diff options
author | Ben Crocker <[email protected]> | 2017-08-23 16:32:43 -0400 |
---|---|---|
committer | Roland Scheidegger <[email protected]> | 2017-09-01 01:20:07 +0200 |
commit | 57c8ead0cd08e6aaf88a389f7ce528c4f0face65 (patch) | |
tree | 8a5ba98fafa63f619d9ce74fe877e575f0afe524 /src | |
parent | 75cb6e36178b9474bbb59b76cbbcce2a67bf88d2 (diff) |
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).
Roland Scheidegger's commit e827d9175675aaa6cfc0b981e2a80685fb7b3a74
plus Ray Strode's patch reduce pre-Roland Piglit failures from ~4000 to ~2000. This patch fixes
three of the four regressions observed by Ray:
- draw-vertices
- draw-vertices-half-float
- draw-vertices-half-float_gles2
One regression remains:
- draw-vertices-2101010
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100613
Cc: "17.2" "17.1" <[email protected]>
Signed-off-by: Ben Crocker <[email protected]>
Reviewed-by: Roland Scheidegger <[email protected]>
Diffstat (limited to 'src')
-rw-r--r-- | src/gallium/auxiliary/gallivm/lp_bld_gather.c | 30 |
1 files changed, 28 insertions, 2 deletions
diff --git a/src/gallium/auxiliary/gallivm/lp_bld_gather.c b/src/gallium/auxiliary/gallivm/lp_bld_gather.c index ccd03765c73..7d11dcd3b64 100644 --- a/src/gallium/auxiliary/gallivm/lp_bld_gather.c +++ b/src/gallium/auxiliary/gallivm/lp_bld_gather.c @@ -234,13 +234,39 @@ 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) { + /* Load 3x16 bit vector. + * The sequence of loads on big-endian hardware proceeds as follows. + * 16-bit fields are denoted by X, Y, Z, and 0. In memory, the sequence + * of three fields appears in the order X, Y, Z. + * + * Load 32-bit word: 0.0.X.Y + * Load 16-bit halfword: 0.0.0.Z + * Rotate left: 0.X.Y.0 + * Bitwise OR: 0.X.Y.Z + * + * The order in which we need the fields in the result is 0.Z.Y.X, + * the same as on little-endian; permute 16-bit fields accordingly + * within 64-bit register: + */ + 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), + }; + res = LLVMBuildBitCast(gallivm->builder, res, + lp_build_vec_type(gallivm, lp_type_uint_vec(16, 4*16)), ""); + res = LLVMBuildShuffleVector(gallivm->builder, res, res, LLVMConstVector(shuffles, 4), ""); + res = LLVMBuildBitCast(gallivm->builder, res, dst_elem_type, ""); + } +#endif } } return res; |