCH v3 71/81] target/arm: Implement SVE2 FCVTNT, Richard Henderson, 2020/09/18
- [PATCH v3 74/81] target/arm: Implement SVE2 FLOGB, Richard Henderson, 2020/09/18