target/arm: Implement SVE2p1 WHILE (predicate pair)

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-79-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 61 insertions, 4 deletions

diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h
index 0b1b588..eac23e7 100644
--- a/target/arm/tcg/helper-sve.h
+++ b/target/arm/tcg/helper-sve.h
@@ -941,6 +941,9 @@ DEF_HELPER_FLAGS_3(sve_cntp, TCG_CALL_NO_RWG, i64, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_whilel, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
 DEF_HELPER_FLAGS_3(sve_whileg, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
 
+DEF_HELPER_FLAGS_3(sve_while2l, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+DEF_HELPER_FLAGS_3(sve_while2g, TCG_CALL_NO_RWG, i32, ptr, i32, i32)
+
 DEF_HELPER_FLAGS_4(sve_subri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 DEF_HELPER_FLAGS_4(sve_subri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
 DEF_HELPER_FLAGS_4(sve_subri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32)
diff --git a/target/arm/tcg/sve.decode b/target/arm/tcg/sve.decode
index c90d975..968b2a5 100644
--- a/target/arm/tcg/sve.decode
+++ b/target/arm/tcg/sve.decode
@@ -796,6 +796,14 @@ WHILE_gt        00100101 esz:2 1 rm:5 000 sf:1 u:1 0 rn:5 eq:1 rd:4  &while
 # SVE2 pointer conflict compare
 WHILE_ptr       00100101 esz:2 1 rm:5 001 100 rn:5 rw:1 rd:4
 
+# SVE2.1 predicate pair
+%pd_pair        1:3 !function=times_2
+@while_pair     ........ esz:2 . rm:5 .... u:1 . rn:5 . ... eq:1 \
+                &while rd=%pd_pair sf=1
+
+WHILE_lt_pair   00100101 .. 1 ..... 0101 . 1 ..... 1 ... .  @while_pair
+WHILE_gt_pair   00100101 .. 1 ..... 0101 . 0 ..... 1 ... .  @while_pair
+
 ### SVE Integer Wide Immediate - Unpredicated Group
 
 # SVE broadcast floating-point immediate (unpredicated)
diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index b8f3fbb..30394f4 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4139,6 +4139,26 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     return pred_count_test(oprbits, count, false);
 }
 
+uint32_t HELPER(sve_while2l)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+    uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+    uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+    uint32_t oprbits = oprsz * 8;
+    uint64_t esz_mask = pred_esz_masks[esz];
+    ARMPredicateReg *d = vd;
+
+    count <<= esz;
+    memset(d, 0, 2 * sizeof(*d));
+    if (count <= oprbits) {
+        do_whilel(&d[0], esz_mask, count, oprbits);
+    } else {
+        do_whilel(&d[0], esz_mask, oprbits, oprbits);
+        do_whilel(&d[1], esz_mask, count - oprbits, oprbits);
+    }
+
+    return pred_count_test(2 * oprbits, count, false);
+}
+
 /* D must be cleared on entry. */
 static void do_whileg(ARMPredicateReg *d, uint64_t esz_mask,
                       uint32_t count, uint32_t oprbits)
@@ -4172,6 +4192,26 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     return pred_count_test(oprbits, count, true);
 }
 
+uint32_t HELPER(sve_while2g)(void *vd, uint32_t count, uint32_t pred_desc)
+{
+    uint32_t oprsz = FIELD_EX32(pred_desc, PREDDESC, OPRSZ);
+    uint32_t esz = FIELD_EX32(pred_desc, PREDDESC, ESZ);
+    uint32_t oprbits = oprsz * 8;
+    uint64_t esz_mask = pred_esz_masks[esz];
+    ARMPredicateReg *d = vd;
+
+    count <<= esz;
+    memset(d, 0, 2 * sizeof(*d));
+    if (count <= oprbits) {
+        do_whileg(&d[1], esz_mask, count, oprbits);
+    } else {
+        do_whilel(&d[1], esz_mask, oprbits, oprbits);
+        do_whileg(&d[0], esz_mask, count - oprbits, oprbits);
+    }
+
+    return pred_count_test(2 * oprbits, count, true);
+}
+
 /* Recursive reduction on a function;
  * C.f. the ARM ARM function ReducePredicated.
  *
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index cb60b53..de6ffe7 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3109,7 +3109,8 @@ static bool trans_CTERM(DisasContext *s, arg_CTERM *a)
 }
 
 typedef void gen_while_fn(TCGv_i32, TCGv_ptr, TCGv_i32, TCGv_i32);
-static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
+static bool do_WHILE(DisasContext *s, arg_while *a,
+                     bool lt, int scale, gen_while_fn *fn)
 {
     TCGv_i64 op0, op1, t0, t1, tmax;
     TCGv_i32 t2;
@@ -3164,7 +3165,7 @@ static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
         }
     }
 
-    tmax = tcg_constant_i64(vsz >> a->esz);
+    tmax = tcg_constant_i64((vsz << scale) >> a->esz);
     if (eq) {
         /* Equality means one more iteration.  */
         tcg_gen_addi_i64(t0, t0, 1);
@@ -3205,8 +3206,13 @@ static bool do_WHILE(DisasContext *s, arg_while *a, bool lt, gen_while_fn *fn)
     return true;
 }
 
-TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, gen_helper_sve_whilel)
-TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, gen_helper_sve_whileg)
+TRANS_FEAT(WHILE_lt, aa64_sve, do_WHILE, a, true, 0, gen_helper_sve_whilel)
+TRANS_FEAT(WHILE_gt, aa64_sve2, do_WHILE, a, false, 0, gen_helper_sve_whileg)
+
+TRANS_FEAT(WHILE_lt_pair, aa64_sme2_or_sve2p1, do_WHILE,
+           a, true, 1, gen_helper_sve_while2l)
+TRANS_FEAT(WHILE_gt_pair, aa64_sme2_or_sve2p1, do_WHILE,
+           a, false, 1, gen_helper_sve_while2g)
 
 static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
 {