summaryrefslogtreecommitdiffstats
path: root/src/gallium/drivers/vc4/vc4_qir.h
diff options
context:
space:
mode:
authorEric Anholt <eric@anholt.net>2014-12-10 14:56:46 -0800
committerEric Anholt <eric@anholt.net>2014-12-17 19:35:13 -0800
commite473fbe4690b5cbe3769042a4917f22559e2ba8d (patch)
treed2c2a467d69a4713651b40bf269db9691544baab /src/gallium/drivers/vc4/vc4_qir.h
parentff266483fb61fd69775daf5c931ca7a56a26f4ac (diff)
vc4: Add support for turning constant uniforms into small immediates.
Small immediates have the downside of taking over the raddr B field, so you might have less chance to pack instructions together thanks to raddr B conflicts. However, it also reduces some register pressure since it lets you load 2 "uniform" values in one instruction (avoiding a previous load of the constant value to a register), and increases some pairing for the same reason. total uniforms in shared programs: 16231 -> 13374 (-17.60%) uniforms in affected programs: 10280 -> 7423 (-27.79%) total instructions in shared programs: 40795 -> 41168 (0.91%) instructions in affected programs: 25551 -> 25924 (1.46%) In a previous version of this patch I had a reduction in instruction count by forcing the other args alongside a SMALL_IMM to be in the A file or accumulators, but that increases register pressure and had a bug in handling FRAG_Z. In this patch is I just use raddr conflict resolution, which is more expensive. I think I'd rather tweak allocation to have some way to slightly prefer good choices for files in general, rather than risk failing to register allocate by forcing things into register classes.
Diffstat (limited to 'src/gallium/drivers/vc4/vc4_qir.h')
-rw-r--r--src/gallium/drivers/vc4/vc4_qir.h7
1 files changed, 7 insertions, 0 deletions
diff --git a/src/gallium/drivers/vc4/vc4_qir.h b/src/gallium/drivers/vc4/vc4_qir.h
index 40c0d3d04dd..db0a4367222 100644
--- a/src/gallium/drivers/vc4/vc4_qir.h
+++ b/src/gallium/drivers/vc4/vc4_qir.h
@@ -38,6 +38,12 @@ enum qfile {
QFILE_TEMP,
QFILE_VARY,
QFILE_UNIF,
+
+ /**
+ * Stores an immediate value in the index field that can be turned
+ * into a small immediate field by qpu_encode_small_immediate().
+ */
+ QFILE_SMALL_IMM,
};
struct qreg {
@@ -382,6 +388,7 @@ bool qir_opt_algebraic(struct vc4_compile *c);
bool qir_opt_copy_propagation(struct vc4_compile *c);
bool qir_opt_cse(struct vc4_compile *c);
bool qir_opt_dead_code(struct vc4_compile *c);
+bool qir_opt_small_immediates(struct vc4_compile *c);
void qpu_schedule_instructions(struct vc4_compile *c);