cdb9738963
Bug noted in D112717 can be sidestepped with this change. Expanding all ConstantExpr involved with LDS up front makes the variable specialisation simpler. Excludes ConstantExpr that don't access LDS to avoid disturbing codegen elsewhere. Reviewed By: rampitec Differential Revision: https://reviews.llvm.org/D133422
137 lines
8.3 KiB
LLVM
137 lines
8.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: -p --check-globals
|
|
; RUN: opt -S -mtriple=amdgcn-- -amdgpu-lower-module-lds < %s | FileCheck %s
|
|
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s | FileCheck %s
|
|
|
|
@lds.1 = internal unnamed_addr addrspace(3) global [2 x i8] undef, align 1
|
|
|
|
; CHECK: %llvm.amdgcn.kernel.k0.lds.t = type { [2 x i8] }
|
|
; CHECK: %llvm.amdgcn.kernel.k1.lds.t = type { [2 x i8] }
|
|
; CHECK: %llvm.amdgcn.kernel.k2.lds.t = type { i32 }
|
|
; CHECK: %llvm.amdgcn.kernel.k3.lds.t = type { [32 x i8] }
|
|
; CHECK: %llvm.amdgcn.kernel.k4.lds.t = type { [2 x i8] }
|
|
; CHECK: %llvm.amdgcn.kernel.k5.lds.t = type { [505 x i32] }
|
|
; CHECK: %llvm.amdgcn.kernel.k6.lds.t = type { [4 x i32] }
|
|
|
|
; Use constant from different kernels
|
|
;.
|
|
; CHECK: @llvm.amdgcn.kernel.k0.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k0.lds.t undef, align 2
|
|
; CHECK: @llvm.amdgcn.kernel.k1.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k1.lds.t undef, align 2
|
|
; CHECK: @llvm.amdgcn.kernel.k2.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k2.lds.t undef, align 4
|
|
; CHECK: @llvm.amdgcn.kernel.k3.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k3.lds.t undef, align 16
|
|
; CHECK: @llvm.amdgcn.kernel.k4.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k4.lds.t undef, align 2
|
|
; CHECK: @llvm.amdgcn.kernel.k5.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k5.lds.t undef, align 16
|
|
; CHECK: @llvm.amdgcn.kernel.k6.lds = internal addrspace(3) global %llvm.amdgcn.kernel.k6.lds.t undef, align 16
|
|
;.
|
|
define amdgpu_kernel void @k0(i64 %x) {
|
|
; CHECK-LABEL: @k0(
|
|
; CHECK-NEXT: %1 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k0.lds.t, %llvm.amdgcn.kernel.k0.lds.t addrspace(3)* @llvm.amdgcn.kernel.k0.lds, i32 0, i32 0), i32 0, i32 0
|
|
; CHECK-NEXT: %2 = addrspacecast i8 addrspace(3)* %1 to i8*
|
|
; CHECK-NEXT: %ptr = getelementptr inbounds i8, i8* %2, i64 %x
|
|
; CHECK-NEXT: store i8 1, i8* %ptr, align 1
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr = getelementptr inbounds i8, i8* addrspacecast ([2 x i8] addrspace(3)* @lds.1 to i8*), i64 %x
|
|
store i8 1, i8 addrspace(0)* %ptr, align 1
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @k1(i64 %x) {
|
|
; CHECK-LABEL: @k1(
|
|
; CHECK-NEXT: %1 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k1.lds.t, %llvm.amdgcn.kernel.k1.lds.t addrspace(3)* @llvm.amdgcn.kernel.k1.lds, i32 0, i32 0), i32 0, i32 0
|
|
; CHECK-NEXT: %2 = addrspacecast i8 addrspace(3)* %1 to i8*
|
|
; CHECK-NEXT: %ptr = getelementptr inbounds i8, i8* %2, i64 %x
|
|
; CHECK-NEXT: store i8 1, i8* %ptr, align 1
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr = getelementptr inbounds i8, i8* addrspacecast ([2 x i8] addrspace(3)* @lds.1 to i8*), i64 %x
|
|
store i8 1, i8 addrspace(0)* %ptr, align 1
|
|
ret void
|
|
}
|
|
|
|
@lds.2 = internal unnamed_addr addrspace(3) global i32 undef, align 4
|
|
|
|
; Use constant twice from the same kernel
|
|
define amdgpu_kernel void @k2(i64 %x) {
|
|
; CHECK-LABEL: @k2(
|
|
; CHECK-NEXT: %ptr1 = bitcast i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k2.lds.t, %llvm.amdgcn.kernel.k2.lds.t addrspace(3)* @llvm.amdgcn.kernel.k2.lds, i32 0, i32 0) to i8 addrspace(3)*
|
|
; CHECK-NEXT: store i8 1, i8 addrspace(3)* %ptr1, align 4
|
|
; CHECK-NEXT: %ptr2 = bitcast i32 addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k2.lds.t, %llvm.amdgcn.kernel.k2.lds.t addrspace(3)* @llvm.amdgcn.kernel.k2.lds, i32 0, i32 0) to i8 addrspace(3)*
|
|
; CHECK-NEXT: store i8 2, i8 addrspace(3)* %ptr2, align 4
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr1 = bitcast i32 addrspace(3)* @lds.2 to i8 addrspace(3)*
|
|
store i8 1, i8 addrspace(3)* %ptr1, align 4
|
|
%ptr2 = bitcast i32 addrspace(3)* @lds.2 to i8 addrspace(3)*
|
|
store i8 2, i8 addrspace(3)* %ptr2, align 4
|
|
ret void
|
|
}
|
|
|
|
@lds.3 = internal unnamed_addr addrspace(3) global [32 x i8] undef, align 1
|
|
|
|
; Use constant twice from the same kernel but a different other constant.
|
|
define amdgpu_kernel void @k3(i64 %x) {
|
|
; CHECK-LABEL: @k3(
|
|
; CHECK-NEXT: %1 = getelementptr inbounds [32 x i8], [32 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k3.lds.t, %llvm.amdgcn.kernel.k3.lds.t addrspace(3)* @llvm.amdgcn.kernel.k3.lds, i32 0, i32 0), i32 0, i32 16
|
|
; CHECK-NEXT: %2 = bitcast i8 addrspace(3)* %1 to i64 addrspace(3)*
|
|
; CHECK-NEXT: %ptr1 = addrspacecast i64 addrspace(3)* %2 to i64*
|
|
; CHECK-NEXT: store i64 1, i64* %ptr1, align 1
|
|
; CHECK-NEXT: %3 = getelementptr inbounds [32 x i8], [32 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k3.lds.t, %llvm.amdgcn.kernel.k3.lds.t addrspace(3)* @llvm.amdgcn.kernel.k3.lds, i32 0, i32 0), i32 0, i32 24
|
|
; CHECK-NEXT: %4 = bitcast i8 addrspace(3)* %3 to i64 addrspace(3)*
|
|
; CHECK-NEXT: %ptr2 = addrspacecast i64 addrspace(3)* %4 to i64*
|
|
; CHECK-NEXT: store i64 2, i64* %ptr2, align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr1 = addrspacecast i64 addrspace(3)* bitcast (i8 addrspace(3)* getelementptr inbounds ([32 x i8], [32 x i8] addrspace(3)* @lds.3, i32 0, i32 16) to i64 addrspace(3)*) to i64*
|
|
store i64 1, i64* %ptr1, align 1
|
|
%ptr2 = addrspacecast i64 addrspace(3)* bitcast (i8 addrspace(3)* getelementptr inbounds ([32 x i8], [32 x i8] addrspace(3)* @lds.3, i32 0, i32 24) to i64 addrspace(3)*) to i64*
|
|
store i64 2, i64* %ptr2, align 1
|
|
ret void
|
|
}
|
|
|
|
; @lds.1 is used from constant expressions in different kernels.
|
|
define amdgpu_kernel void @k4(i64 %x) {
|
|
; CHECK-LABEL: @k4(
|
|
; CHECK-NEXT: %1 = getelementptr inbounds [2 x i8], [2 x i8] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k4.lds.t, %llvm.amdgcn.kernel.k4.lds.t addrspace(3)* @llvm.amdgcn.kernel.k4.lds, i32 0, i32 0), i32 0, i32 0
|
|
; CHECK-NEXT: %2 = addrspacecast i8 addrspace(3)* %1 to i8*
|
|
; CHECK-NEXT: %ptr = getelementptr inbounds i8, i8* %2, i64 %x
|
|
; CHECK-NEXT: store i8 1, i8* %ptr, align 1
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
%ptr = getelementptr inbounds i8, i8* addrspacecast ([2 x i8] addrspace(3)* @lds.1 to i8*), i64 %x
|
|
store i8 1, i8 addrspace(0)* %ptr, align 1
|
|
ret void
|
|
}
|
|
|
|
@lds.4 = internal unnamed_addr addrspace(3) global [505 x i32] undef, align 4
|
|
|
|
; Multiple constexpr use in a same instruction.
|
|
define amdgpu_kernel void @k5() {
|
|
; CHECK-LABEL: @k5(
|
|
; CHECK-NEXT: %1 = addrspacecast [505 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k5.lds.t, %llvm.amdgcn.kernel.k5.lds.t addrspace(3)* @llvm.amdgcn.kernel.k5.lds, i32 0, i32 0) to [505 x i32]*
|
|
; CHECK-NEXT: %2 = getelementptr inbounds [505 x i32], [505 x i32]* %1, i64 0, i64 0
|
|
; CHECK-NEXT: %3 = addrspacecast [505 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k5.lds.t, %llvm.amdgcn.kernel.k5.lds.t addrspace(3)* @llvm.amdgcn.kernel.k5.lds, i32 0, i32 0) to [505 x i32]*
|
|
; CHECK-NEXT: %4 = getelementptr inbounds [505 x i32], [505 x i32]* %3, i64 0, i64 0
|
|
; CHECK-NEXT: call void undef(i32* %2, i32* %4)
|
|
;
|
|
call void undef(i32* getelementptr inbounds ([505 x i32], [505 x i32]* addrspacecast ([505 x i32] addrspace(3)* @lds.4 to [505 x i32]*), i64 0, i64 0), i32* getelementptr inbounds ([505 x i32], [505 x i32]* addrspacecast ([505 x i32] addrspace(3)* @lds.4 to [505 x i32]*), i64 0, i64 0))
|
|
ret void
|
|
}
|
|
|
|
@lds.5 = internal addrspace(3) global [4 x i32] undef, align 4
|
|
|
|
; Both the *value* and *pointer* operands of store instruction are constant expressions, and
|
|
; both of these constant expression paths use same lds - @lds.5. Hence both of these constant
|
|
; expression operands of store should be replaced by equivalent instruction sequences.
|
|
define amdgpu_kernel void @k6() {
|
|
; CHECK-LABEL: @k6(
|
|
|
|
; CHECK-NEXT: %1 = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k6.lds.t, %llvm.amdgcn.kernel.k6.lds.t addrspace(3)* @llvm.amdgcn.kernel.k6.lds, i32 0, i32 0), i32 0, i32 2
|
|
; CHECK-NEXT: %2 = ptrtoint i32 addrspace(3)* %1 to i32
|
|
; CHECK-NEXT: %3 = getelementptr inbounds [4 x i32], [4 x i32] addrspace(3)* getelementptr inbounds (%llvm.amdgcn.kernel.k6.lds.t, %llvm.amdgcn.kernel.k6.lds.t addrspace(3)* @llvm.amdgcn.kernel.k6.lds, i32 0, i32 0), i32 0, i32 2
|
|
; CHECK-NEXT: store i32 %2, i32 addrspace(3)* %3, align 8
|
|
; CHECK-NEXT: ret void
|
|
;
|
|
store i32 ptrtoint (i32 addrspace(3)* getelementptr inbounds ([4 x i32], [4 x i32] addrspace(3)* @lds.5, i32 0, i32 2) to i32), i32 addrspace(3)* getelementptr inbounds ([4 x i32], [4 x i32] addrspace(3)* @lds.5, i32 0, i32 2)
|
|
ret void
|
|
}
|