broadcom/compiler: fix incorrect check for SFU op

Before testing the waddr for SFU we should first validate this
is indeed a valid (not NOP) magic write. Use the helper we have for
this which gets this right.

total instructions in shared programs: 12898957 -> 12850958 (-0.37%)
instructions in affected programs: 4328937 -> 4280938 (-1.11%)
helped: 19974
HURT: 439
Instructions are helped.

total max-temps in shared programs: 2211503 -> 2210893 (-0.03%)
max-temps in affected programs: 12924 -> 12314 (-4.72%)
helped: 509
HURT: 20
Max-temps are helped.

total sfu-stalls in shared programs: 22233 -> 21975 (-1.16%)
sfu-stalls in affected programs: 722 -> 464 (-35.73%)
helped: 297
HURT: 54
Sfu-stalls are helped.

total inst-and-stalls in shared programs: 12921190 -> 12872933 (-0.37%)
inst-and-stalls in affected programs: 4337977 -> 4289720 (-1.11%)
helped: 20015
HURT: 404
Inst-and-stalls are helped.

total nops in shared programs: 333743 -> 305911 (-8.34%)
nops in affected programs: 86902 -> 59070 (-32.03%)
helped: 14545
HURT: 76
Nops are helped.

Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
cc: mesa-stable

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22593>

diff --git a/src/broadcom/compiler/qpu_schedule.c b/src/broadcom/compiler/qpu_schedule.c
index bdf5ede..c5742db 100644 (file)
--- a/src/broadcom/compiler/qpu_schedule.c
+++ b/src/broadcom/compiler/qpu_schedule.c
@@ -1641,12 +1641,8 @@ qpu_inst_before_thrsw_valid_in_delay_slot(struct v3d_compile *c,
          * thread.  The simulator complains for safety, though it
          * would only occur for dead code in our case.
          */
-        if (slot > 0 &&
-            qinst->qpu.type == V3D_QPU_INSTR_TYPE_ALU &&
-            (v3d_qpu_magic_waddr_is_sfu(qinst->qpu.alu.add.waddr) ||
-             v3d_qpu_magic_waddr_is_sfu(qinst->qpu.alu.mul.waddr))) {
+        if (slot > 0 && v3d_qpu_instr_is_legacy_sfu(&qinst->qpu))
                 return false;
-        }
 
         if (slot > 0 && qinst->qpu.sig.ldvary)
                 return false;