summaryrefslogtreecommitdiff
path: root/src
diff options
context:
space:
mode:
authorRoland Scheidegger <sroland@vmware.com>2013-07-31 16:57:50 +0200
committerRoland Scheidegger <sroland@vmware.com>2013-07-31 17:09:02 +0200
commitb1ed7202dfb64c01313e78bd4fe290ecd08bf5f7 (patch)
tree7f365fe4f5b0398688c8193795084f843f56b9de /src
parent8624a514c21e00ec51d4d9d2f4aee315378357ae (diff)
gallivm: use nearest rounding for float->unorm24 conversion
Previously we were using truncation, which gives the correct result only for numbers in [0.5-1.0] range (because there's no mantissa bits to do any rounding there). This is frequently hit (and probably only used there) when converting fragment depth to depth format (d24s8 etc.) or otherwise dealing with depth format. v2: as spotted by Jose, get rid of extra type (src_type is already unsigned). Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Diffstat (limited to 'src')
-rw-r--r--src/gallium/auxiliary/gallivm/lp_bld_conv.c10
1 files changed, 6 insertions, 4 deletions
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_conv.c b/src/gallium/auxiliary/gallivm/lp_bld_conv.c
index ba51ff794f6..712ce5f92dc 100644
--- a/src/gallium/auxiliary/gallivm/lp_bld_conv.c
+++ b/src/gallium/auxiliary/gallivm/lp_bld_conv.c
@@ -266,17 +266,19 @@ lp_build_clamped_float_to_unsigned_norm(struct gallivm_state *gallivm,
else if (dst_width == (mantissa + 1)) {
/*
* The destination width matches exactly what can be represented in
- * floating point (i.e., mantissa + 1 bits). So do a straight
- * multiplication followed by casting. No further rounding is necessary.
+ * floating point (i.e., mantissa + 1 bits). Even so correct rounding
+ * still needs to be applied (only for numbers in [0.5-1.0] would
+ * conversion using truncation after scaling be sufficient).
*/
-
double scale;
+ struct lp_build_context uf32_bld;
+ lp_build_context_init(&uf32_bld, gallivm, src_type);
scale = (double)((1ULL << dst_width) - 1);
res = LLVMBuildFMul(builder, src,
lp_build_const_vec(gallivm, src_type, scale), "");
- res = LLVMBuildFPToSI(builder, res, int_vec_type, "");
+ res = lp_build_iround(&uf32_bld, res);
}
else {
/*