vc4: Pair up QPU instructions when scheduling.

We've got two mostly-independent operations in each QPU instruction, so
try to pack two operations together.  This is fairly naive (doesn't track
read and write separately in instructions, doesn't convert ADD-based MOVs
into MUL-based movs, doesn't reorder across uniform loads), but does show
a decent improvement on shader-db-2.

total instructions in shared programs: 59583 -> 57651 (-3.24%)
instructions in affected programs:     47361 -> 45429 (-4.08%)

1 files changed, 1 insertions, 1 deletions

diff --git a/src/gallium/drivers/vc4/vc4_qpu.h b/src/gallium/drivers/vc4/vc4_qpu.h
index bf41f72..eb06d1a 100644
--- a/src/gallium/drivers/vc4/vc4_qpu.h
+++ b/src/gallium/drivers/vc4/vc4_qpu.h
@@ -129,7 +129,7 @@ uint64_t qpu_a_alu2(enum qpu_op_add op, struct qpu_reg dst,
                     struct qpu_reg src0, struct qpu_reg src1);
 uint64_t qpu_m_alu2(enum qpu_op_mul op, struct qpu_reg dst,
                     struct qpu_reg src0, struct qpu_reg src1);
-uint64_t qpu_inst(uint64_t add, uint64_t mul);
+uint64_t qpu_merge_inst(uint64_t a, uint64_t b);
 uint64_t qpu_load_imm_ui(struct qpu_reg dst, uint32_t val);
 uint64_t qpu_set_sig(uint64_t inst, uint32_t sig);
 uint64_t qpu_set_cond_add(uint64_t inst, uint32_t cond);