On Wed, 2009-06-03 at 18:20 +0200, Maciej Cencora wrote:
> Dnia środa, 3 czerwca 2009 o 11:21:40 Michel Dänzer napisał(a):
> > On Tue, 2009-06-02 at 21:09 +0200, Nicolai Hähnle wrote:
> > > Am Tuesday 02 June 2009 20:18:17 schrieb Michel Dänzer:
> > > > On Mon, 2009-06-01 at 16:39 +0200, Maciej Cencora wrote:
> > > > > Dnia poniedziałek, 1 czerwca 2009 o 14:25:57 Maciej Cencora
> napisał(a):
> > > > > > Dnia poniedziałek, 1 czerwca 2009 o 12:44:20 Michel Dänzer
> napisał(a):
> > > > > > > On Sat, 2009-05-30 at 21:00 +0200, Maciej Cencora wrote:
> > > > > > > > Hi,
> > > > > > > >
> > > > > > > > this round of patches for r300 brings:
> > > > > > > > 1) hardware accelerated support for 8bit and 16bit vertex
> > > > > > > > attribute data formats,
> > > > > > > > 2) support for 16bit vertex indices,
> > > > > > > > 3) support for EXT_vertex_array_bgra extension,
> > > > > > > > 4) T&L path cleanup. it's used when hardware TCL is enabled,
> > > > > > > > but we have to fallback for software TCL - clipping is still
> > > > > > > > done in hardware unlike in software TCL path.
> > > > > > > >
> > > > > > > > Those patches are unfinished, to be done:
> > > > > > > > 1) unmap bo's after rendering is finished
> > > > > > > > Currently the map/unmap functions are noop so it's working ok,
> > > > > > > > but when we will add support for VBO's it won't work.
> > > > > > > >
> > > > > > > > 2) handle big endian machines correctly
> > > > > > > > Is this really an issue?
> > > > > > >
> > > > > > > The driver certainly used to have special code for non-32-bit
> > > > > > > elts on big endian. How can I test this on my PowerBook?
> > > > > >
> > > > > > Hmm, since vbo branch merge all elts are always 32bit. I've looked
> > > > > > a little at the code before the merge and I couldn't find any big
> > > > > > endian specific code for elt handling, but maybe I just haven't
> > > > > > looked hard enough.
> > > > > >
> > > > > > mesa/progs/trivial/draw2arrays is using unsigned bytes as indexes,
> > > > > > change it to unsigned shorts and check if the rendering is correct.
> > > > >
> > > > > I meant mesa/progs/trivial/drawrange
> > > >
> > > > Patch 4 indeed breaks that on my PowerBook. The patch below is a
> > > > minimal fix. Not sure why the #if 0'd code to just swap short indices
> > > > doesn't work...
> > >
> > > Just a stab in the dark, but maybe the single bytes within the shorts
> > > also need to be swapped?
> >
> > No. After some rather confusing experiments, I figured it out:
> > r300EmitElts() didn't copy the extra two bytes. The patch below now
> > works with short and byte indices.
> >
> >
> > commit a67a18d27a1e0e28cb62a346a4a995ca66ecf949
> > Author: Michel Dänzer <daen...@vmware.com>
> > Date: Wed Jun 3 11:18:24 2009 +0200
> >
> > r300: Endianness fixes for recent vertex path changes.
> >
> > diff --git a/src/mesa/drivers/dri/r300/r300_draw.c
> > b/src/mesa/drivers/dri/r300/r300_draw.c index 232ed10..142e934 100644
> > --- a/src/mesa/drivers/dri/r300/r300_draw.c
> > +++ b/src/mesa/drivers/dri/r300/r300_draw.c
> > @@ -69,19 +69,42 @@ static void r300FixupIndexBuffer(GLcontext *ctx, const
> > struct _mesa_index_buffer
> >
> > if (mesa_ind_buf->type == GL_UNSIGNED_BYTE) {
>
> You should add #if MESA_BIG_ENDIAN for this path too.
I don't agree, I prefer sharing code whenever feasible.
> > GLubyte *in = (GLubyte *)src_ptr;
> > - GLushort *out = _mesa_malloc(sizeof(GLushort) *
> > mesa_ind_buf->count);
> > + GLuint *out = _mesa_malloc(sizeof(GLushort) *
> > + ((mesa_ind_buf->count + 1) & ~1));
> > int i;
> >
> > - for (i = 0; i < mesa_ind_buf->count; ++i) {
> > - out[i] = (GLushort) in[i];
> > + for (i = 0; i + 1 < mesa_ind_buf->count; i += 2) {
> > + out[i / 2] = in[i] | in[i + 1] << 16;
> > + }
> > +
> > + if (i < mesa_ind_buf->count) {
> > + out[i / 2] = in[i];
> > }
> >
>
> You should use seperate indexes for in and out arrays
The new patch below uses *out++, hope that's okay.
> > @@ -157,7 +180,11 @@ static void r300TranslateAttrib(GLcontext *ctx, GLuint
> > attr, int count, const st } else
> > src_ptr = input->Ptr;
> >
> > - if (input->Type == GL_DOUBLE || input->Type == GL_UNSIGNED_INT ||
> > input->Type == GL_INT || input->StrideB < 4){ + if (input->Type ==
> > GL_DOUBLE || input->Type == GL_UNSIGNED_INT || input->Type == GL_INT ||
> > +#if MESA_BIG_ENDIAN
> > + getTypeSize(input->Type) != 4 ||
> > +#endif
> > + input->StrideB < 4) {
>
> What's the reason for this change?
Attributes smaller than 4 bytes have the same endianness problem, e.g.
in trivial/drawrange the colours are wrong. Maybe there's a better way
to handle this.
> > --- a/src/mesa/drivers/dri/r300/r300_render.c
> > +++ b/src/mesa/drivers/dri/r300/r300_render.c
> > @@ -184,7 +184,7 @@ static void r300EmitElts(GLcontext * ctx, unsigned long
> > n_elts) &rmesa->radeon.tcl.elt_dma_offset, n_elts * el_size, 4);
> > radeon_bo_map(rmesa->radeon.tcl.elt_dma_bo, 1);
> > out = rmesa->radeon.tcl.elt_dma_bo->ptr +
> > rmesa->radeon.tcl.elt_dma_offset; - memcpy(out, rmesa->ind_buf.ptr, n_elts
> > * el_size);
> > + memcpy(out, rmesa->ind_buf.ptr, (n_elts * el_size + 3) & ~3);
> > radeon_bo_unmap(rmesa->radeon.tcl.elt_dma_bo);
> > }
>
> You should probably round up the dma buffer size to 4 bytes too.
Ah yes, for some reason I thought the last parameter to
radeonAllocDmaRegion() did that.
commit 1a933d1a5748715a325bd0b24427ef095d5389a7
Author: Michel Dänzer <daen...@vmware.com>
Date: Wed Jun 3 19:07:25 2009 +0200
r300: Endianness fixes for recent vertex path changes.
diff --git a/src/mesa/drivers/dri/r300/r300_draw.c
b/src/mesa/drivers/dri/r300/r300_draw.c
index 232ed10..72e6807 100644
--- a/src/mesa/drivers/dri/r300/r300_draw.c
+++ b/src/mesa/drivers/dri/r300/r300_draw.c
@@ -69,19 +69,44 @@ static void r300FixupIndexBuffer(GLcontext *ctx, const
struct _mesa_index_buffer
if (mesa_ind_buf->type == GL_UNSIGNED_BYTE) {
GLubyte *in = (GLubyte *)src_ptr;
- GLushort *out = _mesa_malloc(sizeof(GLushort) *
mesa_ind_buf->count);
+ GLuint *out = _mesa_malloc(sizeof(GLushort) *
+ ((mesa_ind_buf->count + 1) & ~1));
int i;
- for (i = 0; i < mesa_ind_buf->count; ++i) {
- out[i] = (GLushort) in[i];
+ ind_buf->ptr = out;
+
+ for (i = 0; i + 1 < mesa_ind_buf->count; i += 2) {
+ *out++ = in[i] | in[i + 1] << 16;
+ }
+
+ if (i < mesa_ind_buf->count) {
+ *out++ = in[i];
}
- ind_buf->ptr = out;
ind_buf->free_needed = GL_TRUE;
ind_buf->is_32bit = GL_FALSE;
} else if (mesa_ind_buf->type == GL_UNSIGNED_SHORT) {
+#if MESA_BIG_ENDIAN
+ GLushort *in = (GLushort *)src_ptr;
+ GLuint *out = _mesa_malloc(sizeof(GLushort) *
+ ((mesa_ind_buf->count + 1) & ~1));
+ int i;
+
+ ind_buf->ptr = out;
+
+ for (i = 0; i + 1 < mesa_ind_buf->count; i += 2) {
+ *out++ = in[i] | in[i + 1] << 16;
+ }
+
+ if (i < mesa_ind_buf->count) {
+ *out++ = in[i];
+ }
+
+ ind_buf->free_needed = GL_TRUE;
+#else
ind_buf->ptr = src_ptr;
ind_buf->free_needed = GL_FALSE;
+#endif
ind_buf->is_32bit = GL_FALSE;
} else {
ind_buf->ptr = src_ptr;
@@ -157,7 +182,11 @@ static void r300TranslateAttrib(GLcontext *ctx, GLuint
attr, int count, const st
} else
src_ptr = input->Ptr;
- if (input->Type == GL_DOUBLE || input->Type == GL_UNSIGNED_INT ||
input->Type == GL_INT || input->StrideB < 4){
+ if (input->Type == GL_DOUBLE || input->Type == GL_UNSIGNED_INT ||
input->Type == GL_INT ||
+#if MESA_BIG_ENDIAN
+ getTypeSize(input->Type) != 4 ||
+#endif
+ input->StrideB < 4) {
if (RADEON_DEBUG & DEBUG_FALLBACKS) {
fprintf(stderr, "%s: Converting vertex attributes,
attribute data format %x,", __FUNCTION__, input->Type);
fprintf(stderr, "stride %d, components %d\n",
input->StrideB, input->Size);
diff --git a/src/mesa/drivers/dri/r300/r300_render.c
b/src/mesa/drivers/dri/r300/r300_render.c
index adda924..dfbd79a 100644
--- a/src/mesa/drivers/dri/r300/r300_render.c
+++ b/src/mesa/drivers/dri/r300/r300_render.c
@@ -176,15 +176,15 @@ static void r300EmitElts(GLcontext * ctx, unsigned long
n_elts)
{
r300ContextPtr rmesa = R300_CONTEXT(ctx);
void *out;
- GLbyte el_size;
+ GLuint size;
- el_size = rmesa->ind_buf.is_32bit ? 4 : 2;
+ size = ((rmesa->ind_buf.is_32bit ? 4 : 2) * n_elts + 3) & ~3;
radeonAllocDmaRegion(&rmesa->radeon, &rmesa->radeon.tcl.elt_dma_bo,
- &rmesa->radeon.tcl.elt_dma_offset, n_elts *
el_size, 4);
+ &rmesa->radeon.tcl.elt_dma_offset, size, 4);
radeon_bo_map(rmesa->radeon.tcl.elt_dma_bo, 1);
out = rmesa->radeon.tcl.elt_dma_bo->ptr +
rmesa->radeon.tcl.elt_dma_offset;
- memcpy(out, rmesa->ind_buf.ptr, n_elts * el_size);
+ memcpy(out, rmesa->ind_buf.ptr, size);
radeon_bo_unmap(rmesa->radeon.tcl.elt_dma_bo);
}
--
Earthling Michel Dänzer | http://www.vmware.com
Libre software enthusiast | Debian, X and DRI developer
------------------------------------------------------------------------------
OpenSolaris 2009.06 is a cutting edge operating system for enterprises
looking to deploy the next generation of Solaris that includes the latest
innovations from Sun and the OpenSource community. Download a copy and
enjoy capabilities such as Networking, Storage and Virtualization.
Go to: http://p.sf.net/sfu/opensolaris-get
_______________________________________________
Mesa3d-dev mailing list
Mesa3d-dev@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/mesa3d-dev
