[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[PULL 10/39] target/arm: Fix sve_uzp_p vs odd vector lengths
From: |
Peter Maydell |
Subject: |
[PULL 10/39] target/arm: Fix sve_uzp_p vs odd vector lengths |
Date: |
Fri, 12 Mar 2021 13:51:11 +0000 |
From: Richard Henderson <richard.henderson@linaro.org>
Missed out on compressing the second half of a predicate
with length vl % 512 > 256.
Adjust all of the x + (y << s) to x | (y << s) as a
general style fix. Drop the extract64 because the input
uint64_t are known to be already zero-extended from the
current size of the predicate.
Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210309155305.11301-2-richard.henderson@linaro.org
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
---
target/arm/sve_helper.c | 30 +++++++++++++++++++++---------
1 file changed, 21 insertions(+), 9 deletions(-)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 844db08bd57..11c9397dbb6 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -1939,7 +1939,7 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm,
uint32_t pred_desc)
if (oprsz <= 8) {
l = compress_bits(n[0] >> odd, esz);
h = compress_bits(m[0] >> odd, esz);
- d[0] = extract64(l + (h << (4 * oprsz)), 0, 8 * oprsz);
+ d[0] = l | (h << (4 * oprsz));
} else {
ARMPredicateReg tmp_m;
intptr_t oprsz_16 = oprsz / 16;
@@ -1953,23 +1953,35 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm,
uint32_t pred_desc)
h = n[2 * i + 1];
l = compress_bits(l >> odd, esz);
h = compress_bits(h >> odd, esz);
- d[i] = l + (h << 32);
+ d[i] = l | (h << 32);
}
- /* For VL which is not a power of 2, the results from M do not
- align nicely with the uint64_t for D. Put the aligned results
- from M into TMP_M and then copy it into place afterward. */
+ /*
+ * For VL which is not a multiple of 512, the results from M do not
+ * align nicely with the uint64_t for D. Put the aligned results
+ * from M into TMP_M and then copy it into place afterward.
+ */
if (oprsz & 15) {
- d[i] = compress_bits(n[2 * i] >> odd, esz);
+ int final_shift = (oprsz & 15) * 2;
+
+ l = n[2 * i + 0];
+ h = n[2 * i + 1];
+ l = compress_bits(l >> odd, esz);
+ h = compress_bits(h >> odd, esz);
+ d[i] = l | (h << final_shift);
for (i = 0; i < oprsz_16; i++) {
l = m[2 * i + 0];
h = m[2 * i + 1];
l = compress_bits(l >> odd, esz);
h = compress_bits(h >> odd, esz);
- tmp_m.p[i] = l + (h << 32);
+ tmp_m.p[i] = l | (h << 32);
}
- tmp_m.p[i] = compress_bits(m[2 * i] >> odd, esz);
+ l = m[2 * i + 0];
+ h = m[2 * i + 1];
+ l = compress_bits(l >> odd, esz);
+ h = compress_bits(h >> odd, esz);
+ tmp_m.p[i] = l | (h << final_shift);
swap_memmove(vd + oprsz / 2, &tmp_m, oprsz / 2);
} else {
@@ -1978,7 +1990,7 @@ void HELPER(sve_uzp_p)(void *vd, void *vn, void *vm,
uint32_t pred_desc)
h = m[2 * i + 1];
l = compress_bits(l >> odd, esz);
h = compress_bits(h >> odd, esz);
- d[oprsz_16 + i] = l + (h << 32);
+ d[oprsz_16 + i] = l | (h << 32);
}
}
}
--
2.20.1
- [PULL 27/39] hw/misc: Add NPCM7XX MFT Module, (continued)
- [PULL 27/39] hw/misc: Add NPCM7XX MFT Module, Peter Maydell, 2021/03/12
- [PULL 29/39] hw/arm: Connect PWM fans in NPCM7XX boards, Peter Maydell, 2021/03/12
- [PULL 35/39] hw/display/pxa2xx_lcd: Remove dest_width state field, Peter Maydell, 2021/03/12
- [PULL 26/39] hw/misc: Add GPIOs for duty in NPCM7xx PWM, Peter Maydell, 2021/03/12
- [PULL 34/39] hw/display/pxa2xx_lcd: Remove dead code for non-32-bpp surfaces, Peter Maydell, 2021/03/12
- [PULL 16/39] target/arm: Update WHILE for PREDDESC, Peter Maydell, 2021/03/12
- [PULL 23/39] hw/timer/sse-timer: Propagate eventual error in sse_timer_realize(), Peter Maydell, 2021/03/12
- [PULL 12/39] target/arm: Fix sve_punpk_p vs odd vector lengths, Peter Maydell, 2021/03/12
- [PULL 19/39] tests/acceptance/boot_linux_console: remove Armbian 19.11.3 bionic test for orangepi-pc machine, Peter Maydell, 2021/03/12
- [PULL 20/39] tests/acceptance/boot_linux_console: change URL for test_arm_orangepi_bionic_20_08, Peter Maydell, 2021/03/12
- [PULL 10/39] target/arm: Fix sve_uzp_p vs odd vector lengths,
Peter Maydell <=
- [PULL 25/39] hw/arm/virt: KVM: The IPA lower bound is 32, Peter Maydell, 2021/03/12
- [PULL 22/39] tests/acceptance: drop ARMBIAN_ARTIFACTS_CACHED condition for orangepi-pc, cubieboard tests, Peter Maydell, 2021/03/12
- [PULL 30/39] tests/qtest: Test PWM fan RPM using MFT in PWM test, Peter Maydell, 2021/03/12
- [PULL 31/39] hw/display/pl110: Remove dead code for non-32-bpp surfaces, Peter Maydell, 2021/03/12
- [PULL 32/39] hw/display/pl110: Pull included-once parts of template header into pl110.c, Peter Maydell, 2021/03/12
- [PULL 28/39] hw/arm: Add MFT device to NPCM7xx Soc, Peter Maydell, 2021/03/12
- [PULL 33/39] hw/display/pl110: Remove use of BITS from pl110_template.h, Peter Maydell, 2021/03/12
- [PULL 37/39] hw/display/pxa2xx: Apply brace-related coding style fixes to template header, Peter Maydell, 2021/03/12
- [PULL 38/39] hw/display/pxa2xx: Apply whitespace-only coding style fixes to template header, Peter Maydell, 2021/03/12
- [PULL 39/39] hw/display/pxa2xx: Inline template header, Peter Maydell, 2021/03/12