[PULL 08/29] target/arm: Fix SQDMULH (by element) with Q=0

[Peter Maydell]

From: Richard Henderson <richard.henderson@linaro.org>

The inner loop, bounded by eltspersegment, must not be
larger than the outer loop, bounded by elements.

Cc: qemu-stable@nongnu.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240625183536.1672454-3-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
 target/arm/tcg/vec_helper.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c
index 7b34cc98afe..d477479bb19 100644
--- a/target/arm/tcg/vec_helper.c
+++ b/target/arm/tcg/vec_helper.c
@@ -317,10 +317,12 @@ void HELPER(neon_sqdmulh_idx_h)(void *vd, void *vn, void 
*vm,
     intptr_t i, j, opr_sz = simd_oprsz(desc);
     int idx = simd_data(desc);
     int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+    intptr_t elements = opr_sz / 2;
+    intptr_t eltspersegment = MIN(16 / 2, elements);
 
-    for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+    for (i = 0; i < elements; i += 16 / 2) {
         int16_t mm = m[i];
-        for (j = 0; j < 16 / 2; ++j) {
+        for (j = 0; j < eltspersegment; ++j) {
             d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, vq);
         }
     }
@@ -333,10 +335,12 @@ void HELPER(neon_sqrdmulh_idx_h)(void *vd, void *vn, void 
*vm,
     intptr_t i, j, opr_sz = simd_oprsz(desc);
     int idx = simd_data(desc);
     int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx);
+    intptr_t elements = opr_sz / 2;
+    intptr_t eltspersegment = MIN(16 / 2, elements);
 
-    for (i = 0; i < opr_sz / 2; i += 16 / 2) {
+    for (i = 0; i < elements; i += 16 / 2) {
         int16_t mm = m[i];
-        for (j = 0; j < 16 / 2; ++j) {
+        for (j = 0; j < eltspersegment; ++j) {
             d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, vq);
         }
     }
@@ -512,10 +516,12 @@ void HELPER(neon_sqdmulh_idx_s)(void *vd, void *vn, void 
*vm,
     intptr_t i, j, opr_sz = simd_oprsz(desc);
     int idx = simd_data(desc);
     int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+    intptr_t elements = opr_sz / 4;
+    intptr_t eltspersegment = MIN(16 / 4, elements);
 
-    for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+    for (i = 0; i < elements; i += 16 / 4) {
         int32_t mm = m[i];
-        for (j = 0; j < 16 / 4; ++j) {
+        for (j = 0; j < eltspersegment; ++j) {
             d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, vq);
         }
     }
@@ -528,10 +534,12 @@ void HELPER(neon_sqrdmulh_idx_s)(void *vd, void *vn, void 
*vm,
     intptr_t i, j, opr_sz = simd_oprsz(desc);
     int idx = simd_data(desc);
     int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx);
+    intptr_t elements = opr_sz / 4;
+    intptr_t eltspersegment = MIN(16 / 4, elements);
 
-    for (i = 0; i < opr_sz / 4; i += 16 / 4) {
+    for (i = 0; i < elements; i += 16 / 4) {
         int32_t mm = m[i];
-        for (j = 0; j < 16 / 4; ++j) {
+        for (j = 0; j < eltspersegment; ++j) {
             d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, vq);
         }
     }
-- 
2.34.1