target/arm: Move scale by esz into helper_sve_while*

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

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20250704142112.1018902-76-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c
index 5e11e86e5e0236ccc45c67eb8ee225977d57d267..b8f3fbb816cf6280f24ea72d4614135fbc082729 100644 (file)
--- a/target/arm/tcg/sve_helper.c
+++ b/target/arm/tcg/sve_helper.c
@@ -4133,6 +4133,7 @@ uint32_t HELPER(sve_whilel)(void *vd, uint32_t count, uint32_t pred_desc)
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
 
+    count <<= esz;
     memset(d, 0, sizeof(*d));
     do_whilel(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, false);
@@ -4165,6 +4166,7 @@ uint32_t HELPER(sve_whileg)(void *vd, uint32_t count, uint32_t pred_desc)
     uint64_t esz_mask = pred_esz_masks[esz];
     ARMPredicateReg *d = vd;
 
+    count <<= esz;
     memset(d, 0, sizeof(*d));
     do_whileg(d, esz_mask, count, oprbits);
     return pred_count_test(oprbits, count, true);

diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c
index 210a029ab840be0b5e9e93e6e858a652f7dc2189..f74f2bb1b38ca7d1c604b88d65c70d8c86a2ae90 100644 (file)
--- 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);
     }