diff options
| author | Chris Wilson <chris@chris-wilson.co.uk> | 2011-12-10 22:45:25 +0000 |
|---|---|---|
| committer | Chris Wilson <chris@chris-wilson.co.uk> | 2011-12-11 00:52:54 +0000 |
| commit | 051a18063df075536cb1ac0dc4dfc3c1306ab74e (patch) | |
| tree | c485da7f3349fe814b863482a54d642ca9a4a92b /src/sna/kgem_debug_gen7.c | |
| parent | 735a15208dd600eefa3090f344186df9cac0462d (diff) | |
sna: Implement a VMA cache
A VMA cache appears unavoidable thanks to compiz and an excrutiatingly
slow GTT pagefault, though it does look like it will be ineffectual
during everyday usage. Compiz (and presumably other compositing
managers) appears to be undoing all the pagefault minimisation as
demonstrated on gen5 with large XPutImage. It also appears the CPU to
memory bandwidth ratio plays a crucial role in determining whether
going straight to GTT or through the CPU cache is a win - so no trivial
heuristic.
x11perf -putimage10 -putimage500 on i5-2467m:
Before:
bare: 1150,000 2,410
compiz: 438,000 2,670
After:
bare: 1190,000 2,730
compiz: 437,000 2,690
UXA:
bare: 658,000 2,670
compiz: 389,000 2,520
On i3-330m
Before:
bare: 537,000 1,080
compiz: 263,000 398
After:
bare: 606,000 1,360
compiz: 203,000 985
UXA:
bare: 294,000 1,070
compiz: 197,000 821
On pnv:
Before:
bare: 179,000 213
compiz: 106,000 123
After:
bare: 181,000 246
compiz: 103,000 197
UXA:
bare: 114,000 312
compiz: 75,700 191
Reported-by: Michael Larabel <Michael@phoronix.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Diffstat (limited to 'src/sna/kgem_debug_gen7.c')
| -rw-r--r-- | src/sna/kgem_debug_gen7.c | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/src/sna/kgem_debug_gen7.c b/src/sna/kgem_debug_gen7.c index f6a49752..a33a918d 100644 --- a/src/sna/kgem_debug_gen7.c +++ b/src/sna/kgem_debug_gen7.c @@ -89,7 +89,7 @@ static void gen7_update_vertex_buffer(struct kgem *kgem, const uint32_t *data) i = data[0] >> 26; if (state.vb[i].current) - munmap(state.vb[i].base, state.vb[i].current->size); + kgem_bo_unmap(kgem, state.vb[i].base); state.vb[i].current = bo; state.vb[i].base = base; @@ -130,7 +130,7 @@ static void gen7_update_dynamic_buffer(struct kgem *kgem, const uint32_t offset) } if (state.dynamic_state.current) - munmap(state.dynamic_state.base, state.dynamic_state.current->size); + kgem_bo_unmap(kgem, state.dynamic_state.base); state.dynamic_state.current = bo; state.dynamic_state.base = base; @@ -306,7 +306,7 @@ static void finish_vertex_buffers(struct kgem *kgem) for (i = 0; i < ARRAY_SIZE(state.vb); i++) if (state.vb[i].current) - munmap(state.vb[i].base, state.vb[i].current->size); + kgem_bo_unmap(kgem, state.vb[i].current); } static void finish_state(struct kgem *kgem) @@ -314,7 +314,7 @@ static void finish_state(struct kgem *kgem) finish_vertex_buffers(kgem); if (state.dynamic_state.current) - munmap(state.dynamic_state.base, state.dynamic_state.current->size); + kgem_bo_unmap(kgem, state.dynamic_state.base); memset(&state, 0, sizeof(state)); } @@ -482,7 +482,7 @@ static void put_reloc(struct kgem *kgem, struct reloc *r) { if (r->bo != NULL) - munmap(r->base, r->bo->size); + kgem_bo_unmap(kgem, r->bo); } static const char * |