diff options
| author | Richard Henderson <richard.henderson@linaro.org> | 2021-09-12 10:49:25 -0700 |
|---|---|---|
| committer | Michael Roth <michael.roth@amd.com> | 2021-12-15 07:13:27 -0600 |
| commit | 711bd602cc432e4ab0c4c59f19d6611302870248 (patch) | |
| tree | 75d049b884227be43476c1086baad07c1c16c1fe | |
| parent | e88636b4d46b91e130ae715b8d8b90f62e414428 (diff) | |
tcg/arm: Reduce vector alignment requirement for NEON
With arm32, the ABI gives us 8-byte alignment for the stack.
While it's possible to realign the stack to provide 16-byte alignment,
it's far easier to simply not encode 16-byte alignment in the
VLD1 and VST1 instructions that we emit.
Remove the assertion in temp_allocate_frame, limit natural alignment
to the provided stack alignment, and add a comment.
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1999878
Reported-by: Richard W.M. Jones <rjones@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-Id: <20210912174925.200132-1-richard.henderson@linaro.org>
Message-Id: <20211206191335.230683-2-richard.henderson@linaro.org>
(cherry picked from commit b9537d5904f6e3df896264a6144883ab07db9608)
Signed-off-by: Michael Roth <michael.roth@amd.com>
| -rw-r--r-- | tcg/arm/tcg-target.c.inc | 13 | ||||
| -rw-r--r-- | tcg/tcg.c | 8 |
2 files changed, 16 insertions, 5 deletions
diff --git a/tcg/arm/tcg-target.c.inc b/tcg/arm/tcg-target.c.inc index 007ceee68e..34acfb522c 100644 --- a/tcg/arm/tcg-target.c.inc +++ b/tcg/arm/tcg-target.c.inc @@ -2477,8 +2477,13 @@ static void tcg_out_ld(TCGContext *s, TCGType type, TCGReg arg, tcg_out_vldst(s, INSN_VLD1 | 0x7d0, arg, arg1, arg2); return; case TCG_TYPE_V128: - /* regs 2; size 8; align 16 */ - tcg_out_vldst(s, INSN_VLD1 | 0xae0, arg, arg1, arg2); + /* + * We have only 8-byte alignment for the stack per the ABI. + * Rather than dynamically re-align the stack, it's easier + * to simply not request alignment beyond that. So: + * regs 2; size 8; align 8 + */ + tcg_out_vldst(s, INSN_VLD1 | 0xad0, arg, arg1, arg2); return; default: g_assert_not_reached(); @@ -2497,8 +2502,8 @@ static void tcg_out_st(TCGContext *s, TCGType type, TCGReg arg, tcg_out_vldst(s, INSN_VST1 | 0x7d0, arg, arg1, arg2); return; case TCG_TYPE_V128: - /* regs 2; size 8; align 16 */ - tcg_out_vldst(s, INSN_VST1 | 0xae0, arg, arg1, arg2); + /* See tcg_out_ld re alignment: regs 2; size 8; align 8 */ + tcg_out_vldst(s, INSN_VST1 | 0xad0, arg, arg1, arg2); return; default: g_assert_not_reached(); @@ -3060,7 +3060,13 @@ static void temp_allocate_frame(TCGContext *s, TCGTemp *ts) g_assert_not_reached(); } - assert(align <= TCG_TARGET_STACK_ALIGN); + /* + * Assume the stack is sufficiently aligned. + * This affects e.g. ARM NEON, where we have 8 byte stack alignment + * and do not require 16 byte vector alignment. This seems slightly + * easier than fully parameterizing the above switch statement. + */ + align = MIN(TCG_TARGET_STACK_ALIGN, align); off = ROUND_UP(s->current_frame_offset, align); /* If we've exhausted the stack frame, restart with a smaller TB. */ |