mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-25 14:02:52 +02:00
e2ddc2857d
This is a resubmittion of 263158 change after fixing the existing problem with intrinsics mangling (see LTO and intrinsics mangling llvm-dev thread for details). This patch fixes the problem which occurs when loop-vectorize tries to use @llvm.masked.load/store intrinsic for a non-default addrspace pointer. It fails with "Calling a function with a bad signature!" assertion in CallInst constructor because it tries to pass a non-default addrspace pointer to the pointer argument which has default addrspace. The fix is to add pointer type as another overloaded type to @llvm.masked.load/store intrinsics. Reviewed By: reames Differential Revision: http://reviews.llvm.org/D17270 llvm-svn: 274043
58 lines
2.3 KiB
LLVM
58 lines
2.3 KiB
LLVM
; RUN: opt -instcombine -S < %s | FileCheck %s
|
|
|
|
declare <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %ptrs, i32, <2 x i1> %mask, <2 x double> %src0)
|
|
declare void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %val, <2 x double>* %ptrs, i32, <2 x i1> %mask)
|
|
declare <2 x double> @llvm.masked.gather.v2f64(<2 x double*> %ptrs, i32, <2 x i1> %mask, <2 x double> %passthru)
|
|
declare void @llvm.masked.scatter.v2f64(<2 x double> %val, <2 x double*> %ptrs, i32, <2 x i1> %mask)
|
|
|
|
define <2 x double> @load_zeromask(<2 x double>* %ptr, <2 x double> %passthru) {
|
|
%res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %ptr, i32 1, <2 x i1> zeroinitializer, <2 x double> %passthru)
|
|
ret <2 x double> %res
|
|
|
|
; CHECK-LABEL: @load_zeromask(
|
|
; CHECK-NEXT: ret <2 x double> %passthru
|
|
}
|
|
|
|
define <2 x double> @load_onemask(<2 x double>* %ptr, <2 x double> %passthru) {
|
|
%res = call <2 x double> @llvm.masked.load.v2f64.p0v2f64(<2 x double>* %ptr, i32 2, <2 x i1> <i1 1, i1 1>, <2 x double> %passthru)
|
|
ret <2 x double> %res
|
|
|
|
; CHECK-LABEL: @load_onemask(
|
|
; CHECK-NEXT: %unmaskedload = load <2 x double>, <2 x double>* %ptr, align 2
|
|
; CHECK-NEXT: ret <2 x double> %unmaskedload
|
|
}
|
|
|
|
define void @store_zeromask(<2 x double>* %ptr, <2 x double> %val) {
|
|
call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %val, <2 x double>* %ptr, i32 3, <2 x i1> zeroinitializer)
|
|
ret void
|
|
|
|
; CHECK-LABEL: @store_zeromask(
|
|
; CHECK-NEXT: ret void
|
|
}
|
|
|
|
define void @store_onemask(<2 x double>* %ptr, <2 x double> %val) {
|
|
call void @llvm.masked.store.v2f64.p0v2f64(<2 x double> %val, <2 x double>* %ptr, i32 4, <2 x i1> <i1 1, i1 1>)
|
|
ret void
|
|
|
|
; CHECK-LABEL: @store_onemask(
|
|
; CHECK-NEXT: store <2 x double> %val, <2 x double>* %ptr, align 4
|
|
; CHECK-NEXT: ret void
|
|
}
|
|
|
|
define <2 x double> @gather_zeromask(<2 x double*> %ptrs, <2 x double> %passthru) {
|
|
%res = call <2 x double> @llvm.masked.gather.v2f64(<2 x double*> %ptrs, i32 5, <2 x i1> zeroinitializer, <2 x double> %passthru)
|
|
ret <2 x double> %res
|
|
|
|
; CHECK-LABEL: @gather_zeromask(
|
|
; CHECK-NEXT: ret <2 x double> %passthru
|
|
}
|
|
|
|
define void @scatter_zeromask(<2 x double*> %ptrs, <2 x double> %val) {
|
|
call void @llvm.masked.scatter.v2f64(<2 x double> %val, <2 x double*> %ptrs, i32 6, <2 x i1> zeroinitializer)
|
|
ret void
|
|
|
|
; CHECK-LABEL: @scatter_zeromask(
|
|
; CHECK-NEXT: ret void
|
|
}
|
|
|