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>

diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c
index 296826ffe6aef2e9c191d03841fdd8e7dc316b75..1ee2690ceb5a293fdc23146b1a9b294b2b2c49a5 100644 (file)
--- a/target/arm/tcg/sme_helper.c
+++ b/target/arm/tcg/sme_helper.c
@@ -1037,10 +1037,9 @@ 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;
@@ -1073,10 +1072,9 @@ 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;