54 lines
2.3 KiB
Diff
54 lines
2.3 KiB
Diff
|
From fe9725eed4d9be8e14d2c3865f1d7d5f24cbdd73 Mon Sep 17 00:00:00 2001
|
||
|
|
From: gubin <gubin_yewu@cmss.chinamobile.com>
|
||
|
|
Date: Thu, 28 Nov 2024 14:21:15 +0800
|
||
|
|
Subject: [PATCH] target/arm: Fix A64 scalar SQSHRN and SQRSHRN
|
||
|
|
|
||
|
|
cherry-pick from 6fffc8378562c7fea6290c430b4f653f830a4c1a
|
||
|
|
|
||
|
|
In commit 1b7bc9b5c8bf374dd we changed handle_vec_simd_sqshrn() so
|
||
|
|
that instead of starting with a 0 value and depositing in each new
|
||
|
|
element from the narrowing operation, it instead started with the raw
|
||
|
|
result of the narrowing operation of the first element.
|
||
|
|
|
||
|
|
This is fine in the vector case, because the deposit operations for
|
||
|
|
the second and subsequent elements will always overwrite any higher
|
||
|
|
bits that might have been in the first element's result value in
|
||
|
|
tcg_rd. However in the scalar case we only go through this loop
|
||
|
|
once. The effect is that for a signed narrowing operation, if the
|
||
|
|
result is negative then we will now return a value where the bits
|
||
|
|
above the first element are incorrectly 1 (because the narrowfn
|
||
|
|
returns a sign-extended result, not one that is truncated to the
|
||
|
|
element size).
|
||
|
|
|
||
|
|
Fix this by using an extract operation to get exactly the correct
|
||
|
|
bits of the output of the narrowfn for element 1, instead of a
|
||
|
|
plain move.
|
||
|
|
|
||
|
|
Cc: qemu-stable@nongnu.org
|
||
|
|
Fixes: 1b7bc9b5c8bf374dd3 ("target/arm: Avoid tcg_const_ptr in handle_vec_simd_sqshrn")
|
||
|
|
Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2089
|
||
|
|
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
|
||
|
|
Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
|
||
|
|
Message-id: 20240123153416.877308-1-peter.maydell@linaro.org
|
||
|
|
Signed-off-by: gubin <gubin_yewu@cmss.chinamobile.com>
|
||
|
|
---
|
||
|
|
target/arm/tcg/translate-a64.c | 2 +-
|
||
|
|
1 file changed, 1 insertion(+), 1 deletion(-)
|
||
|
|
|
||
|
|
diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c
|
||
|
|
index 5560a53630..a05182b57f 100644
|
||
|
|
--- a/target/arm/tcg/translate-a64.c
|
||
|
|
+++ b/target/arm/tcg/translate-a64.c
|
||
|
|
@@ -8221,7 +8221,7 @@ static void handle_vec_simd_sqshrn(DisasContext *s, bool is_scalar, bool is_q,
|
||
|
|
narrowfn(tcg_rd_narrowed, tcg_env, tcg_rd);
|
||
|
|
tcg_gen_extu_i32_i64(tcg_rd, tcg_rd_narrowed);
|
||
|
|
if (i == 0) {
|
||
|
|
- tcg_gen_mov_i64(tcg_final, tcg_rd);
|
||
|
|
+ tcg_gen_extract_i64(tcg_final, tcg_rd, 0, esize);
|
||
|
|
} else {
|
||
|
|
tcg_gen_deposit_i64(tcg_final, tcg_final, tcg_rd, esize * i, esize);
|
||
|
|
}
|
||
|
|
--
|
||
|
|
2.41.0.windows.1
|
||
|
|
|