0a443f13b4
This PR: * adds support for G_SPLAT_VECTOR generic opcode that may be legally generated instead of G_BUILD_VECTOR by previous passes of the translator (see https://github.com/llvm/llvm-project/pull/80378 for the source of breaking changes); * improves deduction of types for opaque pointers. This PR also fixes the following issues: * if a function has ptr argument(s), two functions that have different SPIR-V type definitions may get identical LLVM function types and break agreements of global register and duplicate checker; * checks for pointer types do not account for TypedPointerType. Update of tests: * A test case is added to cover the issue with function ptr parameters. * The first case, that is support for G_SPLAT_VECTOR generic opcode, is covered by existing test cases. * Multiple additional checks by `spirv-val` is added to cover more possibilities of generation of invalid code.
20 lines
759 B
LLVM
20 lines
759 B
LLVM
; RUN: llc -O0 -mtriple=spirv32-unknown-unknown %s -o - | FileCheck %s --check-prefix=CHECK-SPIRV
|
|
; TODO: %if spirv-tools %{ llc -O0 -mtriple=spirv32-unknown-unknown %s -o - -filetype=obj | spirv-val %}
|
|
|
|
; CHECK-SPIRV: OpCapability GroupNonUniformBallot
|
|
; CHECK-SPIRV: OpDecorate %[[#]] BuiltIn SubgroupGtMask
|
|
|
|
;; kernel void test_mask(global uint4 *out)
|
|
;; {
|
|
;; *out = get_sub_group_gt_mask();
|
|
;; }
|
|
|
|
define dso_local spir_kernel void @test_mask(<4 x i32> addrspace(1)* nocapture noundef writeonly %out) local_unnamed_addr {
|
|
entry:
|
|
%call = tail call spir_func <4 x i32> @_Z21get_sub_group_gt_maskv()
|
|
store <4 x i32> %call, <4 x i32> addrspace(1)* %out, align 16
|
|
ret void
|
|
}
|
|
|
|
declare spir_func <4 x i32> @_Z21get_sub_group_gt_maskv() local_unnamed_addr
|