[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (in
From: |
Richard Henderson |
Subject: |
[PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (indexed) |
Date: |
Tue, 9 Mar 2021 08:20:22 -0800 |
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
target/arm/helper.h | 14 ++++++
target/arm/sve.decode | 8 ++++
target/arm/translate-sve.c | 8 ++++
target/arm/vec_helper.c | 88 ++++++++++++++++++++++++++++++++++++++
4 files changed, 118 insertions(+)
diff --git a/target/arm/helper.h b/target/arm/helper.h
index eb94b6b1e6..e7c463fff5 100644
--- a/target/arm/helper.h
+++ b/target/arm/helper.h
@@ -967,6 +967,20 @@ DEF_HELPER_FLAGS_4(sve2_sqrdmulh_h, TCG_CALL_NO_RWG, void,
ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_sqrdmulh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqdmulh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_h, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_s, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG,
+ void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
#ifdef TARGET_AARCH64
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 8c063e77ae..31a3d909f3 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -841,6 +841,14 @@ SQDMULLB_zzx_d 01000100 .. 1 ..... 1110.0 ..... .....
@rrxl_d
SQDMULLT_zzx_s 01000100 .. 1 ..... 1110.1 ..... ..... @rrxl_s
SQDMULLT_zzx_d 01000100 .. 1 ..... 1110.1 ..... ..... @rrxl_d
+# SVE2 saturating multiply high (indexed)
+SQDMULH_zzx_h 01000100 .. 1 ..... 111100 ..... ..... @rrx_h
+SQDMULH_zzx_s 01000100 .. 1 ..... 111100 ..... ..... @rrx_s
+SQDMULH_zzx_d 01000100 .. 1 ..... 111100 ..... ..... @rrx_d
+SQRDMULH_zzx_h 01000100 .. 1 ..... 111101 ..... ..... @rrx_h
+SQRDMULH_zzx_s 01000100 .. 1 ..... 111101 ..... ..... @rrx_s
+SQRDMULH_zzx_d 01000100 .. 1 ..... 111101 ..... ..... @rrx_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/translate-sve.c b/target/arm/translate-sve.c
index 27a10a9759..a3e7d4f38f 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3864,6 +3864,14 @@ 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)
DO_SVE2_RRX(trans_MUL_zzx_d, gen_helper_gvec_mul_idx_d)
+DO_SVE2_RRX(trans_SQDMULH_zzx_h, gen_helper_sve2_sqdmulh_idx_h)
+DO_SVE2_RRX(trans_SQDMULH_zzx_s, gen_helper_sve2_sqdmulh_idx_s)
+DO_SVE2_RRX(trans_SQDMULH_zzx_d, gen_helper_sve2_sqdmulh_idx_d)
+
+DO_SVE2_RRX(trans_SQRDMULH_zzx_h, gen_helper_sve2_sqrdmulh_idx_h)
+DO_SVE2_RRX(trans_SQRDMULH_zzx_s, gen_helper_sve2_sqrdmulh_idx_s)
+DO_SVE2_RRX(trans_SQRDMULH_zzx_d, gen_helper_sve2_sqrdmulh_idx_d)
+
#undef DO_SVE2_RRX
#define DO_SVE2_RRX_TB(NAME, FUNC, TOP) \
diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c
index 25061c15e1..8b7269d8e1 100644
--- a/target/arm/vec_helper.c
+++ b/target/arm/vec_helper.c
@@ -240,6 +240,36 @@ void HELPER(sve2_sqrdmulh_h)(void *vd, void *vn, void *vm,
uint32_t desc)
}
}
+void HELPER(sve2_sqdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+ int16_t mm = m[i];
+ for (j = 0; j < 16 / 2; ++j) {
+ d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, &discard);
+ }
+ }
+}
+
+void HELPER(sve2_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+ int16_t mm = m[i];
+ for (j = 0; j < 16 / 2; ++j) {
+ d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, &discard);
+ }
+ }
+}
+
/* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */
int32_t do_sqrdmlah_s(int32_t src1, int32_t src2, int32_t src3,
bool neg, bool round, uint32_t *sat)
@@ -373,6 +403,36 @@ void HELPER(sve2_sqrdmulh_s)(void *vd, void *vn, void *vm,
uint32_t desc)
}
}
+void HELPER(sve2_sqdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+ int32_t mm = m[i];
+ for (j = 0; j < 16 / 4; ++j) {
+ d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, &discard);
+ }
+ }
+}
+
+void HELPER(sve2_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+ uint32_t discard;
+
+ for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+ int32_t mm = m[i];
+ for (j = 0; j < 16 / 4; ++j) {
+ d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, &discard);
+ }
+ }
+}
+
/* Signed saturating rounding doubling multiply-accumulate high half, 64-bit */
static int64_t do_sat128_d(Int128 r)
{
@@ -452,6 +512,34 @@ void HELPER(sve2_sqrdmulh_d)(void *vd, void *vn, void *vm,
uint32_t desc)
}
}
+void HELPER(sve2_sqdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx;
+
+ for (i = 0; i < opr_sz / 8; i += 16 / 8) {
+ int64_t mm = m[i];
+ for (j = 0; j < 16 / 8; ++j) {
+ d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, false);
+ }
+ }
+}
+
+void HELPER(sve2_sqrdmulh_idx_d)(void *vd, void *vn, void *vm, uint32_t desc)
+{
+ intptr_t i, j, opr_sz = simd_oprsz(desc);
+ int idx = simd_data(desc);
+ int64_t *d = vd, *n = vn, *m = (int64_t *)vm + idx;
+
+ for (i = 0; i < opr_sz / 8; i += 16 / 8) {
+ int64_t mm = m[i];
+ for (j = 0; j < 16 / 8; ++j) {
+ d[i + j] = do_sqrdmlah_d(n[i + j], mm, 0, false, true);
+ }
+ }
+}
+
/* Integer 8 and 16-bit dot-product.
*
* Note that for the loops herein, host endianness does not matter
--
2.25.1
- [PATCH v4 42/78] target/arm: Implement SVE2 HISTCNT, HISTSEG, (continued)
- [PATCH v4 42/78] target/arm: Implement SVE2 HISTCNT, HISTSEG, Richard Henderson, 2021/03/09
- [PATCH v4 41/78] target/arm: Implement SVE2 RSUBHNB, RSUBHNT, Richard Henderson, 2021/03/09
- [PATCH v4 43/78] target/arm: Implement SVE2 XAR, Richard Henderson, 2021/03/09
- [PATCH v4 45/78] target/arm: Implement SVE2 gather load insns, Richard Henderson, 2021/03/09
- [PATCH v4 46/78] target/arm: Implement SVE2 FMMLA, Richard Henderson, 2021/03/09
- [PATCH v4 44/78] target/arm: Implement SVE2 scatter store insns, Richard Henderson, 2021/03/09
- [PATCH v4 47/78] target/arm: Implement SVE2 SPLICE, EXT, Richard Henderson, 2021/03/09
- [PATCH v4 50/78] target/arm: Split out formats for 2 vectors + 1 index, Richard Henderson, 2021/03/09
- [PATCH v4 49/78] target/arm: Pass separate addend to FCMLA helpers, Richard Henderson, 2021/03/09
- [PATCH v4 48/78] target/arm: Pass separate addend to {U, S}DOT helpers, Richard Henderson, 2021/03/09
- [PATCH v4 59/78] target/arm: Implement SVE2 saturating multiply high (indexed),
Richard Henderson <=
- [PATCH v4 57/78] target/arm: Implement SVE2 saturating multiply (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 54/78] target/arm: Implement SVE2 saturating multiply-add high (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 51/78] target/arm: Split out formats for 3 vectors + 1 index, Richard Henderson, 2021/03/09
- [PATCH v4 53/78] target/arm: Implement SVE2 integer multiply-add (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 52/78] target/arm: Implement SVE2 integer multiply (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 55/78] target/arm: Implement SVE2 saturating multiply-add (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 58/78] target/arm: Implement SVE2 signed saturating doubling multiply high, Richard Henderson, 2021/03/09
- [PATCH v4 60/78] target/arm: Implement SVE2 multiply-add long (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 56/78] target/arm: Implement SVE2 integer multiply long (indexed), Richard Henderson, 2021/03/09
- [PATCH v4 62/78] target/arm: Implement SVE mixed sign dot product (indexed), Richard Henderson, 2021/03/09