aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorDave Airlie <[email protected]>2018-02-06 14:17:46 +1000
committerDave Airlie <[email protected]>2018-02-09 09:53:21 +1000
commit22fc5eff803d14e99e9f86db223ceedcef1b9108 (patch)
treeffa5a056dae1028c400573ebfdf616c866441c9e
parentcd34deb585669ffe1d520b07c629316f2ac22074 (diff)
r600/sb: handle scratch mem reads on r600
On r600 we use the scratch mem with read/read_ind, in that case sb should track the rw_gpr as a dst instead of a src. This stops the whole shader being optimised out. Signed-off-by: Dave Airlie <[email protected]> Reviewed-by: Dave Airlie <[email protected]>
-rw-r--r--src/gallium/drivers/r600/sb/sb_bc_finalize.cpp9
-rw-r--r--src/gallium/drivers/r600/sb/sb_bc_parser.cpp19
2 files changed, 23 insertions, 5 deletions
diff --git a/src/gallium/drivers/r600/sb/sb_bc_finalize.cpp b/src/gallium/drivers/r600/sb/sb_bc_finalize.cpp
index e737f3d6cd0..5c572938a15 100644
--- a/src/gallium/drivers/r600/sb/sb_bc_finalize.cpp
+++ b/src/gallium/drivers/r600/sb/sb_bc_finalize.cpp
@@ -778,8 +778,15 @@ void bc_finalizer::finalize_cf(cf_node* c) {
int reg = -1;
unsigned mask = 0;
+
for (unsigned chan = 0; chan < 4; ++chan) {
- value *v = c->src[chan];
+ value *v;
+ if (ctx.hw_class == HW_CLASS_R600 && c->bc.op == CF_OP_MEM_SCRATCH &&
+ (c->bc.type == 2 || c->bc.type == 3))
+ v = c->dst[chan];
+ else
+ v = c->src[chan];
+
if (!v || v->is_undef())
continue;
diff --git a/src/gallium/drivers/r600/sb/sb_bc_parser.cpp b/src/gallium/drivers/r600/sb/sb_bc_parser.cpp
index 2ec842159b1..a7b828268b9 100644
--- a/src/gallium/drivers/r600/sb/sb_bc_parser.cpp
+++ b/src/gallium/drivers/r600/sb/sb_bc_parser.cpp
@@ -832,12 +832,23 @@ int bc_parser::prepare_ir() {
do {
- c->src.resize(4);
+ if (ctx.hw_class == HW_CLASS_R600 && c->bc.op == CF_OP_MEM_SCRATCH &&
+ (c->bc.type == 2 || c->bc.type == 3)) {
+ c->dst.resize(4);
+ for(int s = 0; s < 4; ++s) {
+ if (c->bc.comp_mask & (1 << s))
+ c->dst[s] =
+ sh->get_gpr_value(true, c->bc.rw_gpr, s, false);
+ }
+ } else {
+ c->src.resize(4);
- for(int s = 0; s < 4; ++s) {
- if (c->bc.comp_mask & (1 << s))
- c->src[s] =
+
+ for(int s = 0; s < 4; ++s) {
+ if (c->bc.comp_mask & (1 << s))
+ c->src[s] =
sh->get_gpr_value(true, c->bc.rw_gpr, s, false);
+ }
}
if (((flags & CF_RAT) || (!(flags & CF_STRM))) && (c->bc.type & 1)) { // indexed write