diff options
| author | Roland Scheidegger <[email protected]> | 2013-06-05 00:11:45 +0200 |
|---|---|---|
| committer | Roland Scheidegger <[email protected]> | 2013-06-05 00:29:46 +0200 |
| commit | 44993c1808dc10da36cac156408a10e05b5dc140 (patch) | |
| tree | 7d5378d8d56ce371c7e80696af69f739e4a9f736 /src/gallium/drivers/llvmpipe | |
| parent | ce82523db93d31bc72c8683ccbded1cc721ad34f (diff) | |
gallivm: enhance special sse2 4x4f and 2x8f -> 1x16ub conversion
There's no good reason why it can't handle 2x4f->1x8ub, 1x4f->1x4ub and
1x8f->1x8ub cases, there might be legitimate reasons why we don't have
enough input vectors for a full destination vector, and using pack
intrinsics should still be much better than using generic conversion
(it looks like convert_alpha from the blend code might hit this though
I suspect it could be avoided).
v2: add another test vector format to lp_test_conv so this gets tested.
Reviewed-by: Jose Fonseca <[email protected]>
Diffstat (limited to 'src/gallium/drivers/llvmpipe')
| -rw-r--r-- | src/gallium/drivers/llvmpipe/lp_test_conv.c | 2 |
1 files changed, 2 insertions, 0 deletions
diff --git a/src/gallium/drivers/llvmpipe/lp_test_conv.c b/src/gallium/drivers/llvmpipe/lp_test_conv.c index 71d45bd5ce7..e2ec6e2bb45 100644 --- a/src/gallium/drivers/llvmpipe/lp_test_conv.c +++ b/src/gallium/drivers/llvmpipe/lp_test_conv.c @@ -377,6 +377,8 @@ const struct lp_type conv_types[] = { { FALSE, FALSE, TRUE, FALSE, 8, 4 }, { FALSE, FALSE, FALSE, TRUE, 8, 4 }, { FALSE, FALSE, FALSE, FALSE, 8, 4 }, + + { FALSE, FALSE, FALSE, TRUE, 8, 8 }, }; |