[FFmpeg-cvslog] lavc/aacpsdsp: fix clobber on RISC-V LP64D/ILP32D

[Rémi Denis-Courmont]

ffmpeg | branch: master | Rémi Denis-Courmont <remi at remlab.net> | Thu Oct  6 21:46:12 2022 +0300| [105921251ab35b870887e0c7348016f4dff3ec5b] | committer: Lynne

lavc/aacpsdsp: fix clobber on RISC-V LP64D/ILP32D

Although the DSP function only uses single precision from RISC-V F, the
caller may leave double precision values in the spilled registers if the
calling convention supports double precision hardware floats. Then, we
need to save and restore FS registers as double precision.

Conversely, we do not need to save anything at all if an integer calling
convention is in use. However we can assume that single precision floats
are supported, since the Zve32f extension implies the F extension.
So for the sake of simplicity, we always save at least single precision
values.

In theory, we should even save quadruple precision values if the LP64Q
ABI is in use. I have yet to see a compiler that supports it though.

> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=105921251ab35b870887e0c7348016f4dff3ec5b
---

 libavcodec/riscv/aacpsdsp_rvv.S | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/libavcodec/riscv/aacpsdsp_rvv.S b/libavcodec/riscv/aacpsdsp_rvv.S
index 1d6e73fd2d..80bd19f6ad 100644
--- a/libavcodec/riscv/aacpsdsp_rvv.S
+++ b/libavcodec/riscv/aacpsdsp_rvv.S
@@ -55,9 +55,10 @@ endfunc
 
 func ff_ps_hybrid_analysis_rvv, zve32f
         /* We need 26 FP registers, for 20 scratch ones. Spill fs0-fs5. */
-        addi    sp, sp, -32
+        addi    sp, sp, -48
         .irp n, 0, 1, 2, 3, 4, 5
-        fsw     fs\n, (4 * \n)(sp)
+HWD     fsd     fs\n, (8 * \n)(sp)
+NOHWD   fsw     fs\n, (4 * \n)(sp)
         .endr
 
         .macro input, j, fd0, fd1, fd2, fd3
@@ -142,9 +143,10 @@ func ff_ps_hybrid_analysis_rvv, zve32f
         bnez       a4, 1b
 
         .irp n, 5, 4, 3, 2, 1, 0
-        flw     fs\n, (4 * \n)(sp)
+HWD     fld     fs\n, (8 * \n)(sp)
+NOHWD   flw     fs\n, (4 * \n)(sp)
         .endr
-        addi    sp, sp, 32
+        addi    sp, sp, 48
         ret
         .purgem input
         .purgem filter