diff options
| author | Dave Airlie <[email protected]> | 2017-02-03 03:26:13 +0000 |
|---|---|---|
| committer | Dave Airlie <[email protected]> | 2017-02-03 19:53:03 +0000 |
| commit | 106a51440d018031b94c91758eecc7424a3bb5ee (patch) | |
| tree | f7c5156fc4fa17ccb0fa2afecc430f5bba0d42b7 /src/amd/common | |
| parent | a1a8aef4c9dbdf254036adada95f0d6e394c5d6a (diff) | |
radv: fix shared memory load/stores.
If we have an indirect index here we need to scale it by attribute slots
e.g. is this is vec2[256] then we get an indir_index in the 0.255 range
but the vec2 are aligned inside vec4 slots. So scale the indir index,
then extract the channels.
Reviewed-by: Bas Nieuwenhuizen <[email protected]>
Cc: "17.0" <[email protected]>
Signed-off-by: Dave Airlie <[email protected]>
Diffstat (limited to 'src/amd/common')
| -rw-r--r-- | src/amd/common/ac_nir_to_llvm.c | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/src/amd/common/ac_nir_to_llvm.c b/src/amd/common/ac_nir_to_llvm.c index 9be6e77f86b..566516fd8a3 100644 --- a/src/amd/common/ac_nir_to_llvm.c +++ b/src/amd/common/ac_nir_to_llvm.c @@ -2237,6 +2237,9 @@ static LLVMValueRef visit_load_var(struct nir_to_llvm_context *ctx, LLVMValueRef ptr = get_shared_memory_ptr(ctx, idx, ctx->i32); LLVMValueRef derived_ptr; + if (indir_index) + indir_index = LLVMBuildMul(ctx->builder, indir_index, LLVMConstInt(ctx->i32, 4, false), ""); + for (unsigned chan = 0; chan < ve; chan++) { LLVMValueRef index = LLVMConstInt(ctx->i32, chan, false); if (indir_index) @@ -2343,6 +2346,10 @@ visit_store_var(struct nir_to_llvm_context *ctx, break; case nir_var_shared: { LLVMValueRef ptr = get_shared_memory_ptr(ctx, idx, ctx->i32); + + if (indir_index) + indir_index = LLVMBuildMul(ctx->builder, indir_index, LLVMConstInt(ctx->i32, 4, false), ""); + for (unsigned chan = 0; chan < 8; chan++) { if (!(writemask & (1 << chan))) continue; |