cba70550cc
The "topological" sorting was behaving incorrectly in some cases: the exit of a loop could have a lower rank than a node in the loop. This causes issues when structurizing some patterns, and also codegen issues as we could generate BBs in the incorrect order in regard to the SPIR-V spec. Fixing this ordering alone broke other parts of the structurizer, which by luck worked. Had to fix those. Added more test cases, especially to test basic patterns. I also needed to tweak/disable some tests for 2 reasons: - SPIR-V now required reg2mem/mem2reg to run. Meaning dead stores are optimized away. Some tests require tweaks to avoid having the whole function removed. - Mem2Reg will generate variable & load/stores. This generates G_BITCAST in several cases. And there is currently something wrong we do with G_BITCAST which causes MIR verifier to complain. Until this is resolved, I disabled -verify-machineinstrs flag on those tests. --------- Signed-off-by: Nathan Gauër <brioche@google.com>
48 lines
1.8 KiB
LLVM
48 lines
1.8 KiB
LLVM
; RUN: llc -mtriple=spirv-unknown-vulkan-compute -O0 %s -o - | FileCheck %s
|
|
; RUN: %if spirv-tools %{ llc -O0 -mtriple=spirv-unknown-vulkan-compute %s -o - -filetype=obj | spirv-val %}
|
|
|
|
target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-G1"
|
|
target triple = "spirv-unknown-vulkan1.3-compute"
|
|
|
|
; Function Attrs: convergent noinline norecurse nounwind optnone
|
|
define spir_func noundef i32 @_Z7processv() #0 {
|
|
|
|
; CHECK: %[[#entry:]] = OpLabel
|
|
; CHECK: OpSelectionMerge %[[#merge:]] None
|
|
; CHECK: OpBranchConditional %[[#]] %[[#left:]] %[[#merge]]
|
|
entry:
|
|
%0 = call token @llvm.experimental.convergence.entry()
|
|
%1 = alloca i32, align 4
|
|
br i1 true, label %left, label %end
|
|
|
|
; CHECK: %[[#left]] = OpLabel
|
|
; CHECK: OpBranch %[[#merge]]
|
|
left:
|
|
store i32 0, ptr %1
|
|
br label %end
|
|
|
|
; CHECK: %[[#merge]] = OpLabel
|
|
; CHECK: OpReturnValue %[[#]]
|
|
end:
|
|
ret i32 0
|
|
}
|
|
|
|
; Function Attrs: convergent nocallback nofree nosync nounwind willreturn memory(none)
|
|
declare token @llvm.experimental.convergence.entry() #1
|
|
|
|
; Function Attrs: convergent nocallback nofree nosync nounwind willreturn memory(none)
|
|
declare token @llvm.experimental.convergence.loop() #1
|
|
|
|
|
|
attributes #0 = { convergent noinline norecurse nounwind optnone "frame-pointer"="all" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
|
|
attributes #1 = { convergent nocallback nofree nosync nounwind willreturn memory(none) }
|
|
attributes #2 = { convergent norecurse "frame-pointer"="all" "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
|
|
attributes #3 = { convergent }
|
|
|
|
!llvm.module.flags = !{!0, !1, !2}
|
|
|
|
|
|
!0 = !{i32 1, !"wchar_size", i32 4}
|
|
!1 = !{i32 4, !"dx.disable_optimizations", i32 1}
|
|
!2 = !{i32 7, !"frame-pointer", i32 2}
|