a059b29930
Two main goals of this PR are: * to support "Arithmetic with Overflow" intrinsics, including the special case when those intrinsics are being generated by the CodeGenPrepare pass during translations with optimization; * to redirect intrinsics with aggregate return type to be lowered via GlobalISel operations instead of SPIRV-specific unfolding/lowering (see https://github.com/llvm/llvm-project/pull/95012). There is a new test case `llvm/test/CodeGen/SPIRV/passes/translate-aggregate-uaddo.ll` that describes and checks the general logics of the translation. This PR continues a series of PRs aimed to identify and fix flaws in code emission, to improve pass rates for the mode with expensive checks set on (see https://github.com/llvm/llvm-project/pull/101732, https://github.com/llvm/llvm-project/pull/104104, https://github.com/llvm/llvm-project/pull/106966), having in mind the ultimate goal of proceeding towards the non-experimental status of SPIR-V Backend. The reproducers are: 1) consider `llc -O3 -mtriple=spirv64-unknown-unknown ...` with: ``` define spir_func i32 @foo(i32 %a, ptr addrspace(4) %p) { entry: br label %l1 l1: %e = phi i32 [ %a, %entry ], [ %i, %body ] %i = add nsw i32 %e, 1 %fl = icmp eq i32 %i, 0 br i1 %fl, label %exit, label %body body: store i8 42, ptr addrspace(4) %p br label %l1 exit: ret i32 %i } ``` 2) consider `llc -O0 -mtriple=spirv64-unknown-unknown ...` with: ``` define spir_func i32 @foo(i32 %a, ptr addrspace(4) %p) { entry: br label %l1 l1: ; preds = %body, %entry %e = phi i32 [ %a, %entry ], [ %math, %body ] %0 = call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %e, i32 1) %math = extractvalue { i32, i1 } %0, 0 %ov = extractvalue { i32, i1 } %0, 1 br i1 %ov, label %exit, label %body body: ; preds = %l1 store i8 42, ptr addrspace(4) %p, align 1 br label %l1 exit: ; preds = %l1 ret i32 %math } ```
57 lines
2.1 KiB
LLVM
57 lines
2.1 KiB
LLVM
; This test aims to check ability to support "Arithmetic with Overflow" intrinsics
|
|
; in the special case when those intrinsics are being generated by the CodeGenPrepare;
|
|
; pass during translations with optimization (note -O3 in llc arguments).
|
|
|
|
; RUN: llc -O3 -mtriple=spirv32-unknown-unknown %s -o - | FileCheck %s
|
|
; RUN: %if spirv-tools %{ llc -O3 -mtriple=spirv32-unknown-unknown %s -o - -filetype=obj | spirv-val %}
|
|
|
|
; RUN: llc -O3 -mtriple=spirv64-unknown-unknown %s -o - | FileCheck %s
|
|
; RUN: %if spirv-tools %{ llc -O3 -mtriple=spirv64-unknown-unknown %s -o - -filetype=obj | spirv-val %}
|
|
|
|
; CHECK-DAG: OpName %[[Val:.*]] "math"
|
|
; CHECK-DAG: OpName %[[IsOver:.*]] "ov"
|
|
; CHECK-DAG: %[[Int:.*]] = OpTypeInt 32 0
|
|
; CHECK-DAG: %[[Char:.*]] = OpTypeInt 8 0
|
|
; CHECK-DAG: %[[PtrChar:.*]] = OpTypePointer Generic %[[Char]]
|
|
; CHECK-DAG: %[[Bool:.*]] = OpTypeBool
|
|
; CHECK-DAG: %[[Struct:.*]] = OpTypeStruct %[[Int]] %[[Int]]
|
|
; CHECK-DAG: %[[Const1:.*]] = OpConstant %[[Int]] 1
|
|
; CHECK-DAG: %[[Const42:.*]] = OpConstant %[[Char]] 42
|
|
; CHECK-DAG: %[[Zero:.*]] = OpConstantNull %[[Int]]
|
|
|
|
; CHECK: OpFunction
|
|
; CHECK: %[[A:.*]] = OpFunctionParameter %[[Int]]
|
|
; CHECK: %[[Ptr:.*]] = OpFunctionParameter %[[PtrChar]]
|
|
; CHECK: %[[#]] = OpLabel
|
|
; CHECK: OpBranch %[[#]]
|
|
; CHECK: %[[#]] = OpLabel
|
|
; CHECK: %[[PhiRes:.*]] = OpPhi %[[Int]] %[[A]] %[[#]] %[[Val]] %[[#]]
|
|
; CHECK: %[[AggRes:.*]] = OpIAddCarry %[[Struct]] %[[PhiRes]] %[[Const1]]
|
|
; CHECK: %[[Val]] = OpCompositeExtract %[[Int]] %[[AggRes]] 0
|
|
; CHECK: %[[Over:.*]] = OpCompositeExtract %[[Int]] %[[AggRes]] 1
|
|
; CHECK: %[[IsOver]] = OpINotEqual %[[Bool:.*]] %[[Over]] %[[Zero]]
|
|
; CHECK: OpBranchConditional %[[IsOver]] %[[#]] %[[#]]
|
|
; CHECK: OpStore %[[Ptr]] %[[Const42]] Aligned 1
|
|
; CHECK: OpBranch %[[#]]
|
|
; CHECK: %[[#]] = OpLabel
|
|
; CHECK: OpReturnValue %[[Val]]
|
|
; CHECK: OpFunctionEnd
|
|
|
|
define spir_func i32 @foo(i32 %a, ptr addrspace(4) %p) {
|
|
entry:
|
|
br label %l1
|
|
|
|
body:
|
|
store i8 42, ptr addrspace(4) %p
|
|
br label %l1
|
|
|
|
l1:
|
|
%e = phi i32 [ %a, %entry ], [ %i, %body ]
|
|
%i = add nsw i32 %e, 1
|
|
%fl = icmp eq i32 %i, 0
|
|
br i1 %fl, label %exit, label %body
|
|
|
|
exit:
|
|
ret i32 %i
|
|
}
|