target/arm: Fix SME FMOPA (16-bit), BFMOPA

Perform the loop increment unconditionally, not nested
within the predication.

Cc: qemu-stable@nongnu.org
Fixes: 3916841ac75 ("target/arm: Implement FMOPA, FMOPS (widening)")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1985
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org>
Message-id: 20231117193135.1180657-1-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 3efd8495735c69b863476e9003e624877382a72d)
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>

diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c
index 73dd838330f160584d4b3728756a330356ad5d37..88567736358baa0140b95115471525b381ed5a83 100644 (file)
--- a/target/arm/sme_helper.c
+++ b/target/arm/sme_helper.c
@@ -1070,10 +1070,9 @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn,
 
                         m = f16mop_adj_pair(m, pcol, 0);
                         *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd);
-
-                        col += 4;
-                        pcol >>= 4;
                     }
+                    col += 4;
+                    pcol >>= 4;
                 } while (col & 15);
             }
             row += 4;
@@ -1106,10 +1105,9 @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn,
 
                         m = f16mop_adj_pair(m, pcol, 0);
                         *a = bfdotadd(*a, n, m);
-
-                        col += 4;
-                        pcol >>= 4;
                     }
+                    col += 4;
+                    pcol >>= 4;
                 } while (col & 15);
             }
             row += 4;