[Mesa-dev] [PATCH] r600g: improve flushed depth texture handling v2
Vadim Girlin
vadimgirlin at gmail.com
Thu Jun 28 07:02:17 PDT 2012
On Tue, 2012-06-26 at 19:40 -0400, Alex Deucher wrote:
> On Tue, Jun 26, 2012 at 7:34 PM, Vadim Girlin <vadimgirlin at gmail.com> wrote:
> > Use r600_resource_texture::flished_depth_texture for GPU access, and
> > allocate it in the VRAM. For transfers we'll allocate untiled texture in the
> > GTT and store it in the r600_transfer::staging.
> >
> > Improves performance when flushed depth texture is frequently used by the
> > GPU (about 30% for Lightsmark).
> >
> > Signed-off-by: Vadim Girlin <vadimgirlin at gmail.com>
> > ---
> >
> > Fixes fbo-clear-formats, fbo-generatemipmap-formats, no regressions on
> > evergreen
>
> This looks similar to Fredrik's patch:
> http://people.freedesktop.org/~fredrik/0001-r600g-be-smarter-about-domain-selection-for-depth-te.patch
Yes, generally the idea is the same. My patch also drops
R600_RESOURCE_FLAG_TRANSFER for the VRAM case, resulting in further
performance improvement. I've noticed 2x-3x fps boost in some scenes of
the Lightsmark after dropping this flag (e.g. "hard shadows" scene, also
the scene right after "penumbra shadows"), though I'm not sure yet why
it's so significant, will look into it.
Vadim
> Although I think your patch cleans things up a bit nicer.
>
> Alex
>
> >
> > src/gallium/drivers/r600/evergreen_state.c | 5 +-
> > src/gallium/drivers/r600/r600_blit.c | 21 +++---
> > src/gallium/drivers/r600/r600_pipe.h | 4 +-
> > src/gallium/drivers/r600/r600_resource.h | 6 +-
> > src/gallium/drivers/r600/r600_state.c | 2 +-
> > src/gallium/drivers/r600/r600_texture.c | 106 ++++++++++++++++------------
> > 6 files changed, 83 insertions(+), 61 deletions(-)
> >
> > diff --git a/src/gallium/drivers/r600/evergreen_state.c b/src/gallium/drivers/r600/evergreen_state.c
> > index f0fdd2b..2aa5ccb 100644
> > --- a/src/gallium/drivers/r600/evergreen_state.c
> > +++ b/src/gallium/drivers/r600/evergreen_state.c
> > @@ -988,7 +988,7 @@ static struct pipe_sampler_view *evergreen_create_sampler_view(struct pipe_conte
> > }
> >
> > if (tmp->is_depth && !tmp->is_flushing_texture) {
> > - r600_init_flushed_depth_texture(ctx, texture);
> > + r600_init_flushed_depth_texture(ctx, texture, NULL);
> > tmp = tmp->flushed_depth_texture;
> > if (!tmp) {
> > FREE(view);
> > @@ -1314,7 +1314,8 @@ static void evergreen_cb(struct r600_context *rctx, struct r600_pipe_state *rsta
> > rctx->have_depth_fb = TRUE;
> >
> > if (rtex->is_depth && !rtex->is_flushing_texture) {
> > - r600_init_flushed_depth_texture(&rctx->context, state->cbufs[cb]->texture);
> > + r600_init_flushed_depth_texture(&rctx->context,
> > + state->cbufs[cb]->texture, NULL);
> > rtex = rtex->flushed_depth_texture;
> > assert(rtex);
> > }
> > diff --git a/src/gallium/drivers/r600/r600_blit.c b/src/gallium/drivers/r600/r600_blit.c
> > index 031cd39..90d1992 100644
> > --- a/src/gallium/drivers/r600/r600_blit.c
> > +++ b/src/gallium/drivers/r600/r600_blit.c
> > @@ -114,13 +114,17 @@ static unsigned u_num_layers(struct pipe_resource *r, unsigned level)
> > }
> > }
> >
> > -void r600_blit_uncompress_depth(struct pipe_context *ctx, struct r600_resource_texture *texture)
> > +void r600_blit_uncompress_depth(struct pipe_context *ctx,
> > + struct r600_resource_texture *texture,
> > + struct r600_resource_texture *staging)
> > {
> > struct r600_context *rctx = (struct r600_context *)ctx;
> > unsigned layer, level;
> > float depth = 1.0f;
> > + struct r600_resource_texture *flushed_depth_texture = staging ?
> > + staging : texture->flushed_depth_texture;
> >
> > - if (!texture->dirty_db)
> > + if (!staging && !texture->dirty_db)
> > return;
> >
> > if (rctx->family == CHIP_RV610 || rctx->family == CHIP_RV630 ||
> > @@ -141,10 +145,10 @@ void r600_blit_uncompress_depth(struct pipe_context *ctx, struct r600_resource_t
> >
> > zsurf = ctx->create_surface(ctx, &texture->resource.b.b, &surf_tmpl);
> >
> > - surf_tmpl.format = texture->flushed_depth_texture->real_format;
> > + surf_tmpl.format = flushed_depth_texture->real_format;
> > surf_tmpl.usage = PIPE_BIND_RENDER_TARGET;
> > cbsurf = ctx->create_surface(ctx,
> > - (struct pipe_resource*)texture->flushed_depth_texture, &surf_tmpl);
> > + (struct pipe_resource*)flushed_depth_texture, &surf_tmpl);
> >
> > r600_blitter_begin(ctx, R600_DECOMPRESS);
> > util_blitter_custom_depth_stencil(rctx->blitter, zsurf, cbsurf, rctx->custom_dsa_flush, depth);
> > @@ -155,7 +159,8 @@ void r600_blit_uncompress_depth(struct pipe_context *ctx, struct r600_resource_t
> > }
> > }
> >
> > - texture->dirty_db = FALSE;
> > + if (!staging)
> > + texture->dirty_db = FALSE;
> > }
> >
> > void r600_flush_depth_textures(struct r600_context *rctx)
> > @@ -178,7 +183,7 @@ void r600_flush_depth_textures(struct r600_context *rctx)
> > if (tex->is_flushing_texture)
> > continue;
> >
> > - r600_blit_uncompress_depth(&rctx->context, tex);
> > + r600_blit_uncompress_depth(&rctx->context, tex, NULL);
> > }
> >
> > /* also check CB here */
> > @@ -192,7 +197,7 @@ void r600_flush_depth_textures(struct r600_context *rctx)
> > if (tex->is_flushing_texture)
> > continue;
> >
> > - r600_blit_uncompress_depth(&rctx->context, tex);
> > + r600_blit_uncompress_depth(&rctx->context, tex, NULL);
> > }
> > }
> >
> > @@ -342,7 +347,7 @@ static void r600_resource_copy_region(struct pipe_context *ctx,
> > }
> >
> > if (rsrc->is_depth && !rsrc->is_flushing_texture)
> > - r600_texture_depth_flush(ctx, src);
> > + r600_texture_depth_flush(ctx, src, NULL);
> >
> > restore_orig[0] = restore_orig[1] = FALSE;
> >
> > diff --git a/src/gallium/drivers/r600/r600_pipe.h b/src/gallium/drivers/r600/r600_pipe.h
> > index 82c4a12..032a6ec 100644
> > --- a/src/gallium/drivers/r600/r600_pipe.h
> > +++ b/src/gallium/drivers/r600/r600_pipe.h
> > @@ -426,7 +426,9 @@ void evergreen_update_dual_export_state(struct r600_context * rctx);
> >
> > /* r600_blit.c */
> > void r600_init_blit_functions(struct r600_context *rctx);
> > -void r600_blit_uncompress_depth(struct pipe_context *ctx, struct r600_resource_texture *texture);
> > +void r600_blit_uncompress_depth(struct pipe_context *ctx,
> > + struct r600_resource_texture *texture,
> > + struct r600_resource_texture *staging);
> > void r600_flush_depth_textures(struct r600_context *rctx);
> >
> > /* r600_buffer.c */
> > diff --git a/src/gallium/drivers/r600/r600_resource.h b/src/gallium/drivers/r600/r600_resource.h
> > index 13fce00..c02fae1 100644
> > --- a/src/gallium/drivers/r600/r600_resource.h
> > +++ b/src/gallium/drivers/r600/r600_resource.h
> > @@ -88,9 +88,11 @@ static INLINE struct r600_resource *r600_resource(struct pipe_resource *r)
> > }
> >
> > void r600_init_flushed_depth_texture(struct pipe_context *ctx,
> > - struct pipe_resource *texture);
> > + struct pipe_resource *texture,
> > + struct r600_resource_texture **staging);
> > void r600_texture_depth_flush(struct pipe_context *ctx,
> > - struct pipe_resource *texture);
> > + struct pipe_resource *texture,
> > + struct r600_resource_texture **staging);
> >
> > /* r600_texture.c texture transfer functions. */
> > struct pipe_transfer* r600_texture_get_transfer(struct pipe_context *ctx,
> > diff --git a/src/gallium/drivers/r600/r600_state.c b/src/gallium/drivers/r600/r600_state.c
> > index bb72bf8..96344fe 100644
> > --- a/src/gallium/drivers/r600/r600_state.c
> > +++ b/src/gallium/drivers/r600/r600_state.c
> > @@ -1000,7 +1000,7 @@ static struct pipe_sampler_view *r600_create_sampler_view(struct pipe_context *c
> > }
> >
> > if (tmp->is_depth && !tmp->is_flushing_texture) {
> > - r600_init_flushed_depth_texture(ctx, texture);
> > + r600_init_flushed_depth_texture(ctx, texture, NULL);
> > tmp = tmp->flushed_depth_texture;
> > if (!tmp) {
> > FREE(view);
> > diff --git a/src/gallium/drivers/r600/r600_texture.c b/src/gallium/drivers/r600/r600_texture.c
> > index 2368126..e24fcb3 100644
> > --- a/src/gallium/drivers/r600/r600_texture.c
> > +++ b/src/gallium/drivers/r600/r600_texture.c
> > @@ -298,7 +298,8 @@ static int r600_init_surface(struct radeon_surface *surface,
> > if (ptex->bind & PIPE_BIND_SCANOUT) {
> > surface->flags |= RADEON_SURF_SCANOUT;
> > }
> > - if (util_format_is_depth_and_stencil(ptex->format) && !is_transfer) {
> > + if ((ptex->bind & PIPE_BIND_DEPTH_STENCIL) &&
> > + util_format_is_depth_and_stencil(ptex->format) && !is_transfer) {
> > surface->flags |= RADEON_SURF_ZBUFFER;
> > surface->flags |= RADEON_SURF_SBUFFER;
> > }
> > @@ -517,7 +518,7 @@ r600_texture_create_object(struct pipe_screen *screen,
> > rtex->real_format = base->format;
> >
> > /* We must split depth and stencil into two separate buffers on Evergreen. */
> > - if (!(base->flags & R600_RESOURCE_FLAG_TRANSFER) &&
> > + if ((base->bind & PIPE_BIND_DEPTH_STENCIL) &&
> > ((struct r600_screen*)screen)->chip_class >= EVERGREEN &&
> > util_format_is_depth_and_stencil(base->format) &&
> > !rscreen->use_surface_alloc) {
> > @@ -561,7 +562,8 @@ r600_texture_create_object(struct pipe_screen *screen,
> > }
> >
> > /* only mark depth textures the HW can hit as depth textures */
> > - if (util_format_is_depth_or_stencil(rtex->real_format) && permit_hardware_blit(screen, base))
> > + if (util_format_is_depth_or_stencil(rtex->real_format) &&
> > + permit_hardware_blit(screen, base))
> > rtex->is_depth = true;
> >
> > r600_setup_miptree(screen, rtex, array_mode);
> > @@ -729,12 +731,15 @@ struct pipe_resource *r600_texture_from_handle(struct pipe_screen *screen,
> > }
> >
> > void r600_init_flushed_depth_texture(struct pipe_context *ctx,
> > - struct pipe_resource *texture)
> > + struct pipe_resource *texture,
> > + struct r600_resource_texture **staging)
> > {
> > struct r600_resource_texture *rtex = (struct r600_resource_texture*)texture;
> > struct pipe_resource resource;
> > + struct r600_resource_texture **flushed_depth_texture = staging ?
> > + staging : &rtex->flushed_depth_texture;
> >
> > - if (rtex->flushed_depth_texture)
> > + if (!staging && rtex->flushed_depth_texture)
> > return; /* it's ready */
> >
> > resource.target = texture->target;
> > @@ -745,32 +750,44 @@ void r600_init_flushed_depth_texture(struct pipe_context *ctx,
> > resource.array_size = texture->array_size;
> > resource.last_level = texture->last_level;
> > resource.nr_samples = texture->nr_samples;
> > - resource.usage = PIPE_USAGE_DYNAMIC;
> > - resource.bind = texture->bind | PIPE_BIND_DEPTH_STENCIL;
> > - resource.flags = R600_RESOURCE_FLAG_TRANSFER | texture->flags;
> > + resource.usage = staging ? PIPE_USAGE_DYNAMIC : PIPE_USAGE_DEFAULT;
> > + resource.bind = texture->bind & ~PIPE_BIND_DEPTH_STENCIL;
> > + resource.flags = texture->flags;
> > +
> > + if (staging)
> > + resource.flags |= R600_RESOURCE_FLAG_TRANSFER;
> > + else
> > + rtex->dirty_db = TRUE;
> >
> > - rtex->flushed_depth_texture = (struct r600_resource_texture *)ctx->screen->resource_create(ctx->screen, &resource);
> > - if (rtex->flushed_depth_texture == NULL) {
> > - R600_ERR("failed to create temporary texture to hold untiled copy\n");
> > + *flushed_depth_texture = (struct r600_resource_texture *)ctx->screen->resource_create(ctx->screen, &resource);
> > + if (*flushed_depth_texture == NULL) {
> > + R600_ERR("failed to create temporary texture to hold flushed depth\n");
> > return;
> > }
> >
> > - ((struct r600_resource_texture *)rtex->flushed_depth_texture)->is_flushing_texture = TRUE;
> > + (*flushed_depth_texture)->is_flushing_texture = TRUE;
> > +
> > }
> >
> > void r600_texture_depth_flush(struct pipe_context *ctx,
> > - struct pipe_resource *texture)
> > + struct pipe_resource *texture,
> > + struct r600_resource_texture **staging)
> > {
> > struct r600_resource_texture *rtex = (struct r600_resource_texture*)texture;
> >
> > - r600_init_flushed_depth_texture(ctx, texture);
> > + r600_init_flushed_depth_texture(ctx, texture, staging);
> >
> > - if (!rtex->flushed_depth_texture)
> > - return; /* error */
> > + if (staging) {
> > + if (!*staging)
> > + return; /* error */
> >
> > - /* XXX: only do this if the depth texture has actually changed:
> > - */
> > - r600_blit_uncompress_depth(ctx, rtex);
> > + r600_blit_uncompress_depth(ctx, rtex, *staging);
> > + } else {
> > + if (!rtex->flushed_depth_texture)
> > + return; /* error */
> > +
> > + r600_blit_uncompress_depth(ctx, rtex, NULL);
> > + }
> > }
> >
> > /* Needs adjustment for pixelformat:
> > @@ -834,15 +851,18 @@ struct pipe_transfer* r600_texture_get_transfer(struct pipe_context *ctx,
> > */
> > /* XXX: when discard is true, no need to read back from depth texture
> > */
> > - r600_texture_depth_flush(ctx, texture);
> > - if (!rtex->flushed_depth_texture) {
> > + struct r600_resource_texture *staging_depth;
> > +
> > + r600_texture_depth_flush(ctx, texture, &staging_depth);
> > + if (!staging_depth) {
> > R600_ERR("failed to create temporary texture to hold untiled copy\n");
> > pipe_resource_reference(&trans->transfer.resource, NULL);
> > FREE(trans);
> > return NULL;
> > }
> > - trans->transfer.stride = rtex->flushed_depth_texture->pitch_in_bytes[level];
> > - trans->offset = r600_texture_get_offset(rtex->flushed_depth_texture, level, box->z);
> > + trans->transfer.stride = staging_depth->pitch_in_bytes[level];
> > + trans->offset = r600_texture_get_offset(staging_depth, level, box->z);
> > + trans->staging = (struct r600_resource*)staging_depth;
> > return &trans->transfer;
> > } else if (use_staging_texture) {
> > resource.target = PIPE_TEXTURE_2D;
> > @@ -897,15 +917,8 @@ void r600_texture_transfer_destroy(struct pipe_context *ctx,
> > struct pipe_resource *texture = transfer->resource;
> > struct r600_resource_texture *rtex = (struct r600_resource_texture*)texture;
> >
> > - if (rtransfer->staging) {
> > - if (transfer->usage & PIPE_TRANSFER_WRITE) {
> > - r600_copy_from_staging_texture(ctx, rtransfer);
> > - }
> > - pipe_resource_reference((struct pipe_resource**)&rtransfer->staging, NULL);
> > - }
> > -
> > - if (rtex->is_depth && !rtex->is_flushing_texture) {
> > - if ((transfer->usage & PIPE_TRANSFER_WRITE) && rtex->flushed_depth_texture) {
> > + if (rtex->is_depth) {
> > + if ((transfer->usage & PIPE_TRANSFER_WRITE) && rtransfer->staging) {
> > struct pipe_box sbox;
> >
> > sbox.x = sbox.y = sbox.z = 0;
> > @@ -915,11 +928,18 @@ void r600_texture_transfer_destroy(struct pipe_context *ctx,
> > sbox.depth = 1;
> >
> > ctx->resource_copy_region(ctx, texture, 0, 0, 0, 0,
> > - &rtex->flushed_depth_texture->resource.b.b, 0,
> > + &rtransfer->staging->b.b, 0,
> > &sbox);
> > }
> > + } else if (rtransfer->staging) {
> > + if (transfer->usage & PIPE_TRANSFER_WRITE) {
> > + r600_copy_from_staging_texture(ctx, rtransfer);
> > + }
> > }
> >
> > + if (rtransfer->staging)
> > + pipe_resource_reference((struct pipe_resource**)&rtransfer->staging, NULL);
> > +
> > pipe_resource_reference(&transfer->resource, NULL);
> > FREE(transfer);
> > }
> > @@ -930,6 +950,8 @@ void* r600_texture_transfer_map(struct pipe_context *ctx,
> > struct r600_context *rctx = (struct r600_context *)ctx;
> > struct r600_transfer *rtransfer = (struct r600_transfer*)transfer;
> > struct radeon_winsys_cs_handle *buf;
> > + struct r600_resource_texture *rtex =
> > + (struct r600_resource_texture*)transfer->resource;
> > enum pipe_format format = transfer->resource->format;
> > unsigned offset = 0;
> > char *map;
> > @@ -941,17 +963,13 @@ void* r600_texture_transfer_map(struct pipe_context *ctx,
> > if (rtransfer->staging) {
> > buf = ((struct r600_resource *)rtransfer->staging)->cs_buf;
> > } else {
> > - struct r600_resource_texture *rtex = (struct r600_resource_texture*)transfer->resource;
> > -
> > - if (rtex->flushed_depth_texture)
> > - buf = ((struct r600_resource *)rtex->flushed_depth_texture)->cs_buf;
> > - else
> > - buf = ((struct r600_resource *)transfer->resource)->cs_buf;
> > + buf = ((struct r600_resource *)transfer->resource)->cs_buf;
> > + }
> >
> > + if (rtex->is_depth || !rtransfer->staging)
> > offset = rtransfer->offset +
> > transfer->box.y / util_format_get_blockheight(format) * transfer->stride +
> > transfer->box.x / util_format_get_blockwidth(format) * util_format_get_blocksize(format);
> > - }
> >
> > if (!(map = rctx->ws->buffer_map(buf, rctx->cs, transfer->usage))) {
> > return NULL;
> > @@ -974,13 +992,7 @@ void r600_texture_transfer_unmap(struct pipe_context *ctx,
> > if (rtransfer->staging) {
> > buf = ((struct r600_resource *)rtransfer->staging)->cs_buf;
> > } else {
> > - struct r600_resource_texture *rtex = (struct r600_resource_texture*)transfer->resource;
> > -
> > - if (rtex->flushed_depth_texture) {
> > - buf = ((struct r600_resource *)rtex->flushed_depth_texture)->cs_buf;
> > - } else {
> > - buf = ((struct r600_resource *)transfer->resource)->cs_buf;
> > - }
> > + buf = ((struct r600_resource *)transfer->resource)->cs_buf;
> > }
> > rctx->ws->buffer_unmap(buf);
> > }
> > --
> > 1.7.10.4
> >
> > _______________________________________________
> > mesa-dev mailing list
> > mesa-dev at lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/mesa-dev
More information about the mesa-dev
mailing list