* [PATCH 1/4] target/arm: Implement SVE2 ADDHNB, ADDHNT
2020-04-17 16:22 [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Stephen Long
@ 2020-04-17 16:22 ` Stephen Long
2020-04-17 16:22 ` [PATCH 2/4] target/arm: Implement SVE2 RADDHNB, RADDHNT Stephen Long
` (3 subsequent siblings)
4 siblings, 0 replies; 8+ messages in thread
From: Stephen Long @ 2020-04-17 16:22 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, richard.henderson, apazos
Signed-off-by: Stephen Long <steplong@quicinc.com>
---
target/arm/helper-sve.h | 8 ++++++++
target/arm/sve.decode | 5 +++++
target/arm/sve_helper.c | 36 ++++++++++++++++++++++++++++++++++++
target/arm/translate-sve.c | 13 +++++++++++++
4 files changed, 62 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 958ad623f6..5b8a8b0656 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2516,6 +2516,14 @@ DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_addhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_addhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_addhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_addhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_addhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_addhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG,
i32, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 9dd20eb6ec..e6a12f4e66 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1321,6 +1321,11 @@ UQSHRNT 01000101 .. 1 ..... 00 1101 ..... ..... @rd_rn_tszimm_shr
UQRSHRNB 01000101 .. 1 ..... 00 1110 ..... ..... @rd_rn_tszimm_shr
UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr
+## SVE2 integer add/subtract narrow high part
+
+ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm
+ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm
+
### SVE2 Character Match
MATCH 01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 65857e27b4..743240aa80 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2025,6 +2025,42 @@ DO_SHRNT(sve2_uqrshrnt_d, uint64_t, uint32_t, , H1_4, DO_UQRSHRN_D)
#undef DO_SHRNB
#undef DO_SHRNT
+#define DO_BINOPNB(NAME, TYPEW, TYPEN, SHIFT, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \
+ TYPEW nn = *(TYPEW *)(vn + i); \
+ TYPEW mm = *(TYPEW *)(vm + i); \
+ *(TYPEW *)(vd + i) = (TYPEN)OP(nn, mm, SHIFT); \
+ } \
+}
+
+#define DO_BINOPNT(NAME, TYPEW, TYPEN, SHIFT, HW, HN, OP) \
+void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
+{ \
+ intptr_t i, opr_sz = simd_oprsz(desc); \
+ for (i = 0; i < opr_sz; i += sizeof(TYPEW)) { \
+ TYPEW nn = *(TYPEW *)(vn + HW(i)); \
+ TYPEW mm = *(TYPEW *)(vm + HW(i)); \
+ *(TYPEN *)(vd + HN(i + sizeof(TYPEN))) = OP(nn, mm, SHIFT); \
+ } \
+}
+
+#define DO_ADDHN(N, M, SH) ((N + M) >> SH)
+
+DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN)
+DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN)
+DO_BINOPNB(sve2_addhnb_d, uint64_t, uint32_t, 32, DO_ADDHN)
+
+DO_BINOPNT(sve2_addhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_ADDHN)
+DO_BINOPNT(sve2_addhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_ADDHN)
+DO_BINOPNT(sve2_addhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_ADDHN)
+
+#undef DO_ADDHN
+
+#undef DO_BINOPNB
+
/* Fully general four-operand expander, controlled by a predicate.
*/
#define DO_ZPZZZ(NAME, TYPE, H, OP) \
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 6c237343ef..0d1a9cd8a5 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7504,6 +7504,19 @@ static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz *a)
return do_sve2_shr_narrow(s, a, ops);
}
+#define DO_SVE2_ZZZ_NARROW(NAME, name) \
+static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \
+{ \
+ static gen_helper_gvec_3 * const fns[4] = { \
+ NULL, gen_helper_sve2_##name##_h, \
+ gen_helper_sve2_##name##_s, gen_helper_sve2_##name##_d, \
+ }; \
+ return do_sve2_zzz_ool(s, a, fns[a->esz]); \
+}
+
+DO_SVE2_ZZZ_NARROW(ADDHNB, addhnb)
+DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt)
+
static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_flags_4 *fn)
{
--
2.17.1
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH 2/4] target/arm: Implement SVE2 RADDHNB, RADDHNT
2020-04-17 16:22 [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Stephen Long
2020-04-17 16:22 ` [PATCH 1/4] target/arm: Implement SVE2 ADDHNB, ADDHNT Stephen Long
@ 2020-04-17 16:22 ` Stephen Long
2020-04-17 21:24 ` Richard Henderson
2020-04-17 16:22 ` [PATCH 3/4] target/arm: Implement SVE2 SUBHNB, SUBHNT Stephen Long
` (2 subsequent siblings)
4 siblings, 1 reply; 8+ messages in thread
From: Stephen Long @ 2020-04-17 16:22 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, richard.henderson, apazos
Signed-off-by: Stephen Long <steplong@quicinc.com>
---
target/arm/helper-sve.h | 8 ++++++++
target/arm/sve.decode | 2 ++
target/arm/sve_helper.c | 10 ++++++++++
target/arm/translate-sve.c | 2 ++
4 files changed, 22 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 5b8a8b0656..5d5542a82a 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2524,6 +2524,14 @@ DEF_HELPER_FLAGS_4(sve2_addhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_addhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_addhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_raddhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_raddhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_raddhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_raddhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_raddhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_raddhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG,
i32, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index e6a12f4e66..9d82677808 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1325,6 +1325,8 @@ UQRSHRNT 01000101 .. 1 ..... 00 1111 ..... ..... @rd_rn_tszimm_shr
ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm
ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm
+RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm
+RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm
### SVE2 Character Match
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 743240aa80..f92b8dd312 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2048,6 +2048,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
}
#define DO_ADDHN(N, M, SH) ((N + M) >> SH)
+#define DO_RADDHN(N, M, SH) ((N + M + (1 << (SH - 1))) >> SH)
DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN)
DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN)
@@ -2057,6 +2058,15 @@ DO_BINOPNT(sve2_addhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_ADDHN)
DO_BINOPNT(sve2_addhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_ADDHN)
DO_BINOPNT(sve2_addhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_ADDHN)
+DO_BINOPNB(sve2_raddhnb_h, uint16_t, uint8_t, 8, DO_RADDHN)
+DO_BINOPNB(sve2_raddhnb_s, uint32_t, uint16_t, 16, DO_RADDHN)
+DO_BINOPNB(sve2_raddhnb_d, uint64_t, uint32_t, 32, DO_RADDHN)
+
+DO_BINOPNT(sve2_raddhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RADDHN)
+DO_BINOPNT(sve2_raddhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RADDHN)
+DO_BINOPNT(sve2_raddhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RADDHN)
+
+#undef DO_RADDHN
#undef DO_ADDHN
#undef DO_BINOPNB
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 0d1a9cd8a5..a36eb9cf98 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7516,6 +7516,8 @@ static bool trans_##NAME(DisasContext *s, arg_rrr_esz *a) \
DO_SVE2_ZZZ_NARROW(ADDHNB, addhnb)
DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt)
+DO_SVE2_ZZZ_NARROW(RADDHNB, raddhnb)
+DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt)
static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_flags_4 *fn)
--
2.17.1
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH 2/4] target/arm: Implement SVE2 RADDHNB, RADDHNT
2020-04-17 16:22 ` [PATCH 2/4] target/arm: Implement SVE2 RADDHNB, RADDHNT Stephen Long
@ 2020-04-17 21:24 ` Richard Henderson
2020-04-17 23:58 ` Richard Henderson
0 siblings, 1 reply; 8+ messages in thread
From: Richard Henderson @ 2020-04-17 21:24 UTC (permalink / raw)
To: Stephen Long, qemu-devel; +Cc: qemu-arm, apazos
On 4/17/20 9:22 AM, Stephen Long wrote:
> +#define DO_RADDHN(N, M, SH) ((N + M + (1 << (SH - 1))) >> SH)
This formula will overflow. See DO_RSHR -- with some added parenthesis, we
could actually reuse that macro.
r~
^ permalink raw reply [flat|nested] 8+ messages in thread
* Re: [PATCH 2/4] target/arm: Implement SVE2 RADDHNB, RADDHNT
2020-04-17 21:24 ` Richard Henderson
@ 2020-04-17 23:58 ` Richard Henderson
0 siblings, 0 replies; 8+ messages in thread
From: Richard Henderson @ 2020-04-17 23:58 UTC (permalink / raw)
To: Stephen Long, qemu-devel; +Cc: qemu-arm, apazos
On 4/17/20 2:24 PM, Richard Henderson wrote:
> On 4/17/20 9:22 AM, Stephen Long wrote:
>> +#define DO_RADDHN(N, M, SH) ((N + M + (1 << (SH - 1))) >> SH)
>
> This formula will overflow. See DO_RSHR -- with some added parenthesis, we
> could actually reuse that macro.
My bad. While it does overflow, all of these operations are truncating not
saturating, and moreover truncate to halfesize bits. Therefore overflow
doesn't matter.
r~
^ permalink raw reply [flat|nested] 8+ messages in thread
* [PATCH 3/4] target/arm: Implement SVE2 SUBHNB, SUBHNT
2020-04-17 16:22 [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Stephen Long
2020-04-17 16:22 ` [PATCH 1/4] target/arm: Implement SVE2 ADDHNB, ADDHNT Stephen Long
2020-04-17 16:22 ` [PATCH 2/4] target/arm: Implement SVE2 RADDHNB, RADDHNT Stephen Long
@ 2020-04-17 16:22 ` Stephen Long
2020-04-17 16:22 ` [PATCH 4/4] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Stephen Long
2020-04-19 18:28 ` [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Richard Henderson
4 siblings, 0 replies; 8+ messages in thread
From: Stephen Long @ 2020-04-17 16:22 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, richard.henderson, apazos
Signed-off-by: Stephen Long <steplong@quicinc.com>
---
target/arm/helper-sve.h | 8 ++++++++
target/arm/sve.decode | 2 ++
target/arm/sve_helper.c | 10 ++++++++++
target/arm/translate-sve.c | 3 +++
4 files changed, 23 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 5d5542a82a..00e3706da0 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2532,6 +2532,14 @@ DEF_HELPER_FLAGS_4(sve2_raddhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_raddhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_raddhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_subhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_subhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_subhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_subhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_subhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_subhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG,
i32, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 9d82677808..75996897a1 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1327,6 +1327,8 @@ ADDHNB 01000101 .. 1 ..... 011 000 ..... ..... @rd_rn_rm
ADDHNT 01000101 .. 1 ..... 011 001 ..... ..... @rd_rn_rm
RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm
RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm
+SUBHNB 01000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm
+SUBHNT 01000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm
### SVE2 Character Match
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index f92b8dd312..f6e7694b9f 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2049,6 +2049,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
#define DO_ADDHN(N, M, SH) ((N + M) >> SH)
#define DO_RADDHN(N, M, SH) ((N + M + (1 << (SH - 1))) >> SH)
+#define DO_SUBHN(N, M, SH) ((N - M) >> SH)
DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN)
DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN)
@@ -2066,6 +2067,15 @@ DO_BINOPNT(sve2_raddhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RADDHN)
DO_BINOPNT(sve2_raddhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RADDHN)
DO_BINOPNT(sve2_raddhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RADDHN)
+DO_BINOPNB(sve2_subhnb_h, uint16_t, uint8_t, 8, DO_SUBHN)
+DO_BINOPNB(sve2_subhnb_s, uint32_t, uint16_t, 16, DO_SUBHN)
+DO_BINOPNB(sve2_subhnb_d, uint64_t, uint32_t, 32, DO_SUBHN)
+
+DO_BINOPNT(sve2_subhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_SUBHN)
+DO_BINOPNT(sve2_subhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_SUBHN)
+DO_BINOPNT(sve2_subhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_SUBHN)
+
+#undef DO_SUBHN
#undef DO_RADDHN
#undef DO_ADDHN
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index a36eb9cf98..4081fcb873 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7519,6 +7519,9 @@ DO_SVE2_ZZZ_NARROW(ADDHNT, addhnt)
DO_SVE2_ZZZ_NARROW(RADDHNB, raddhnb)
DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt)
+DO_SVE2_ZZZ_NARROW(SUBHNB, subhnb)
+DO_SVE2_ZZZ_NARROW(SUBHNT, subhnt)
+
static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_flags_4 *fn)
{
--
2.17.1
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH 4/4] target/arm: Implement SVE2 RSUBHNB, RSUBHNT
2020-04-17 16:22 [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Stephen Long
` (2 preceding siblings ...)
2020-04-17 16:22 ` [PATCH 3/4] target/arm: Implement SVE2 SUBHNB, SUBHNT Stephen Long
@ 2020-04-17 16:22 ` Stephen Long
2020-04-19 18:28 ` [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Richard Henderson
4 siblings, 0 replies; 8+ messages in thread
From: Stephen Long @ 2020-04-17 16:22 UTC (permalink / raw)
To: qemu-devel; +Cc: qemu-arm, richard.henderson, apazos
This completes the section 'SVE2 integer add/subtract narrow high part'
Signed-off-by: Stephen Long <steplong@quicinc.com>
---
target/arm/helper-sve.h | 8 ++++++++
target/arm/sve.decode | 2 ++
target/arm/sve_helper.c | 10 ++++++++++
target/arm/translate-sve.c | 2 ++
4 files changed, 22 insertions(+)
diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 00e3706da0..011aa03010 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2540,6 +2540,14 @@ DEF_HELPER_FLAGS_4(sve2_subhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_subhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_4(sve2_subhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_rsubhnb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_rsubhnb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_rsubhnb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve2_rsubhnt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_rsubhnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve2_rsubhnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG,
i32, ptr, ptr, ptr, ptr, i32)
DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 75996897a1..f0e6143e00 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1329,6 +1329,8 @@ RADDHNB 01000101 .. 1 ..... 011 010 ..... ..... @rd_rn_rm
RADDHNT 01000101 .. 1 ..... 011 011 ..... ..... @rd_rn_rm
SUBHNB 01000101 .. 1 ..... 011 100 ..... ..... @rd_rn_rm
SUBHNT 01000101 .. 1 ..... 011 101 ..... ..... @rd_rn_rm
+RSUBHNB 01000101 .. 1 ..... 011 110 ..... ..... @rd_rn_rm
+RSUBHNT 01000101 .. 1 ..... 011 111 ..... ..... @rd_rn_rm
### SVE2 Character Match
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index f6e7694b9f..d616010390 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2050,6 +2050,7 @@ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \
#define DO_ADDHN(N, M, SH) ((N + M) >> SH)
#define DO_RADDHN(N, M, SH) ((N + M + (1 << (SH - 1))) >> SH)
#define DO_SUBHN(N, M, SH) ((N - M) >> SH)
+#define DO_RSUBHN(N, M, SH) ((N - M + (1 << (SH - 1))) >> SH)
DO_BINOPNB(sve2_addhnb_h, uint16_t, uint8_t, 8, DO_ADDHN)
DO_BINOPNB(sve2_addhnb_s, uint32_t, uint16_t, 16, DO_ADDHN)
@@ -2075,6 +2076,15 @@ DO_BINOPNT(sve2_subhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_SUBHN)
DO_BINOPNT(sve2_subhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_SUBHN)
DO_BINOPNT(sve2_subhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_SUBHN)
+DO_BINOPNB(sve2_rsubhnb_h, uint16_t, uint8_t, 8, DO_RSUBHN)
+DO_BINOPNB(sve2_rsubhnb_s, uint32_t, uint16_t, 16, DO_RSUBHN)
+DO_BINOPNB(sve2_rsubhnb_d, uint64_t, uint32_t, 32, DO_RSUBHN)
+
+DO_BINOPNT(sve2_rsubhnt_h, uint16_t, uint8_t, 8, H1_2, H1, DO_RSUBHN)
+DO_BINOPNT(sve2_rsubhnt_s, uint32_t, uint16_t, 16, H1_4, H1_2, DO_RSUBHN)
+DO_BINOPNT(sve2_rsubhnt_d, uint64_t, uint32_t, 32, , H1_4, DO_RSUBHN)
+
+#undef DO_RSUBHN
#undef DO_SUBHN
#undef DO_RADDHN
#undef DO_ADDHN
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 4081fcb873..d75dd938ef 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7521,6 +7521,8 @@ DO_SVE2_ZZZ_NARROW(RADDHNT, raddhnt)
DO_SVE2_ZZZ_NARROW(SUBHNB, subhnb)
DO_SVE2_ZZZ_NARROW(SUBHNT, subhnt)
+DO_SVE2_ZZZ_NARROW(RSUBHNB, rsubhnb)
+DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt)
static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a,
gen_helper_gvec_flags_4 *fn)
--
2.17.1
^ permalink raw reply related [flat|nested] 8+ messages in thread* Re: [PATCH 0/4] target/arm: Implement last SVE2 narrowing section
2020-04-17 16:22 [PATCH 0/4] target/arm: Implement last SVE2 narrowing section Stephen Long
` (3 preceding siblings ...)
2020-04-17 16:22 ` [PATCH 4/4] target/arm: Implement SVE2 RSUBHNB, RSUBHNT Stephen Long
@ 2020-04-19 18:28 ` Richard Henderson
4 siblings, 0 replies; 8+ messages in thread
From: Richard Henderson @ 2020-04-19 18:28 UTC (permalink / raw)
To: Stephen Long, qemu-devel; +Cc: qemu-arm, apazos
On 4/17/20 9:22 AM, Stephen Long wrote:
> Submitting patches for the section 'SVE2 integer add/subtract narrow
> high part' for early review.
>
> Stephen Long (4):
> target/arm: Implement SVE2 ADDHNB, ADDHNT
> target/arm: Implement SVE2 RADDHNB, RADDHNT
> target/arm: Implement SVE2 SUBHNB, SUBHNT
> target/arm: Implement SVE2 RSUBHNB, RSUBHNT
Thanks. Applied to my SVE2 branch.
r~
^ permalink raw reply [flat|nested] 8+ messages in thread