[PATCH 1/2] infiniband: Help gcc generate better code for ocrdma_srq_toggle_bit
From: Rasmus Villemoes
Date: Fri Jan 16 2015 - 09:40:22 EST
gcc emits a surprising amount of code in order to flip a bit. One
would think that a single instruction is enough.
$ scripts/bloat-o-meter /tmp/ocrdma_verbs.o drivers/infiniband/hw/ocrdma/ocrdma_verbs.o
add/remove: 0/0 grow/shrink: 0/3 up/down: 0/-142 (-142)
function old new delta
ocrdma_post_srq_recv 498 460 -38
ocrdma_poll_cq 2010 1962 -48
ocrdma_discard_cqes 495 439 -56
All three calls of ocrdma_srq_toggle_bit happen within spinlocks, so
saving a few useless instructions might be worthwhile.
Signed-off-by: Rasmus Villemoes <linux@xxxxxxxxxxxxxxxxxx>
---
drivers/infiniband/hw/ocrdma/ocrdma_verbs.c | 5 +----
1 file changed, 1 insertion(+), 4 deletions(-)
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index fb8d8c4dfbb9..eff11e6c6183 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1484,10 +1484,7 @@ static void ocrdma_srq_toggle_bit(struct ocrdma_srq *srq, int idx)
int i = idx / 32;
unsigned int mask = (1 << (idx % 32));
- if (srq->idx_bit_fields[i] & mask)
- srq->idx_bit_fields[i] &= ~mask;
- else
- srq->idx_bit_fields[i] |= mask;
+ srq->idx_bit_fields[i] ^= mask;
}
static int ocrdma_hwq_free_cnt(struct ocrdma_qp_hwq_info *q)
--
2.1.3
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/