itx: Size optimizations for arm32, arm64 and riscv64

  arm32 saves 1424 bytes
  arm64 saves 2176 bytes
riscv64 saves 2918 bytes

arm32/itx: Reuse 4x16 epilog, saves 268 bytes
arm32/itx: Reuse 16x4 epilog, saves 220 bytes
arm32/itx: Reuse 8x16 epilog, saves 48 bytes
arm32/itx: Remove 16x8 variant, saves 528 bytes
arm32/itx: Reuse horz_16x4 epilog, saves 336 bytes
arm32/itx16: Reuse horz_16x2 epilog, saves 24 bytes

arm64/itx: Reuse 4x16 epilog, saves 312 bytes
arm64/itx: Reuse 16x4 epilog, saves 264 bytes
arm64/itx: Reuse 8x16 epilog, saves 424 bytes
arm64/itx: Reuse 16x8 epilog, saves 568 bytes
arm64/itx: Reuse horz_16x8 epilog, saves 512 bytes
arm64/itx16: Reuse horz_16x4 epilog, saves 96 bytes

riscv64/itx: Fix unrolled .irp loops, saves 12 bytes
riscv64/itx: Reuse 4x16 epilog, saves 642 bytes
riscv64/itx: Reuse 16x4 epilog, saves 354 bytes
riscv64/itx: Tail call vert_8x16, saves 1086 bytes
riscv64/itx: Reuse 8x16 epilog, saves 24 bytes
riscv64/itx: Reuse 16x8 epilog, saves 706 bytes
riscv64/itx: Reuse horz_16x8 epilog, saves 94 bytes

changed milestone to %1.4.1

added ARM RISC-V performance labels

requested review from @mstorsjo

added 18 commits

• dc018ddd...71d1faf5 - 8 earlier commits
• 30f19634 - riscv64/itx: Fix unrolled .irp loops, saves 12 bytes
• 8e2bd3a8 - riscv64/itx: Reuse 4x16 epilog, saves 642 bytes
• 982f00c1 - riscv64/itx: Reuse 16x4 epilog, saves 354 bytes
• b1a8250a - riscv64/itx: Tail call vert_8x16, saves 1086 bytes
• 5b8b4b67 - riscv64/itx: Reuse 8x16 epilog, saves 24 bytes
• 78f16524 - riscv64/itx: Reuse 16x8 epilog, saves 706 bytes
• 4f01f66e - arm32/itx: Reuse horz_16x4 epilog, saves 336 bytes
• 37a7659a - arm64/itx: Reuse horz_16x8 epilog, saves 512 bytes
• 01a075b4 - riscv64/itx: Reuse horz_16x8 epilog, saves 94 bytes
• daacb9cf - arm64/itx16: Reuse horz_16x4 epilog, saves 96 bytes

Compare with previous version

changed the description

added 12 commits

• daacb9cf...d5943101 - 2 earlier commits
• 1ffa7cb0 - riscv64/itx: Reuse 4x16 epilog, saves 642 bytes
• 2ff172af - riscv64/itx: Reuse 16x4 epilog, saves 354 bytes
• 292c165f - riscv64/itx: Tail call vert_8x16, saves 1086 bytes
• 86ac149b - riscv64/itx: Reuse 8x16 epilog, saves 24 bytes
• 467d8adc - riscv64/itx: Reuse 16x8 epilog, saves 706 bytes
• 9078f97a - arm32/itx: Reuse horz_16x4 epilog, saves 336 bytes
• 77e7167a - arm64/itx: Reuse horz_16x8 epilog, saves 512 bytes
• 2c554c21 - riscv64/itx: Reuse horz_16x8 epilog, saves 94 bytes
• 441f34d9 - arm32/itx16: Reuse horz_16x2 epilog, saves 24 bytes
• 40f70760 - arm64/itx16: Reuse horz_16x4 epilog, saves 96 bytes

Compare with previous version

changed the description

added 2 commits

• 6c8d9126 - arm32/itx16: Reuse horz_16x2 epilog, saves 24 bytes
• c5bcc351 - arm64/itx16: Reuse horz_16x4 epilog, saves 96 bytes

Compare with previous version

resolved all threads

added 12 commits

• c5bcc351...a9b627e1 - 2 earlier commits
• 97e85823 - riscv64/itx: Reuse 4x16 epilog, saves 642 bytes
• 8e1f4401 - riscv64/itx: Reuse 16x4 epilog, saves 354 bytes
• 434cab7e - riscv64/itx: Tail call vert_8x16, saves 1086 bytes
• 09f12161 - riscv64/itx: Reuse 8x16 epilog, saves 24 bytes
• 30a34c7a - riscv64/itx: Reuse 16x8 epilog, saves 706 bytes
• d4157fd4 - arm32/itx: Reuse horz_16x4 epilog, saves 336 bytes
• 27d08375 - arm64/itx: Reuse horz_16x8 epilog, saves 512 bytes
• 0efd6a6b - riscv64/itx: Reuse horz_16x8 epilog, saves 94 bytes
• 94c04123 - arm32/itx16: Reuse horz_16x2 epilog, saves 24 bytes
• 27d7bb06 - arm64/itx16: Reuse horz_16x4 epilog, saves 96 bytes

Compare with previous version

requested review from @mstorsjo

approved this merge request

added 25 commits

• 27d7bb06...d22de29c - 4 commits from branch videolan:master
• d22de29c...e7378375 - 11 earlier commits
• 311816b4 - riscv64/itx: Reuse 4x16 epilog, saves 642 bytes
• 1830c9b5 - riscv64/itx: Reuse 16x4 epilog, saves 354 bytes
• be47dfcd - riscv64/itx: Tail call vert_8x16, saves 1086 bytes
• 45857634 - riscv64/itx: Reuse 8x16 epilog, saves 24 bytes
• 6e5d1df6 - riscv64/itx: Reuse 16x8 epilog, saves 706 bytes
• 6249bd88 - arm32/itx: Reuse horz_16x4 epilog, saves 336 bytes
• f15b0731 - arm64/itx: Reuse horz_16x8 epilog, saves 512 bytes
• 4bb0005c - riscv64/itx: Reuse horz_16x8 epilog, saves 94 bytes
• 28c7e530 - arm32/itx16: Reuse horz_16x2 epilog, saves 24 bytes
• 7be30df4 - arm64/itx16: Reuse horz_16x4 epilog, saves 96 bytes

Compare with previous version

merged