diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2024-06-25 11:35:24 -0700 |
|---|---|---|
| committer | Michael Tokarev <mjt@tls.msk.ru> | 2024-07-02 09:03:21 +0300 |
| commit | 10b9e0c546de7e73f6cfe9594cbdaf36384e6888 (patch) | |
| tree | 6be049b29d589f8b8dbce9cfa16c6f4291236251 | |
| parent | 50a8a6b4d6bdd423140d37b47779fc006c101e4c (diff) | |
| download | qemu-10b9e0c546de7e73f6cfe9594cbdaf36384e6888.zip qemu-10b9e0c546de7e73f6cfe9594cbdaf36384e6888.tar.gz qemu-10b9e0c546de7e73f6cfe9594cbdaf36384e6888.tar.bz2 | |
target/arm: Fix VCMLA Dd, Dn, Dm[idx]
The inner loop, bounded by eltspersegment, must not be
larger than the outer loop, bounded by elements.
Cc: qemu-stable@nongnu.org
Fixes: 18fc2405781 ("target/arm: Implement SVE fp complex multiply add (indexed)")
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2376
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20240625183536.1672454-2-richard.henderson@linaro.org
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
(cherry picked from commit 76bccf3cb9d9383da0128bbc6d1300cddbe3ae8f)
Signed-off-by: Michael Tokarev <mjt@tls.msk.ru>
| -rw-r--r-- | target/arm/tcg/vec_helper.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 1f93510..cc7cab3 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -843,7 +843,7 @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va, intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; intptr_t elements = opr_sz / sizeof(float16); - intptr_t eltspersegment = 16 / sizeof(float16); + intptr_t eltspersegment = MIN(16 / sizeof(float16), elements); intptr_t i, j; /* Shift boolean to the sign bit so we can xor to negate. */ @@ -905,7 +905,7 @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va, intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; intptr_t elements = opr_sz / sizeof(float32); - intptr_t eltspersegment = 16 / sizeof(float32); + intptr_t eltspersegment = MIN(16 / sizeof(float32), elements); intptr_t i, j; /* Shift boolean to the sign bit so we can xor to negate. */ |