diff options
| author | Eric Anholt <[email protected]> | 2014-11-26 12:44:19 -0800 |
|---|---|---|
| committer | Eric Anholt <[email protected]> | 2014-12-01 11:00:23 -0800 |
| commit | 3fe4d8e1e39b47c9c5c4bfdd87300abd0c336a7e (patch) | |
| tree | 5ac8c5cee06176519262f90dabb3d304c120f655 /src/gallium/drivers/vc4/vc4_qpu.h | |
| parent | 6958c404caf3f4b2219ef686e2beeeaf48664905 (diff) | |
vc4: Introduce scheduling of QPU instructions.
This doesn't reschedule much currently, just tries to fit things into the
regfile A/B write-versus-read slots (the cause of the improvements in
shader-db), and hide texture fetch latency by scheduling setup early and
results collection late (haven't performance tested it). This
infrastructure will be important for doing instruction pairing, though.
shader-db2 results:
total instructions in shared programs: 61874 -> 59583 (-3.70%)
instructions in affected programs: 50677 -> 48386 (-4.52%)
Diffstat (limited to 'src/gallium/drivers/vc4/vc4_qpu.h')
| -rw-r--r-- | src/gallium/drivers/vc4/vc4_qpu.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/src/gallium/drivers/vc4/vc4_qpu.h b/src/gallium/drivers/vc4/vc4_qpu.h index 5f4caab193e..bf41f72c34b 100644 --- a/src/gallium/drivers/vc4/vc4_qpu.h +++ b/src/gallium/drivers/vc4/vc4_qpu.h @@ -30,6 +30,8 @@ #include "vc4_qpu_defines.h" +struct vc4_compile; + struct qpu_reg { enum qpu_mux mux; uint8_t addr; @@ -135,6 +137,7 @@ uint64_t qpu_set_cond_mul(uint64_t inst, uint32_t cond); bool qpu_waddr_is_tlb(uint32_t waddr); bool qpu_inst_is_tlb(uint64_t inst); +void qpu_serialize_one_inst(struct vc4_compile *c, uint64_t inst); static inline uint64_t qpu_load_imm_f(struct qpu_reg dst, float val) |