diff mbox series

[v2,33/67] target/arm: Implement SVE reverse within elements

Message ID 20180217182323.25885-34-richard.henderson@linaro.org
State Superseded
Headers show
Series target/arm: Scalable Vector Extension | expand

Commit Message

Richard Henderson Feb. 17, 2018, 6:22 p.m. UTC 
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

---
 target/arm/helper-sve.h    | 14 ++++++++++++++
 target/arm/sve_helper.c    | 41 ++++++++++++++++++++++++++++++++++-------
 target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++
 target/arm/sve.decode      |  7 +++++++
 4 files changed, 93 insertions(+), 7 deletions(-)

-- 
2.14.3

Comments

Peter Maydell Feb. 23, 2018, 3:50 p.m. UTC | #1 
On 17 February 2018 at 18:22, Richard Henderson
<richard.henderson@linaro.org> wrote:
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

> ---

>  target/arm/helper-sve.h    | 14 ++++++++++++++

>  target/arm/sve_helper.c    | 41 ++++++++++++++++++++++++++++++++++-------

>  target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++

>  target/arm/sve.decode      |  7 +++++++

>  4 files changed, 93 insertions(+), 7 deletions(-)


> +/* Swap 16-bit words within a 32-bit word.  */

> +static inline uint32_t hswap32(uint32_t h)

> +{

> +    return rol32(h, 16);

> +}

> +

> +/* Swap 16-bit words within a 64-bit word.  */

> +static inline uint64_t hswap64(uint64_t h)

> +{

> +    uint64_t m = 0x0000ffff0000ffffull;

> +    h = rol64(h, 32);

> +    return ((h & m) << 16) | ((h >> 16) & m);

> +}

> +

> +/* Swap 32-bit words within a 64-bit word.  */

> +static inline uint64_t wswap64(uint64_t h)

> +{

> +    return rol64(h, 32);

> +}

> +


Were there cases in earlier patches that could have used these? I forget.
I guess they're not useful enough to be worth putting in bswap.h.

> @@ -1577,13 +1611,6 @@ void HELPER(sve_rev_b)(void *vd, void *vn, uint32_t desc)

>      }

>  }

>

> -static inline uint64_t hswap64(uint64_t h)

> -{

> -    uint64_t m = 0x0000ffff0000ffffull;

> -    h = rol64(h, 32);

> -    return ((h & m) << 16) | ((h >> 16) & m);

> -}

> -


Better to put the function in the right place to start with.

Otherwise
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>


thanks
-- PMM
Richard Henderson Feb. 23, 2018, 8:21 p.m. UTC | #2 
On 02/23/2018 07:50 AM, Peter Maydell wrote:
> On 17 February 2018 at 18:22, Richard Henderson

> <richard.henderson@linaro.org> wrote:

>> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

>> ---

>>  target/arm/helper-sve.h    | 14 ++++++++++++++

>>  target/arm/sve_helper.c    | 41 ++++++++++++++++++++++++++++++++++-------

>>  target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++

>>  target/arm/sve.decode      |  7 +++++++

>>  4 files changed, 93 insertions(+), 7 deletions(-)

> 

>> +/* Swap 16-bit words within a 32-bit word.  */

>> +static inline uint32_t hswap32(uint32_t h)

>> +{

>> +    return rol32(h, 16);

>> +}

>> +

>> +/* Swap 16-bit words within a 64-bit word.  */

>> +static inline uint64_t hswap64(uint64_t h)

>> +{

>> +    uint64_t m = 0x0000ffff0000ffffull;

>> +    h = rol64(h, 32);

>> +    return ((h & m) << 16) | ((h >> 16) & m);

>> +}

>> +

>> +/* Swap 32-bit words within a 64-bit word.  */

>> +static inline uint64_t wswap64(uint64_t h)

>> +{

>> +    return rol64(h, 32);

>> +}

>> +

> 

> Were there cases in earlier patches that could have used these? I forget.


No, the earlier patches dealt with bits not bytes.

> I guess they're not useful enough to be worth putting in bswap.h.


Probably not.

>> -static inline uint64_t hswap64(uint64_t h)

>> -{

>> -    uint64_t m = 0x0000ffff0000ffffull;

>> -    h = rol64(h, 32);

>> -    return ((h & m) << 16) | ((h >> 16) & m);

>> -}

>> -

> 

> Better to put the function in the right place to start with.


Oops, yes.


r~
diff mbox series

Patch

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index a58fb4ba01..3b7c54905d 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -465,6 +465,20 @@  DEF_HELPER_FLAGS_4(sve_compact_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
 
 DEF_HELPER_FLAGS_2(sve_last_active_element, TCG_CALL_NO_RWG, s32, ptr, i32)
 
+DEF_HELPER_FLAGS_4(sve_revb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_revb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_revb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_revh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_revh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_revw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_4(sve_rbit_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_4(sve_rbit_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_5(sve_and_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_bic_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve_eor_pppp, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index ee289be642..a67bb579b8 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -237,6 +237,26 @@  static inline uint64_t expand_pred_s(uint8_t byte)
     return word[byte & 0x11];
 }
 
+/* Swap 16-bit words within a 32-bit word.  */
+static inline uint32_t hswap32(uint32_t h)
+{
+    return rol32(h, 16);
+}
+
+/* Swap 16-bit words within a 64-bit word.  */
+static inline uint64_t hswap64(uint64_t h)
+{
+    uint64_t m = 0x0000ffff0000ffffull;
+    h = rol64(h, 32);
+    return ((h & m) << 16) | ((h >> 16) & m);
+}
+
+/* Swap 32-bit words within a 64-bit word.  */
+static inline uint64_t wswap64(uint64_t h)
+{
+    return rol64(h, 32);
+}
+
 #define LOGICAL_PPPP(NAME, FUNC) \
 void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc)  \
 {                                                                         \
@@ -615,6 +635,20 @@  DO_ZPZ(sve_neg_h, uint16_t, H1_2, DO_NEG)
 DO_ZPZ(sve_neg_s, uint32_t, H1_4, DO_NEG)
 DO_ZPZ_D(sve_neg_d, uint64_t, DO_NEG)
 
+DO_ZPZ(sve_revb_h, uint16_t, H1_2, bswap16)
+DO_ZPZ(sve_revb_s, uint32_t, H1_4, bswap32)
+DO_ZPZ_D(sve_revb_d, uint64_t, bswap64)
+
+DO_ZPZ(sve_revh_s, uint32_t, H1_4, hswap32)
+DO_ZPZ_D(sve_revh_d, uint64_t, hswap64)
+
+DO_ZPZ_D(sve_revw_d, uint64_t, wswap64)
+
+DO_ZPZ(sve_rbit_b, uint8_t, H1, revbit8)
+DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16)
+DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32)
+DO_ZPZ_D(sve_rbit_d, uint64_t, revbit64)
+
 /* Three-operand expander, unpredicated, in which the third operand is "wide".
  */
 #define DO_ZZW(NAME, TYPE, TYPEW, H, OP)                       \
@@ -1577,13 +1611,6 @@  void HELPER(sve_rev_b)(void *vd, void *vn, uint32_t desc)
     }
 }
 
-static inline uint64_t hswap64(uint64_t h)
-{
-    uint64_t m = 0x0000ffff0000ffffull;
-    h = rol64(h, 32);
-    return ((h & m) << 16) | ((h >> 16) & m);
-}
-
 void HELPER(sve_rev_h)(void *vd, void *vn, uint32_t desc)
 {
     intptr_t i, j, opr_sz = simd_oprsz(desc);
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index fc2a295ab7..5a1ed379ad 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -2435,6 +2435,44 @@  static void trans_CPY_m_v(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
     tcg_temp_free_i64(t);
 }
 
+static void trans_REVB(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        NULL,
+        gen_helper_sve_revb_h,
+        gen_helper_sve_revb_s,
+        gen_helper_sve_revb_d,
+    };
+    do_zpz_ool(s, a, fns[a->esz]);
+}
+
+static void trans_REVH(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        NULL,
+        NULL,
+        gen_helper_sve_revh_s,
+        gen_helper_sve_revh_d,
+    };
+    do_zpz_ool(s, a, fns[a->esz]);
+}
+
+static void trans_REVW(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    do_zpz_ool(s, a, a->esz == 3 ? gen_helper_sve_revw_d : NULL);
+}
+
+static void trans_RBIT(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    static gen_helper_gvec_3 * const fns[4] = {
+        gen_helper_sve_rbit_b,
+        gen_helper_sve_rbit_h,
+        gen_helper_sve_rbit_s,
+        gen_helper_sve_rbit_d,
+    };
+    do_zpz_ool(s, a, fns[a->esz]);
+}
+
 /*
  *** SVE Memory - 32-bit Gather and Unsized Contiguous Group
  */
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 5e127de88c..8903fb6592 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -457,6 +457,13 @@  CPY_m_v		00000101 .. 100000 100 ... ..... .....		@rd_pg_rn
 # SVE copy element from general register to vector (predicated)
 CPY_m_r		00000101 .. 101000 101 ... ..... .....		@rd_pg_rn
 
+# SVE reverse within elements
+# Note esz >= operation size
+REVB		00000101 .. 1001 00 100 ... ..... .....		@rd_pg_rn
+REVH		00000101 .. 1001 01 100 ... ..... .....		@rd_pg_rn
+REVW		00000101 .. 1001 10 100 ... ..... .....		@rd_pg_rn
+RBIT		00000101 .. 1001 11 100 ... ..... .....		@rd_pg_rn
+
 ### SVE Predicate Logical Operations Group
 
 # SVE predicate logical operations