summaryrefslogtreecommitdiffstats
path: root/src/gallium/auxiliary/translate/translate_generic.c
diff options
context:
space:
mode:
Diffstat (limited to 'src/gallium/auxiliary/translate/translate_generic.c')
-rw-r--r--src/gallium/auxiliary/translate/translate_generic.c213
1 files changed, 118 insertions, 95 deletions
diff --git a/src/gallium/auxiliary/translate/translate_generic.c b/src/gallium/auxiliary/translate/translate_generic.c
index 42cfd763e9c..ad809db720d 100644
--- a/src/gallium/auxiliary/translate/translate_generic.c
+++ b/src/gallium/auxiliary/translate/translate_generic.c
@@ -64,6 +64,14 @@ struct translate_generic {
unsigned input_stride;
unsigned max_index;
+ /* this value is set to -1 if this is a normal element with output_format != input_format:
+ * in this case, u_format is used to do a full conversion
+ *
+ * this value is set to the format size in bytes if output_format == input_format or for 32-bit instance ids:
+ * in this case, memcpy is used to copy this amount of bytes
+ */
+ int copy_size;
+
} attrib[PIPE_MAX_ATTRIBS];
unsigned nr_attrib;
@@ -354,7 +362,65 @@ static emit_func get_emit_func( enum pipe_format format )
}
}
+static ALWAYS_INLINE void PIPE_CDECL generic_run_one( struct translate_generic *tg,
+ unsigned elt,
+ unsigned instance_id,
+ void *vert )
+{
+ unsigned nr_attrs = tg->nr_attrib;
+ unsigned attr;
+
+ for (attr = 0; attr < nr_attrs; attr++) {
+ float data[4];
+ uint8_t *dst = (uint8_t *)vert + tg->attrib[attr].output_offset;
+
+ if (tg->attrib[attr].type == TRANSLATE_ELEMENT_NORMAL) {
+ const uint8_t *src;
+ unsigned index;
+ int copy_size;
+
+ if (tg->attrib[attr].instance_divisor) {
+ index = instance_id / tg->attrib[attr].instance_divisor;
+ }
+ else {
+ index = elt;
+ }
+
+ /* clamp to void going out of bounds */
+ index = MIN2(index, tg->attrib[attr].max_index);
+ src = tg->attrib[attr].input_ptr +
+ tg->attrib[attr].input_stride * index;
+
+ copy_size = tg->attrib[attr].copy_size;
+ if(likely(copy_size >= 0))
+ memcpy(dst, src, copy_size);
+ else
+ {
+ tg->attrib[attr].fetch( data, src, 0, 0 );
+
+ if (0)
+ debug_printf("Fetch linear attr %d from %p stride %d index %d: "
+ " %f, %f, %f, %f \n",
+ attr,
+ tg->attrib[attr].input_ptr,
+ tg->attrib[attr].input_stride,
+ index,
+ data[0], data[1],data[2], data[3]);
+
+ tg->attrib[attr].emit( data, dst );
+ }
+ } else {
+ if(likely(tg->attrib[attr].copy_size >= 0))
+ memcpy(data, &instance_id, 4);
+ else
+ {
+ data[0] = (float)instance_id;
+ tg->attrib[attr].emit( data, dst );
+ }
+ }
+ }
+}
/**
* Fetch vertex attributes for 'count' vertices.
@@ -367,62 +433,45 @@ static void PIPE_CDECL generic_run_elts( struct translate *translate,
{
struct translate_generic *tg = translate_generic(translate);
char *vert = output_buffer;
- unsigned nr_attrs = tg->nr_attrib;
- unsigned attr;
unsigned i;
- /* loop over vertex attributes (vertex shader inputs)
- */
for (i = 0; i < count; i++) {
- const unsigned elt = *elts++;
-
- for (attr = 0; attr < nr_attrs; attr++) {
- float data[4];
- char *dst = vert + tg->attrib[attr].output_offset;
-
- if (tg->attrib[attr].type == TRANSLATE_ELEMENT_NORMAL) {
- const uint8_t *src;
- unsigned index;
-
- if (tg->attrib[attr].instance_divisor) {
- index = instance_id / tg->attrib[attr].instance_divisor;
- } else {
- index = elt;
- }
-
- /* clamp to void going out of bounds */
- index = MIN2(index, tg->attrib[attr].max_index);
-
- src = tg->attrib[attr].input_ptr +
- tg->attrib[attr].input_stride * index;
-
- tg->attrib[attr].fetch( data, src, 0, 0 );
-
- if (0)
- debug_printf("Fetch elt attr %d from %p stride %d div %u max %u index %d: "
- " %f, %f, %f, %f \n",
- attr,
- tg->attrib[attr].input_ptr,
- tg->attrib[attr].input_stride,
- tg->attrib[attr].instance_divisor,
- tg->attrib[attr].max_index,
- index,
- data[0], data[1],data[2], data[3]);
- } else {
- data[0] = (float)instance_id;
- }
+ generic_run_one(tg, *elts++, instance_id, vert);
+ vert += tg->translate.key.output_stride;
+ }
+}
- if (0)
- debug_printf("vert %d/%d attr %d: %f %f %f %f\n",
- i, elt, attr, data[0], data[1], data[2], data[3]);
+static void PIPE_CDECL generic_run_elts16( struct translate *translate,
+ const uint16_t *elts,
+ unsigned count,
+ unsigned instance_id,
+ void *output_buffer )
+{
+ struct translate_generic *tg = translate_generic(translate);
+ char *vert = output_buffer;
+ unsigned i;
- tg->attrib[attr].emit( data, dst );
- }
+ for (i = 0; i < count; i++) {
+ generic_run_one(tg, *elts++, instance_id, vert);
vert += tg->translate.key.output_stride;
}
}
+static void PIPE_CDECL generic_run_elts8( struct translate *translate,
+ const uint8_t *elts,
+ unsigned count,
+ unsigned instance_id,
+ void *output_buffer )
+{
+ struct translate_generic *tg = translate_generic(translate);
+ char *vert = output_buffer;
+ unsigned i;
+ for (i = 0; i < count; i++) {
+ generic_run_one(tg, *elts++, instance_id, vert);
+ vert += tg->translate.key.output_stride;
+ }
+}
static void PIPE_CDECL generic_run( struct translate *translate,
unsigned start,
@@ -432,57 +481,10 @@ static void PIPE_CDECL generic_run( struct translate *translate,
{
struct translate_generic *tg = translate_generic(translate);
char *vert = output_buffer;
- unsigned nr_attrs = tg->nr_attrib;
- unsigned attr;
unsigned i;
- /* loop over vertex attributes (vertex shader inputs)
- */
for (i = 0; i < count; i++) {
- unsigned elt = start + i;
-
- for (attr = 0; attr < nr_attrs; attr++) {
- float data[4];
- char *dst = vert + tg->attrib[attr].output_offset;
-
- if (tg->attrib[attr].type == TRANSLATE_ELEMENT_NORMAL) {
- const uint8_t *src;
- unsigned index;
-
- if (tg->attrib[attr].instance_divisor) {
- index = instance_id / tg->attrib[attr].instance_divisor;
- }
- else {
- index = elt;
- }
-
- /* clamp to void going out of bounds */
- index = MIN2(index, tg->attrib[attr].max_index);
-
- src = tg->attrib[attr].input_ptr +
- tg->attrib[attr].input_stride * index;
-
- tg->attrib[attr].fetch( data, src, 0, 0 );
-
- if (0)
- debug_printf("Fetch linear attr %d from %p stride %d index %d: "
- " %f, %f, %f, %f \n",
- attr,
- tg->attrib[attr].input_ptr,
- tg->attrib[attr].input_stride,
- index,
- data[0], data[1],data[2], data[3]);
- } else {
- data[0] = (float)instance_id;
- }
-
- if (0)
- debug_printf("vert %d attr %d: %f %f %f %f\n",
- i, attr, data[0], data[1], data[2], data[3]);
-
- tg->attrib[attr].emit( data, dst );
- }
-
+ generic_run_one(tg, start + i, instance_id, vert);
vert += tg->translate.key.output_stride;
}
}
@@ -528,6 +530,8 @@ struct translate *translate_generic_create( const struct translate_key *key )
tg->translate.release = generic_release;
tg->translate.set_buffer = generic_set_buffer;
tg->translate.run_elts = generic_run_elts;
+ tg->translate.run_elts16 = generic_run_elts16;
+ tg->translate.run_elts8 = generic_run_elts8;
tg->translate.run = generic_run;
for (i = 0; i < key->nr_elements; i++) {
@@ -544,9 +548,28 @@ struct translate *translate_generic_create( const struct translate_key *key )
tg->attrib[i].input_offset = key->element[i].input_offset;
tg->attrib[i].instance_divisor = key->element[i].instance_divisor;
- tg->attrib[i].emit = get_emit_func(key->element[i].output_format);
tg->attrib[i].output_offset = key->element[i].output_offset;
+ tg->attrib[i].copy_size = -1;
+ if (tg->attrib[i].type == TRANSLATE_ELEMENT_INSTANCE_ID)
+ {
+ if(key->element[i].output_format == PIPE_FORMAT_R32_USCALED
+ || key->element[i].output_format == PIPE_FORMAT_R32_SSCALED)
+ tg->attrib[i].copy_size = 4;
+ }
+ else
+ {
+ if(key->element[i].input_format == key->element[i].output_format
+ && format_desc->block.width == 1
+ && format_desc->block.height == 1
+ && !(format_desc->block.bits & 7))
+ tg->attrib[i].copy_size = format_desc->block.bits >> 3;
+ }
+
+ if(tg->attrib[i].copy_size < 0)
+ tg->attrib[i].emit = get_emit_func(key->element[i].output_format);
+ else
+ tg->attrib[i].emit = NULL;
}
tg->nr_attrib = key->nr_elements;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-14 04:12:46 +0000