Change the API to pass element count rather than bit count.
This will be helpful later for predicate as counter.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/tcg/sve_helper.c    |  2 ++
 target/arm/tcg/translate-sve.c | 13 +++++--------
 2 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index ba5ab6b513..dbade6ece0 100644
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4135,6 +4135,7 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     uint32_t oprbits = oprsz * 8;
     uint64_t esz_mask = pred_esz_masks[esz];
 
+    count <<= esz;
     do_zero(vd, oprsz);
     do_whilel(vd, esz_mask, count, oprbits);
 
@@ -4166,6 +4167,7 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     uint32_t oprbits = oprsz * 8;
     uint64_t esz_mask = pred_esz_masks[esz];
 
+    count <<= esz;
     do_zero(vd, oprsz);
     do_whileg(vd, esz_mask, count, oprbits);
 
diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 210a029ab8..f74f2bb1b3 100644
--- a/target/arm/tcg/translate-sve.c
+++ b/target/arm/tcg/translate-sve.c
@@ -3198,9 +3198,6 @@ static bool trans_WHILE(DisasContext *s, arg_WHILE *a)
     t2 = tcg_temp_new_i32();
     tcg_gen_extrl_i64_i32(t2, t0);
 
-    /* Scale elements to bits.  */
-    tcg_gen_shli_i32(t2, t2, a->esz);
-
     desc = FIELD_DP32(desc, PREDDESC, OPRSZ, vsz / 8);
     desc = FIELD_DP32(desc, PREDDESC, ESZ, a->esz);
 
@@ -3234,7 +3231,7 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
     op0 = read_cpu_reg(s, a->rn, 1);
     op1 = read_cpu_reg(s, a->rm, 1);
 
-    tmax = tcg_constant_i64(vsz);
+    tmax = tcg_constant_i64(vsz >> a->esz);
     diff = tcg_temp_new_i64();
 
     if (a->rw) {
@@ -3244,15 +3241,15 @@ static bool trans_WHILE_ptr(DisasContext *s, arg_WHILE_ptr *a)
         tcg_gen_sub_i64(diff, op0, op1);
         tcg_gen_sub_i64(t1, op1, op0);
         tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, diff, t1);
-        /* Round down to a multiple of ESIZE.  */
-        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* Divide, rounding down, by ESIZE.  */
+        tcg_gen_shri_i64(diff, diff, a->esz);
         /* If op1 == op0, diff == 0, and the condition is always true. */
         tcg_gen_movcond_i64(TCG_COND_EQ, diff, op0, op1, tmax, diff);
     } else {
         /* WHILEWR */
         tcg_gen_sub_i64(diff, op1, op0);
-        /* Round down to a multiple of ESIZE.  */
-        tcg_gen_andi_i64(diff, diff, -1 << a->esz);
+        /* Divide, rounding down, by ESIZE.  */
+        tcg_gen_shri_i64(diff, diff, a->esz);
         /* If op0 >= op1, diff <= 0, the condition is always true. */
         tcg_gen_movcond_i64(TCG_COND_GEU, diff, op0, op1, tmax, diff);
     }
-- 
2.43.0

On Wed, 2 Jul 2025 at 13:38, Richard Henderson
<richard.henderson@linaro.org> wrote:
>
> Change the API to pass element count rather than bit count.
> This will be helpful later for predicate as counter.
>
> Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

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

thanks
-- PMM