summaryrefslogtreecommitdiffstats
path: root/src/mesa/swrast
diff options
context:
space:
mode:
Diffstat (limited to 'src/mesa/swrast')
-rw-r--r--src/mesa/swrast/s_aatritemp.h72
-rw-r--r--src/mesa/swrast/s_context.c105
-rw-r--r--src/mesa/swrast/s_span.c2
-rw-r--r--src/mesa/swrast/s_stencil.c3
-rw-r--r--src/mesa/swrast/s_texcombine.c4
5 files changed, 69 insertions, 117 deletions
diff --git a/src/mesa/swrast/s_aatritemp.h b/src/mesa/swrast/s_aatritemp.h
index 91d4f7a10ab..77b3ae6ec7a 100644
--- a/src/mesa/swrast/s_aatritemp.h
+++ b/src/mesa/swrast/s_aatritemp.h
@@ -181,13 +181,20 @@
const GLfloat *pMax = vMax->attrib[FRAG_ATTRIB_WPOS];
const GLfloat dxdy = majDx / majDy;
const GLfloat xAdj = dxdy < 0.0F ? -dxdy : 0.0F;
- GLfloat x = pMin[0] - (yMin - iyMin) * dxdy;
GLint iy;
- for (iy = iyMin; iy < iyMax; iy++, x += dxdy) {
+#ifdef _OPENMP
+#pragma omp parallel for schedule(dynamic) private(iy) firstprivate(span)
+#endif
+ for (iy = iyMin; iy < iyMax; iy++) {
+ GLfloat x = pMin[0] - (yMin - iy) * dxdy;
GLint ix, startX = (GLint) (x - xAdj);
GLuint count;
GLfloat coverage = 0.0F;
+#ifdef _OPENMP
+ /* each thread needs to use a different (global) SpanArrays variable */
+ span.array = SWRAST_CONTEXT(ctx)->SpanArrays + omp_get_thread_num();
+#endif
/* skip over fragments with zero coverage */
while (startX < MAX_WIDTH) {
coverage = compute_coveragef(pMin, pMid, pMax, startX, iy);
@@ -228,13 +235,12 @@
coverage = compute_coveragef(pMin, pMid, pMax, ix, iy);
}
- if (ix <= startX)
- continue;
-
- span.x = startX;
- span.y = iy;
- span.end = (GLuint) ix - (GLuint) startX;
- _swrast_write_rgba_span(ctx, &span);
+ if (ix > startX) {
+ span.x = startX;
+ span.y = iy;
+ span.end = (GLuint) ix - (GLuint) startX;
+ _swrast_write_rgba_span(ctx, &span);
+ }
}
}
else {
@@ -244,13 +250,20 @@
const GLfloat *pMax = vMax->attrib[FRAG_ATTRIB_WPOS];
const GLfloat dxdy = majDx / majDy;
const GLfloat xAdj = dxdy > 0 ? dxdy : 0.0F;
- GLfloat x = pMin[0] - (yMin - iyMin) * dxdy;
GLint iy;
- for (iy = iyMin; iy < iyMax; iy++, x += dxdy) {
+#ifdef _OPENMP
+#pragma omp parallel for schedule(dynamic) private(iy) firstprivate(span)
+#endif
+ for (iy = iyMin; iy < iyMax; iy++) {
+ GLfloat x = pMin[0] - (yMin - iy) * dxdy;
GLint ix, left, startX = (GLint) (x + xAdj);
GLuint count, n;
GLfloat coverage = 0.0F;
+#ifdef _OPENMP
+ /* each thread needs to use a different (global) SpanArrays variable */
+ span.array = SWRAST_CONTEXT(ctx)->SpanArrays + omp_get_thread_num();
+#endif
/* make sure we're not past the window edge */
if (startX >= ctx->DrawBuffer->_Xmax) {
startX = ctx->DrawBuffer->_Xmax - 1;
@@ -296,31 +309,30 @@
ATTRIB_LOOP_END
#endif
- if (startX <= ix)
- continue;
-
- n = (GLuint) startX - (GLuint) ix;
+ if (startX > ix) {
+ n = (GLuint) startX - (GLuint) ix;
- left = ix + 1;
+ left = ix + 1;
- /* shift all values to the left */
- /* XXX this is temporary */
- {
- SWspanarrays *array = span.array;
- GLint j;
- for (j = 0; j < (GLint) n; j++) {
- array->coverage[j] = array->coverage[j + left];
- COPY_CHAN4(array->rgba[j], array->rgba[j + left]);
+ /* shift all values to the left */
+ /* XXX this is temporary */
+ {
+ SWspanarrays *array = span.array;
+ GLint j;
+ for (j = 0; j < (GLint) n; j++) {
+ array->coverage[j] = array->coverage[j + left];
+ COPY_CHAN4(array->rgba[j], array->rgba[j + left]);
#ifdef DO_Z
- array->z[j] = array->z[j + left];
+ array->z[j] = array->z[j + left];
#endif
+ }
}
- }
- span.x = left;
- span.y = iy;
- span.end = n;
- _swrast_write_rgba_span(ctx, &span);
+ span.x = left;
+ span.y = iy;
+ span.end = n;
+ _swrast_write_rgba_span(ctx, &span);
+ }
}
}
}
diff --git a/src/mesa/swrast/s_context.c b/src/mesa/swrast/s_context.c
index def1531d7ff..792b528ee34 100644
--- a/src/mesa/swrast/s_context.c
+++ b/src/mesa/swrast/s_context.c
@@ -417,84 +417,6 @@ _swrast_validate_blend_func(struct gl_context *ctx, GLuint n, const GLubyte mask
swrast->BlendFunc( ctx, n, mask, src, dst, chanType );
}
-
-/**
- * Make sure we have texture image data for all the textures we may need
- * for subsequent rendering.
- */
-static void
-_swrast_validate_texture_images(struct gl_context *ctx)
-{
- SWcontext *swrast = SWRAST_CONTEXT(ctx);
- GLuint u;
-
- if (!swrast->ValidateTextureImage || !ctx->Texture._EnabledUnits) {
- /* no textures enabled, or no way to validate images! */
- return;
- }
-
- for (u = 0; u < ctx->Const.MaxTextureImageUnits; u++) {
- if (ctx->Texture.Unit[u]._ReallyEnabled) {
- struct gl_texture_object *texObj = ctx->Texture.Unit[u]._Current;
- ASSERT(texObj);
- if (texObj) {
- GLuint numFaces = (texObj->Target == GL_TEXTURE_CUBE_MAP) ? 6 : 1;
- GLuint face;
- for (face = 0; face < numFaces; face++) {
- GLint lvl;
- for (lvl = texObj->BaseLevel; lvl <= texObj->_MaxLevel; lvl++) {
- struct gl_texture_image *texImg = texObj->Image[face][lvl];
- if (texImg && !texImg->Data) {
- swrast->ValidateTextureImage(ctx, texObj, face, lvl);
- ASSERT(texObj->Image[face][lvl]->Data);
- }
- }
- }
- }
- }
- }
-}
-
-
-/**
- * Free the texture image data attached to all currently enabled
- * textures. Meant to be called by device drivers when transitioning
- * from software to hardware rendering.
- */
-void
-_swrast_eject_texture_images(struct gl_context *ctx)
-{
- GLuint u;
-
- if (!ctx->Texture._EnabledUnits) {
- /* no textures enabled */
- return;
- }
-
- for (u = 0; u < ctx->Const.MaxTextureImageUnits; u++) {
- if (ctx->Texture.Unit[u]._ReallyEnabled) {
- struct gl_texture_object *texObj = ctx->Texture.Unit[u]._Current;
- ASSERT(texObj);
- if (texObj) {
- GLuint numFaces = (texObj->Target == GL_TEXTURE_CUBE_MAP) ? 6 : 1;
- GLuint face;
- for (face = 0; face < numFaces; face++) {
- GLint lvl;
- for (lvl = texObj->BaseLevel; lvl <= texObj->_MaxLevel; lvl++) {
- struct gl_texture_image *texImg = texObj->Image[face][lvl];
- if (texImg && texImg->Data) {
- _mesa_free_texmemory(texImg->Data);
- texImg->Data = NULL;
- }
- }
- }
- }
- }
- }
-}
-
-
-
static void
_swrast_sleep( struct gl_context *ctx, GLbitfield new_state )
{
@@ -640,7 +562,6 @@ _swrast_validate_derived( struct gl_context *ctx )
if (swrast->NewState & (_NEW_TEXTURE | _NEW_PROGRAM)) {
_swrast_update_texture_samplers( ctx );
- _swrast_validate_texture_images(ctx);
}
if (swrast->NewState & (_NEW_COLOR | _NEW_PROGRAM))
@@ -772,6 +693,11 @@ _swrast_CreateContext( struct gl_context *ctx )
{
GLuint i;
SWcontext *swrast = (SWcontext *)CALLOC(sizeof(SWcontext));
+#ifdef _OPENMP
+ const GLint maxThreads = omp_get_max_threads();
+#else
+ const GLint maxThreads = 1;
+#endif
if (SWRAST_DEBUG) {
_mesa_debug(ctx, "_swrast_CreateContext\n");
@@ -806,19 +732,25 @@ _swrast_CreateContext( struct gl_context *ctx )
for (i = 0; i < MAX_TEXTURE_IMAGE_UNITS; i++)
swrast->TextureSample[i] = NULL;
- swrast->SpanArrays = MALLOC_STRUCT(sw_span_arrays);
+ /* SpanArrays is global and shared by all SWspan instances. However, when
+ * using multiple threads, it is necessary to have one SpanArrays instance
+ * per thread.
+ */
+ swrast->SpanArrays = (SWspanarrays *) MALLOC(maxThreads * sizeof(SWspanarrays));
if (!swrast->SpanArrays) {
FREE(swrast);
return GL_FALSE;
}
- swrast->SpanArrays->ChanType = CHAN_TYPE;
+ for(i = 0; i < maxThreads; i++) {
+ swrast->SpanArrays[i].ChanType = CHAN_TYPE;
#if CHAN_TYPE == GL_UNSIGNED_BYTE
- swrast->SpanArrays->rgba = swrast->SpanArrays->rgba8;
+ swrast->SpanArrays[i].rgba = swrast->SpanArrays[i].rgba8;
#elif CHAN_TYPE == GL_UNSIGNED_SHORT
- swrast->SpanArrays->rgba = swrast->SpanArrays->rgba16;
+ swrast->SpanArrays[i].rgba = swrast->SpanArrays[i].rgba16;
#else
- swrast->SpanArrays->rgba = swrast->SpanArrays->attribs[FRAG_ATTRIB_COL0];
+ swrast->SpanArrays[i].rgba = swrast->SpanArrays[i].attribs[FRAG_ATTRIB_COL0];
#endif
+ }
/* init point span buffer */
swrast->PointSpan.primitive = GL_POINT;
@@ -826,7 +758,10 @@ _swrast_CreateContext( struct gl_context *ctx )
swrast->PointSpan.facing = 0;
swrast->PointSpan.array = swrast->SpanArrays;
- swrast->TexelBuffer = (GLfloat *) MALLOC(ctx->Const.MaxTextureImageUnits *
+ /* TexelBuffer is also global and normally shared by all SWspan instances;
+ * when running with multiple threads, create one per thread.
+ */
+ swrast->TexelBuffer = (GLfloat *) MALLOC(ctx->Const.MaxTextureImageUnits * maxThreads *
MAX_WIDTH * 4 * sizeof(GLfloat));
if (!swrast->TexelBuffer) {
FREE(swrast->SpanArrays);
diff --git a/src/mesa/swrast/s_span.c b/src/mesa/swrast/s_span.c
index db102ac7946..9a91be39970 100644
--- a/src/mesa/swrast/s_span.c
+++ b/src/mesa/swrast/s_span.c
@@ -212,10 +212,10 @@ interpolate_active_attribs(struct gl_context *ctx, SWspan *span, GLbitfield attr
static INLINE void
interpolate_int_colors(struct gl_context *ctx, SWspan *span)
{
+#if CHAN_BITS != 32
const GLuint n = span->end;
GLuint i;
-#if CHAN_BITS != 32
ASSERT(!(span->arrayMask & SPAN_RGBA));
#endif
diff --git a/src/mesa/swrast/s_stencil.c b/src/mesa/swrast/s_stencil.c
index 5bec71c057b..fa5093a3407 100644
--- a/src/mesa/swrast/s_stencil.c
+++ b/src/mesa/swrast/s_stencil.c
@@ -462,7 +462,8 @@ stencil_and_ztest_span(struct gl_context *ctx, SWspan *span, GLuint face)
* Some fragments passed the stencil test, apply depth test to them
* and apply Zpass and Zfail stencil ops.
*/
- if (ctx->Depth.Test == GL_FALSE) {
+ if (ctx->Depth.Test == GL_FALSE ||
+ ctx->DrawBuffer->_DepthBuffer == NULL) {
/*
* No depth buffer, just apply zpass stencil function to active pixels.
*/
diff --git a/src/mesa/swrast/s_texcombine.c b/src/mesa/swrast/s_texcombine.c
index 086ed0b33d7..80b9dff3cc2 100644
--- a/src/mesa/swrast/s_texcombine.c
+++ b/src/mesa/swrast/s_texcombine.c
@@ -48,7 +48,11 @@ typedef float (*float4_array)[4];
static INLINE float4_array
get_texel_array(SWcontext *swrast, GLuint unit)
{
+#ifdef _OPENMP
+ return (float4_array) (swrast->TexelBuffer + unit * MAX_WIDTH * 4 * omp_get_num_threads() + (MAX_WIDTH * 4 * omp_get_thread_num()));
+#else
return (float4_array) (swrast->TexelBuffer + unit * MAX_WIDTH * 4);
+#endif
}
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-19 19:35:33 +0000