diff options
| author | Reimar Döffinger <Reimar.Doeffinger@gmx.de> | 2022-10-09 21:17:47 +0200 |
|---|---|---|
| committer | Reimar Döffinger <Reimar.Doeffinger@gmx.de> | 2022-10-11 09:12:02 +0200 |
| commit | 38cd829dce7184400c944ead299a11e57c8ec7f8 (patch) | |
| tree | 1003ec1a6835e3aa61dd47aca9af74e9de7750c3 /libavutil/aarch64 | |
| parent | e10e27a2ead8848648b29a1b397cc240206e9c3d (diff) | |
aarch64: Implement stack spilling in a consistent way.
Currently it is done in several different ways, which
might cause needless dependencies or in case of
tx_float_neon.S is incorrect.
Reviewed-by: Martin Storsjö <martin@martin.st>
Signed-off-by: Reimar Döffinger <Reimar.Doeffinger@gmx.de>
Diffstat (limited to 'libavutil/aarch64')
| -rw-r--r-- | libavutil/aarch64/tx_float_neon.S | 52 |
1 files changed, 26 insertions, 26 deletions
diff --git a/libavutil/aarch64/tx_float_neon.S b/libavutil/aarch64/tx_float_neon.S index 4126c3b812..e5531dcc7c 100644 --- a/libavutil/aarch64/tx_float_neon.S +++ b/libavutil/aarch64/tx_float_neon.S @@ -866,10 +866,10 @@ FFT16_FN ns_float, 1 .macro FFT32_FN name, no_perm function ff_tx_fft32_\name\()_neon, export=1 - stp d8, d9, [sp, #-16] - stp d10, d11, [sp, #-32] - stp d12, d13, [sp, #-48] - stp d14, d15, [sp, #-64] + stp d14, d15, [sp, #-16*4]! + stp d8, d9, [sp, #16*3] + stp d10, d11, [sp, #16*2] + stp d12, d13, [sp, #16] LOAD_SUBADD SETUP_SR_RECOMB 32, x7, x8, x9 @@ -911,10 +911,10 @@ function ff_tx_fft32_\name\()_neon, export=1 zip2 v31.2d, v11.2d, v15.2d st1 { v28.4s, v29.4s, v30.4s, v31.4s }, [x1] - ldp d14, d15, [sp, #-64] - ldp d12, d13, [sp, #-48] - ldp d10, d11, [sp, #-32] - ldp d8, d9, [sp, #-16] + ldp d12, d13, [sp, #16] + ldp d10, d11, [sp, #16*2] + ldp d8, d9, [sp, #16*3] + ldp d14, d15, [sp], #16*4 ret endfunc @@ -966,12 +966,12 @@ FFT32_FN ns_float, 1 .macro FFT_SPLIT_RADIX_FN name, no_perm function ff_tx_fft_sr_\name\()_neon, export=1 - stp d8, d9, [sp, #-16]! - stp d10, d11, [sp, #-16]! - stp d12, d13, [sp, #-16]! - stp d14, d15, [sp, #-16]! - stp x19, x20, [sp, #-16]! - stp x21, x22, [sp, #-16]! + stp x21, x22, [sp, #-16*6]! + stp d8, d9, [sp, #16*5] + stp d10, d11, [sp, #16*4] + stp d12, d13, [sp, #16*3] + stp d14, d15, [sp, #16*2] + stp x19, x20, [sp, #16] ldr w19, [x0, #0] // global target mov w20, w19 // local length @@ -1185,12 +1185,12 @@ SR_TRANSFORM_DEF 131072 subs w19, w19, #32*4 b.gt 0b - ldp x21, x22, [sp], #16 - ldp x19, x20, [sp], #16 - ldp d14, d15, [sp], #16 - ldp d12, d13, [sp], #16 - ldp d10, d11, [sp], #16 - ldp d8, d9, [sp], #16 + ldp x19, x20, [sp, #16] + ldp d14, d15, [sp, #16*2] + ldp d12, d13, [sp, #16*3] + ldp d10, d11, [sp, #16*4] + ldp d8, d9, [sp, #16*5] + ldp x21, x22, [sp], #16*6 ret @@ -1279,12 +1279,12 @@ SR_TRANSFORM_DEF 131072 zip2 v7.2d, v15.2d, v23.2d st1 { v4.4s, v5.4s, v6.4s, v7.4s }, [x15] - ldp x21, x22, [sp], #16 - ldp x19, x20, [sp], #16 - ldp d14, d15, [sp], #16 - ldp d12, d13, [sp], #16 - ldp d10, d11, [sp], #16 - ldp d8, d9, [sp], #16 + ldp x19, x20, [sp, #16] + ldp d14, d15, [sp, #16*2] + ldp d12, d13, [sp, #16*3] + ldp d10, d11, [sp, #16*4] + ldp d8, d9, [sp, #16*5] + ldp x21, x22, [sp], #16*6 ret endfunc |