diff options
| author | Connor Abbott <[email protected]> | 2017-06-07 14:16:31 -0700 |
|---|---|---|
| committer | Connor Abbott <[email protected]> | 2017-07-03 11:58:58 -0700 |
| commit | 7168425dd77f37fa048de5a4639619763556c331 (patch) | |
| tree | cb904e94d04683812d7afc1f9ec4f8e7369826a2 /src/amd/vulkan/radv_pipeline.c | |
| parent | 196e6b60b1e392c5e55c07a9f9b4e85dad52fb66 (diff) | |
ac/nir: implement 64-bit packing and unpacking
We implement the split opcodes, and tell NIR to lower the original ones.
The lowering to LLVM is a little more complicated, but NIR can optimize
the split ones a little better, and some NIR lowering passes that we
might want to use (particularly for doubles) emit the split ones.
This should fix pack/unpackDouble2x32, which seems like a bug since when
we enabled the Float64 capability. It will also fix pack/unpackInt2x32
when we enable the Int64 capability.
Fixes: 798ae37c ("radv: Enable Float64 support.")
Signed-off-by: Connor Abbott <[email protected]>
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
Diffstat (limited to 'src/amd/vulkan/radv_pipeline.c')
| -rw-r--r-- | src/amd/vulkan/radv_pipeline.c | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/amd/vulkan/radv_pipeline.c b/src/amd/vulkan/radv_pipeline.c index efe641dc0be..d05acd28506 100644 --- a/src/amd/vulkan/radv_pipeline.c +++ b/src/amd/vulkan/radv_pipeline.c @@ -151,6 +151,7 @@ radv_optimize_nir(struct nir_shader *shader) progress = false; NIR_PASS_V(shader, nir_lower_vars_to_ssa); + NIR_PASS_V(shader, nir_lower_64bit_pack); NIR_PASS_V(shader, nir_lower_alu_to_scalar); NIR_PASS_V(shader, nir_lower_phis_to_scalar); |