can_speculate, true);
}
+LLVMValueRef
+ac_build_tbuffer_load_short(struct ac_llvm_context *ctx,
+ LLVMValueRef rsrc,
+ LLVMValueRef vindex,
+ LLVMValueRef voffset,
+ LLVMValueRef soffset,
+ LLVMValueRef immoffset)
+{
+ const char *name = "llvm.amdgcn.tbuffer.load.i32";
+ LLVMTypeRef type = ctx->i32;
+ LLVMValueRef params[] = {
+ rsrc,
+ vindex,
+ voffset,
+ soffset,
+ immoffset,
+ LLVMConstInt(ctx->i32, V_008F0C_BUF_DATA_FORMAT_16, false),
+ LLVMConstInt(ctx->i32, V_008F0C_BUF_NUM_FORMAT_UINT, false),
+ ctx->i1false,
+ ctx->i1false,
+ };
+ LLVMValueRef res = ac_build_intrinsic(ctx, name, type, params, 9, 0);
+ return LLVMBuildTrunc(ctx->builder, res, ctx->i16, "");
+}
+
/**
* Set range metadata on an instruction. This can only be used on load and
* call instructions. If you know an instruction can only produce the values
if (instr->dest.ssa.bit_size == 64)
num_components *= 2;
- ret = ac_build_buffer_load(&ctx->ac, rsrc, num_components, NULL, offset,
- NULL, 0, false, false, true, true);
- ret = ac_trim_vector(&ctx->ac, ret, num_components);
+ if (instr->dest.ssa.bit_size == 16) {
+ LLVMValueRef results[num_components];
+ for (unsigned i = 0; i < num_components; ++i) {
+ results[i] = ac_build_tbuffer_load_short(&ctx->ac,
+ rsrc,
+ ctx->ac.i32_0,
+ offset,
+ ctx->ac.i32_0,
+ LLVMConstInt(ctx->ac.i32, 2 * i, 0));
+ }
+ ret = ac_build_gather_values(&ctx->ac, results, num_components);
+ } else {
+ ret = ac_build_buffer_load(&ctx->ac, rsrc, num_components, NULL, offset,
+ NULL, 0, false, false, true, true);
+
+ ret = ac_trim_vector(&ctx->ac, ret, num_components);
+ }
+
return LLVMBuildBitCast(ctx->ac.builder, ret,
get_def_type(ctx, &instr->dest.ssa), "");
}