Now that we have execution sizes, we can use that instead of the dispatch
width. This way it also works for 8-wide instructions in SIMD16.
---
src/mesa/drivers/dri/i965/brw_fs.cpp | 10 +++++-----
src/mesa/drivers/dri/i965/brw_fs.h | 4 ++--
src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp | 4 ++--
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/src/mesa/drivers/dri/i965/brw_fs.cpp
b/src/mesa/drivers/dri/i965/brw_fs.cpp
index 551bc2b..ffbfdbd 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs.cpp
@@ -354,7 +354,7 @@ fs_visitor::LOAD_PAYLOAD(const fs_reg &dst, fs_reg *src,
int sources)
* dealing with whole registers. If this ever changes, we can deal
* with it later.
*/
- int size = src[i].effective_width(this) * type_sz(src[i].type);
+ int size = src[i].effective_width(inst) * type_sz(src[i].type);
assert(size % 32 == 0);
inst->regs_written += (size + 31) / 32;
}
@@ -583,7 +583,7 @@ fs_reg::equals(const fs_reg &r) const
}
uint8_t
-fs_reg::effective_width(const fs_visitor *v) const
+fs_reg::effective_width(const fs_inst *inst) const
{
switch (this->file) {
case BAD_FILE:
@@ -591,10 +591,10 @@ fs_reg::effective_width(const fs_visitor *v) const
case UNIFORM:
case IMM:
assert(this->width == 1);
- return v->dispatch_width;
+ return inst->exec_size;
case GRF:
case HW_REG:
- assert(this->width > 1 && this->width <= v->dispatch_width);
+ assert(this->width > 1 && this->width <= inst->exec_size);
assert(this->width % 8 == 0);
return this->width;
case MRF:
@@ -2994,7 +2994,7 @@ fs_visitor::lower_load_payload()
fs_reg dst = inst->dst;
for (int i = 0; i < inst->sources; i++) {
- dst.width = inst->src[i].effective_width(this);
+ dst.width = inst->src[i].effective_width(inst);
dst.type = inst->src[i].type;
if (inst->src[i].file == BAD_FILE) {
diff --git a/src/mesa/drivers/dri/i965/brw_fs.h
b/src/mesa/drivers/dri/i965/brw_fs.h
index 4ffbec8..c282b5e 100644
--- a/src/mesa/drivers/dri/i965/brw_fs.h
+++ b/src/mesa/drivers/dri/i965/brw_fs.h
@@ -62,7 +62,7 @@ namespace brw {
class fs_live_variables;
}
-class fs_visitor;
+class fs_inst;
class fs_reg : public backend_reg {
public:
@@ -110,7 +110,7 @@ public:
* effectively take on the width of the instruction in which they are
* used.
*/
- uint8_t effective_width(const fs_visitor *v) const;
+ uint8_t effective_width(const fs_inst *inst) const;
/** Register region horizontal stride */
uint8_t stride;
diff --git a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
index aafc49b..73a196d 100644
--- a/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
+++ b/src/mesa/drivers/dri/i965/brw_fs_copy_propagation.cpp
@@ -640,13 +640,13 @@ fs_visitor::opt_copy_propagate_local(void *copy_prop_ctx,
bblock_t *block,
inst->dst.file == GRF) {
int offset = 0;
for (int i = 0; i < inst->sources; i++) {
- int regs_written = ((inst->src[i].effective_width(this) *
+ int regs_written = ((inst->src[i].effective_width(inst) *
type_sz(inst->src[i].type)) + 31) / 32;
if (inst->src[i].file == GRF) {
acp_entry *entry = ralloc(copy_prop_ctx, acp_entry);
entry->dst = inst->dst;
entry->dst.reg_offset = offset;
- entry->dst.width = inst->src[i].effective_width(this);
+ entry->dst.width = inst->src[i].effective_width(inst);
entry->src = inst->src[i];
entry->regs_written = regs_written;
entry->opcode = inst->opcode;
--
2.1.0
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
