Message ID | 20211220135700.615644-1-alankelly@google.com |
---|---|
State | New |
Headers | show |
Series | [FFmpeg-devel,1/2] libavutil/cpu: Add AV_CPU_FLAG_SLOW_GATHER. | expand |
Context | Check | Description |
---|---|---|
andriy/make_x86 | success | Make finished |
andriy/make_fate_x86 | success | Make fate finished |
andriy/make_ppc | success | Make finished |
andriy/make_fate_ppc | success | Make fate finished |
On 12/20/2021 10:57 AM, Alan Kelly wrote: > This is instead of EXTERNAL_AVX2_FAST so that the avx2 hscale functions > are only used where they are faster. > --- > libswscale/utils.c | 2 +- > libswscale/x86/swscale.c | 2 +- > tests/checkasm/sw_scale.c | 2 +- > 3 files changed, 3 insertions(+), 3 deletions(-) > > diff --git a/libswscale/utils.c b/libswscale/utils.c > index d4a72d3ce1..9a69b45afe 100644 > --- a/libswscale/utils.c > +++ b/libswscale/utils.c > @@ -282,7 +282,7 @@ void ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, int filterSiz > #if ARCH_X86_64 > int i, j, k, l; > int cpu_flags = av_get_cpu_flags(); > - if (EXTERNAL_AVX2_FAST(cpu_flags)){ > + if (cpu_flags & AV_CPU_FLAG_SLOW_GATHER) { The other way around. Like this you're enabling these functions only on CPUs with slow gather. The check needs to be if (EXTERNAL_AVX2_FAST(cpu_flags) && !(cpu_flags & AV_CPU_FLAG_SLOW_GATHER)) To ensure it's run on AVX2 enabled CPUs with both fast 256bits ops and fast gather. Same below. > if ((c->srcBpc == 8) && (c->dstBpc <= 14)){ > if (dstW % 16 == 0){ > if (filter != NULL){ > diff --git a/libswscale/x86/swscale.c b/libswscale/x86/swscale.c > index c49a05c37b..eb5334a2be 100644 > --- a/libswscale/x86/swscale.c > +++ b/libswscale/x86/swscale.c > @@ -578,7 +578,7 @@ switch(c->dstBpc){ \ > break; \ > } > > - if (EXTERNAL_AVX2_FAST(cpu_flags)) { > + if (cpu_flags & AV_CPU_FLAG_SLOW_GATHER) { > if ((c->srcBpc == 8) && (c->dstBpc <= 14)) { > if (c->chrDstW % 16 == 0) > ASSIGN_AVX2_SCALE_FUNC(c->hcScale, c->hChrFilterSize); > diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c > index f4912e6c2c..680562af08 100644 > --- a/tests/checkasm/sw_scale.c > +++ b/tests/checkasm/sw_scale.c > @@ -217,7 +217,7 @@ static void check_hscale(void) > } > ff_sws_init_scale(ctx); > memcpy(filterAvx2, filter, sizeof(uint16_t) * (SRC_PIXELS * MAX_FILTER_WIDTH + MAX_FILTER_WIDTH)); > - if (cpu_flags & AV_CPU_FLAG_AVX2) > + if (cpu_flags & AV_CPU_FLAG_SLOW_GATHER) > ff_shuffle_filter_coefficients(ctx, filterPosAvx, width, filterAvx2, SRC_PIXELS); > > if (check_func(ctx->hcScale, "hscale_%d_to_%d_width%d", ctx->srcBpc, ctx->dstBpc + 1, width)) {
diff --git a/libswscale/utils.c b/libswscale/utils.c index d4a72d3ce1..9a69b45afe 100644 --- a/libswscale/utils.c +++ b/libswscale/utils.c @@ -282,7 +282,7 @@ void ff_shuffle_filter_coefficients(SwsContext *c, int *filterPos, int filterSiz #if ARCH_X86_64 int i, j, k, l; int cpu_flags = av_get_cpu_flags(); - if (EXTERNAL_AVX2_FAST(cpu_flags)){ + if (cpu_flags & AV_CPU_FLAG_SLOW_GATHER) { if ((c->srcBpc == 8) && (c->dstBpc <= 14)){ if (dstW % 16 == 0){ if (filter != NULL){ diff --git a/libswscale/x86/swscale.c b/libswscale/x86/swscale.c index c49a05c37b..eb5334a2be 100644 --- a/libswscale/x86/swscale.c +++ b/libswscale/x86/swscale.c @@ -578,7 +578,7 @@ switch(c->dstBpc){ \ break; \ } - if (EXTERNAL_AVX2_FAST(cpu_flags)) { + if (cpu_flags & AV_CPU_FLAG_SLOW_GATHER) { if ((c->srcBpc == 8) && (c->dstBpc <= 14)) { if (c->chrDstW % 16 == 0) ASSIGN_AVX2_SCALE_FUNC(c->hcScale, c->hChrFilterSize); diff --git a/tests/checkasm/sw_scale.c b/tests/checkasm/sw_scale.c index f4912e6c2c..680562af08 100644 --- a/tests/checkasm/sw_scale.c +++ b/tests/checkasm/sw_scale.c @@ -217,7 +217,7 @@ static void check_hscale(void) } ff_sws_init_scale(ctx); memcpy(filterAvx2, filter, sizeof(uint16_t) * (SRC_PIXELS * MAX_FILTER_WIDTH + MAX_FILTER_WIDTH)); - if (cpu_flags & AV_CPU_FLAG_AVX2) + if (cpu_flags & AV_CPU_FLAG_SLOW_GATHER) ff_shuffle_filter_coefficients(ctx, filterPosAvx, width, filterAvx2, SRC_PIXELS); if (check_func(ctx->hcScale, "hscale_%d_to_%d_width%d", ctx->srcBpc, ctx->dstBpc + 1, width)) {