aboutsummaryrefslogtreecommitdiffstats
path: root/src/gallium/auxiliary
diff options
context:
space:
mode:
authorRoland Scheidegger <[email protected]>2016-12-21 04:53:41 +0100
committerRoland Scheidegger <[email protected]>2017-01-05 23:59:38 +0100
commita03a2ac6fd3005218eeddeae89e60115fbedde85 (patch)
tree12adcdccc080b581f5b8e4c8d38074db8347e103 /src/gallium/auxiliary
parentdb7e786a2552d808e512ba33fbc9b19d8bb37108 (diff)
gallivm: use 2 srcs for 32->16bit conversions in lp_bld_conv_auto
If we only feed one source vector at a time, we cannot use pack intrinsics (as we only have a 64bit destination dst vector). lp_bld_conv_auto is specifically designed to alter the length and number of destination vectors, so this works just fine (if we use single source vectors at a time, afterwards we immediately reassemble the vectors). For AVX though this isn't really possible, since we expect 128bit output already for a single 256bit input. (One day we should handle AVX2 which again would need multiple inputs, however there's the problem that we get different ordered output there and we don't want to reorder, so would need to be able to tell build_conv to handle upper and lower halfs independently.) A similar strategy would probably work for 32->8bit too (if it doesn't hit the special case) but I'm going to try something different for that... Reviewed-by: Jose Fonseca <[email protected]>
Diffstat (limited to 'src/gallium/auxiliary')
-rw-r--r--src/gallium/auxiliary/gallivm/lp_bld_conv.c21
1 files changed, 19 insertions, 2 deletions
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_conv.c b/src/gallium/auxiliary/gallivm/lp_bld_conv.c
index 69d24a55bce..c8f9c28ddc6 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_conv.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_conv.c
@@ -497,8 +497,25 @@ int lp_build_conv_auto(struct gallivm_state *gallivm,
if (src_type.width == dst_type->width) {
lp_build_conv(gallivm, src_type, *dst_type, src, num_srcs, dst, num_dsts);
} else {
- for (i = 0; i < num_srcs; ++i) {
- lp_build_conv(gallivm, src_type, *dst_type, &src[i], 1, &dst[i], 1);
+ /*
+ * If dst_width is 16 bits and src_width 32 and the dst vector size
+ * 64bit, try feeding 2 vectors at once so pack intrinsics can be used.
+ * (For AVX, this isn't needed, since we usually get 256bit src and
+ * 128bit dst vectors which works ok. If we do AVX2 pack this should
+ * be extended but need to be able to tell conversion code about pack
+ * ordering first.)
+ */
+ unsigned ratio = 1;
+ if (src_type.width == 2 * dst_type->width &&
+ src_type.length == dst_type->length &&
+ dst_type->floating == 0 && (num_srcs % 2 == 0) &&
+ dst_type->width * dst_type->length == 64) {
+ ratio = 2;
+ num_dsts /= 2;
+ dst_type->length *= 2;
+ }
+ for (i = 0; i < num_dsts; i++) {
+ lp_build_conv(gallivm, src_type, *dst_type, &src[i*ratio], ratio, &dst[i], 1);
}
}