[PATCH v4 1/8] target/arm: Fix sve_uzp_p vs odd vector lengths

[Richard Henderson <richard.henderson@linaro.org>]

Missed out on compressing the second half of a predicate
with length vl % 512 > 256.

Adjust all of the x + (y << s) to x | (y << s) as a
general style fix.  Drop the extract64 because the input
uint64_t are known to be already zero-extended from the
current size of the predicate.

Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/sve_helper.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 844db08bd5..11c9397dbb 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1939,7 +1939,7 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc)
     if (oprsz <= 8) {
         l = compress_bits(n[0] >> odd, esz);
         h = compress_bits(m[0] >> odd, esz);
-        d[0] = extract64(l + (h << (4 * oprsz)), 0, 8 * oprsz);
+        d[0] = l | (h << (4 * oprsz));
     } else {
         ARMPredicateReg tmp_m;
         intptr_t oprsz_16 = oprsz / 16;
@@ -1953,23 +1953,35 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc)
             h = n[2 * i + 1];
             l = compress_bits(l >> odd, esz);
             h = compress_bits(h >> odd, esz);
-            d[i] = l + (h << 32);
+            d[i] = l | (h << 32);
         }
 
-        /* For VL which is not a power of 2, the results from M do not
-           align nicely with the uint64_t for D.  Put the aligned results
-           from M into TMP_M and then copy it into place afterward.  */
+        /*
+         * For VL which is not a multiple of 512, the results from M do not
+         * align nicely with the uint64_t for D.  Put the aligned results
+         * from M into TMP_M and then copy it into place afterward.
+         */
         if (oprsz & 15) {
-            d[i] = compress_bits(n[2 * i] >> odd, esz);
+            int final_shift = (oprsz & 15) * 2;
+
+            l = n[2 * i + 0];
+            h = n[2 * i + 1];
+            l = compress_bits(l >> odd, esz);
+            h = compress_bits(h >> odd, esz);
+            d[i] = l | (h << final_shift);
 
             for (i = 0; i < oprsz_16; i++) {
                 l = m[2 * i + 0];
                 h = m[2 * i + 1];
                 l = compress_bits(l >> odd, esz);
                 h = compress_bits(h >> odd, esz);
-                tmp_m.p[i] = l + (h << 32);
+                tmp_m.p[i] = l | (h << 32);
             }
-            tmp_m.p[i] = compress_bits(m[2 * i] >> odd, esz);
+            l = m[2 * i + 0];
+            h = m[2 * i + 1];
+            l = compress_bits(l >> odd, esz);
+            h = compress_bits(h >> odd, esz);
+            tmp_m.p[i] = l | (h << final_shift);
 
             swap_memmove(vd + oprsz / 2, &tmp_m, oprsz / 2);
         } else {
@@ -1978,7 +1990,7 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm, uint32_t pred_desc)
                 h = m[2 * i + 1];
                 l = compress_bits(l >> odd, esz);
                 h = compress_bits(h >> odd, esz);
-                d[oprsz_16 + i] = l + (h << 32);
+                d[oprsz_16 + i] = l | (h << 32);
             }
         }
     }
-- 
2.25.1