Stefan Dirsch
07667cc47b
* Fix loading of a 3x16 vector as a single 48-bit load on
big-endian systems (PPC64, S390). [fdo#100613]
OBS-URL: https://build.opensuse.org/package/show/X11:XOrg/Mesa?expand=0&rev=617
50 lines
1.9 KiB
Diff
50 lines
1.9 KiB
Diff
From 3f993cdf6db5cf344179fcb4fbf899f6ef9a6b2b Mon Sep 17 00:00:00 2001
|
|
From: Ben Crocker <bcrocker@redhat.com>
|
|
Date: Tue, 30 May 2017 12:34:23 -0400
|
|
Subject: [PATCH] llvmpipe: lp_build_gather_elem_vec BE fix for 3x16 load
|
|
|
|
Fix loading of a 3x16 vector as a single 48-bit load
|
|
on big-endian systems (PPC64, S390).
|
|
|
|
Signed-off-by: Ben Crocker <bcrocker@redhat.com>
|
|
---
|
|
src/gallium/auxiliary/gallivm/lp_bld_gather.c | 17 +++++++++++++++--
|
|
1 file changed, 15 insertions(+), 2 deletions(-)
|
|
|
|
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_gather.c b/src/gallium/auxiliary/gallivm/lp_bld_gather.c
|
|
index ccd0376..8e56e42 100644
|
|
--- a/src/gallium/auxiliary/gallivm/lp_bld_gather.c
|
|
+++ b/src/gallium/auxiliary/gallivm/lp_bld_gather.c
|
|
@@ -234,13 +234,26 @@ lp_build_gather_elem_vec(struct gallivm_state *gallivm,
|
|
*/
|
|
res = LLVMBuildZExt(gallivm->builder, res, dst_elem_type, "");
|
|
|
|
- if (vector_justify) {
|
|
#ifdef PIPE_ARCH_BIG_ENDIAN
|
|
+ if (vector_justify) {
|
|
res = LLVMBuildShl(gallivm->builder, res,
|
|
LLVMConstInt(dst_elem_type,
|
|
dst_type.width - src_width, 0), "");
|
|
-#endif
|
|
}
|
|
+ if (src_width == 48) {
|
|
+ LLVMValueRef shuffles[4] = {
|
|
+ lp_build_const_int32(gallivm, 2),
|
|
+ lp_build_const_int32(gallivm, 1),
|
|
+ lp_build_const_int32(gallivm, 0),
|
|
+ lp_build_const_int32(gallivm, 3),
|
|
+ };
|
|
+ struct lp_type type16 = {FALSE, FALSE, TRUE, FALSE, 16, 4};
|
|
+ res = LLVMBuildBitCast(gallivm->builder, res,
|
|
+ lp_build_vec_type(gallivm, type16), "");
|
|
+ res = LLVMBuildShuffleVector(gallivm->builder, res, res, LLVMConstVector(shuffles, 4), "");
|
|
+ res = LLVMBuildBitCast(gallivm->builder, res, dst_elem_type, "");
|
|
+ }
|
|
+#endif
|
|
}
|
|
}
|
|
return res;
|
|
--
|
|
2.7.4
|
|
|