From 6ab4b92e82ea585aac44bd0342f841a8ba45bb66 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?R=C3=A9mi=20Denis-Courmont?= Date: Tue, 14 May 2024 22:15:43 +0300 Subject: [PATCH] lavc/flacdsp: optimise RVV vector type for lpc16 This calculates the optimal vector type value at run-time based on the hardware vector length and the FLAC LPC prediction order. In this particular case, the additional computation is easily amortised over the loop iterations: T-Head C908: C V before V after 1 48.0 214.7 95.2 2 64.7 214.2 94.7 3 79.7 213.5 94.5 4 96.2 196.5 94.2 # 5 111.0 195.7 118.5 6 127.0 211.2 102.0 7 143.7 194.2 101.5 8 175.7 193.2 101.2 # 9 176.2 224.2 126.0 10 191.5 192.0 125.5 11 224.5 191.2 124.7 12 223.0 190.2 124.2 13 239.2 189.5 123.7 14 253.7 188.7 139.5 15 286.2 188.0 122.7 16 284.0 187.0 122.5 # 17 300.2 186.5 186.5 18 314.0 185.5 185.7 19 329.7 184.7 185.0 20 343.0 184.2 184.2 21 358.7 199.2 183.7 22 371.7 182.7 182.7 23 387.5 181.7 182.0 24 400.7 181.0 181.2 25 431.5 180.2 196.5 26 443.7 195.5 196.0 27 459.0 178.7 196.2 28 470.7 177.7 194.2 29 470.0 177.0 193.5 30 481.2 176.2 176.5 31 496.2 175.5 175.7 32 507.2 174.7 191.0 # # Power of two boundary. With 128-bit vectors, improvements are expected for the first two test cases only. For the other two, there is overhead but below noise. Improvements should be better observable with prediction order of 8 and less, or on hardware with larger vector sizes. --- libavcodec/riscv/flacdsp_init.c | 2 +- libavcodec/riscv/flacdsp_rvv.S | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/libavcodec/riscv/flacdsp_init.c b/libavcodec/riscv/flacdsp_init.c index 4f1652dbe7..735aec0691 100644 --- a/libavcodec/riscv/flacdsp_init.c +++ b/libavcodec/riscv/flacdsp_init.c @@ -71,7 +71,7 @@ av_cold void ff_flacdsp_init_riscv(FLACDSPContext *c, enum AVSampleFormat fmt, if ((flags & AV_CPU_FLAG_RVV_I32) && (flags & AV_CPU_FLAG_RVB_ADDR)) { int vlenb = ff_get_rv_vlenb(); - if (vlenb >= 16) + if ((flags & AV_CPU_FLAG_RVB_BASIC) && vlenb >= 16) c->lpc16 = ff_flac_lpc16_rvv; # if (__riscv_xlen >= 64) diff --git a/libavcodec/riscv/flacdsp_rvv.S b/libavcodec/riscv/flacdsp_rvv.S index 6287faa260..e1a20ce8e1 100644 --- a/libavcodec/riscv/flacdsp_rvv.S +++ b/libavcodec/riscv/flacdsp_rvv.S @@ -20,8 +20,9 @@ #include "libavutil/riscv/asm.S" -func ff_flac_lpc16_rvv, zve32x - vsetvli zero, a2, e32, m8, ta, ma +func ff_flac_lpc16_rvv, zve32x, zbb + vtype_vli t0, a2, t2, e32, ta, ma + vsetvl zero, a2, t0 vle32.v v8, (a1) sub a4, a4, a2 vle32.v v16, (a0)