forked from OSchip/llvm-project
213 lines
10 KiB
LLVM
213 lines
10 KiB
LLVM
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||
|
|
; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -enable-arm-maskedldst -enable-mem-access-versioning=false -enable-arm-maskedgatscat -tail-predication=force-enabled %s -o - | FileCheck %s
|
||
|
|
|
||
|
|
define dso_local void @mve_gather_qi_wb(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %n, i32 %m, i32 %l) {
|
||
|
|
; CHECK-LABEL: mve_gather_qi_wb:
|
||
|
|
; CHECK: @ %bb.0: @ %entry
|
||
|
|
; CHECK-NEXT: .save {r4, lr}
|
||
|
|
; CHECK-NEXT: push {r4, lr}
|
||
|
|
; CHECK-NEXT: adr r4, .LCPI0_0
|
||
|
|
; CHECK-NEXT: add.w r12, r0, r3, lsl #2
|
||
|
|
; CHECK-NEXT: vldrw.u32 q0, [r4]
|
||
|
|
; CHECK-NEXT: adds r0, r3, #1
|
||
|
|
; CHECK-NEXT: vmov.i32 q2, #0x0
|
||
|
|
; CHECK-NEXT: vadd.i32 q0, q0, r1
|
||
|
|
; CHECK-NEXT: adds r1, r3, #4
|
||
|
|
; CHECK-NEXT: dlstp.32 lr, r0
|
||
|
|
; CHECK-NEXT: .LBB0_1: @ %vector.body
|
||
|
|
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
|
||
|
|
; CHECK-NEXT: vldrw.u32 q1, [r12], #16
|
||
|
|
; CHECK-NEXT: vldrw.u32 q3, [q0, #80]!
|
||
|
|
; CHECK-NEXT: vmul.i32 q1, q3, q1
|
||
|
|
; CHECK-NEXT: vadd.i32 q2, q2, q1
|
||
|
|
; CHECK-NEXT: letp lr, .LBB0_1
|
||
|
|
; CHECK-NEXT: @ %bb.2: @ %middle.block
|
||
|
|
; CHECK-NEXT: vmov q0, q2
|
||
|
|
; CHECK-NEXT: vaddv.u32 r0, q0
|
||
|
|
; CHECK-NEXT: str.w r0, [r2, r1, lsl #2]
|
||
|
|
; CHECK-NEXT: pop {r4, pc}
|
||
|
|
; CHECK-NEXT: .p2align 4
|
||
|
|
; CHECK-NEXT: @ %bb.3:
|
||
|
|
; CHECK-NEXT: .LCPI0_0:
|
||
|
|
; CHECK-NEXT: .long 4294967228 @ 0xffffffbc
|
||
|
|
; CHECK-NEXT: .long 4294967248 @ 0xffffffd0
|
||
|
|
; CHECK-NEXT: .long 4294967268 @ 0xffffffe4
|
||
|
|
; CHECK-NEXT: .long 4294967288 @ 0xfffffff8
|
||
|
|
entry: ; preds = %middle.
|
||
|
|
%add.us.us = add i32 4, %n
|
||
|
|
%arrayidx.us.us = getelementptr inbounds i32, i32* %C, i32 %add.us.us
|
||
|
|
br label %vector.body
|
||
|
|
vector.body: ; preds = %vector.body, %entry
|
||
|
|
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
|
||
|
|
%vec.phi = phi <4 x i32> [ zeroinitializer, %entry ], [ %7, %vector.body ]
|
||
|
|
%vec.ind = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %entry ], [ %vec.ind.next, %vector.body ]
|
||
|
|
%0 = add i32 %index, %n
|
||
|
|
%1 = getelementptr inbounds i32, i32* %A, i32 %0
|
||
|
|
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
|
||
|
|
%2 = bitcast i32* %1 to <4 x i32>*
|
||
|
|
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
|
||
|
|
%3 = mul <4 x i32> %vec.ind, <i32 5, i32 5, i32 5, i32 5>
|
||
|
|
%4 = add <4 x i32> %3, <i32 3, i32 3, i32 3, i32 3>
|
||
|
|
%5 = getelementptr inbounds i32, i32* %B, <4 x i32> %4
|
||
|
|
%wide.masked.gather = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %5, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
|
||
|
|
%6 = mul nsw <4 x i32> %wide.masked.gather, %wide.masked.load
|
||
|
|
%7 = add <4 x i32> %vec.phi, %6
|
||
|
|
%index.next = add i32 %index, 4
|
||
|
|
%vec.ind.next = add <4 x i32> %vec.ind, <i32 4, i32 4, i32 4, i32 4>
|
||
|
|
%8 = icmp eq i32 %index.next, 5000
|
||
|
|
br i1 %8, label %middle.block, label %vector.body
|
||
|
|
middle.block: ; preds = %vector.body
|
||
|
|
%9 = select <4 x i1> %active.lane.mask, <4 x i32> %7, <4 x i32> %vec.phi
|
||
|
|
%10 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %9)
|
||
|
|
store i32 %10, i32* %arrayidx.us.us, align 4
|
||
|
|
%inc21.us.us = add nuw i32 4, 1
|
||
|
|
%exitcond81.not = icmp eq i32 %inc21.us.us, %n
|
||
|
|
br label %end
|
||
|
|
end: ; preds = %middle.block
|
||
|
|
ret void
|
||
|
|
}
|
||
|
|
|
||
|
|
define dso_local void @mve_gatherscatter_offset(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %n, i32 %m, i32 %l) {
|
||
|
|
; CHECK-LABEL: mve_gatherscatter_offset:
|
||
|
|
; CHECK: @ %bb.0: @ %entry
|
||
|
|
; CHECK-NEXT: .save {r4, lr}
|
||
|
|
; CHECK-NEXT: push {r4, lr}
|
||
|
|
; CHECK-NEXT: .vsave {d8, d9}
|
||
|
|
; CHECK-NEXT: vpush {d8, d9}
|
||
|
|
; CHECK-NEXT: adr r4, .LCPI1_0
|
||
|
|
; CHECK-NEXT: add.w r12, r0, r3, lsl #2
|
||
|
|
; CHECK-NEXT: adds r0, r3, #1
|
||
|
|
; CHECK-NEXT: vldrw.u32 q1, [r4]
|
||
|
|
; CHECK-NEXT: adds r3, #4
|
||
|
|
; CHECK-NEXT: vmov.i32 q3, #0x0
|
||
|
|
; CHECK-NEXT: vmov.i32 q0, #0x14
|
||
|
|
; CHECK-NEXT: dlstp.32 lr, r0
|
||
|
|
; CHECK-NEXT: .LBB1_1: @ %vector.body
|
||
|
|
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
|
||
|
|
; CHECK-NEXT: vldrw.u32 q2, [r1, q1, uxtw #2]
|
||
|
|
; CHECK-NEXT: vldrw.u32 q4, [r12], #16
|
||
|
|
; CHECK-NEXT: vmul.i32 q2, q2, q4
|
||
|
|
; CHECK-NEXT: vstrw.32 q2, [r1, q1, uxtw #2]
|
||
|
|
; CHECK-NEXT: vadd.i32 q1, q1, q0
|
||
|
|
; CHECK-NEXT: vadd.i32 q3, q3, q2
|
||
|
|
; CHECK-NEXT: letp lr, .LBB1_1
|
||
|
|
; CHECK-NEXT: @ %bb.2: @ %middle.block
|
||
|
|
; CHECK-NEXT: vmov q0, q3
|
||
|
|
; CHECK-NEXT: vaddv.u32 r0, q0
|
||
|
|
; CHECK-NEXT: str.w r0, [r2, r3, lsl #2]
|
||
|
|
; CHECK-NEXT: vpop {d8, d9}
|
||
|
|
; CHECK-NEXT: pop {r4, pc}
|
||
|
|
; CHECK-NEXT: .p2align 4
|
||
|
|
; CHECK-NEXT: @ %bb.3:
|
||
|
|
; CHECK-NEXT: .LCPI1_0:
|
||
|
|
; CHECK-NEXT: .long 3 @ 0x3
|
||
|
|
; CHECK-NEXT: .long 8 @ 0x8
|
||
|
|
; CHECK-NEXT: .long 13 @ 0xd
|
||
|
|
; CHECK-NEXT: .long 18 @ 0x12
|
||
|
|
entry: ; preds = %middle.
|
||
|
|
%add.us.us = add i32 4, %n
|
||
|
|
%arrayidx.us.us = getelementptr inbounds i32, i32* %C, i32 %add.us.us
|
||
|
|
br label %vector.body
|
||
|
|
vector.body: ; preds = %vector.body, %entry
|
||
|
|
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
|
||
|
|
%vec.phi = phi <4 x i32> [ zeroinitializer, %entry ], [ %7, %vector.body ]
|
||
|
|
%vec.ind = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %entry ], [ %vec.ind.next, %vector.body ]
|
||
|
|
%0 = add i32 %index, %n
|
||
|
|
%1 = getelementptr inbounds i32, i32* %A, i32 %0
|
||
|
|
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
|
||
|
|
%2 = bitcast i32* %1 to <4 x i32>*
|
||
|
|
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
|
||
|
|
%3 = mul <4 x i32> %vec.ind, <i32 5, i32 5, i32 5, i32 5>
|
||
|
|
%4 = add <4 x i32> %3, <i32 3, i32 3, i32 3, i32 3>
|
||
|
|
%5 = getelementptr inbounds i32, i32* %B, <4 x i32> %4
|
||
|
|
%wide.masked.gather = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> %5, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
|
||
|
|
%6 = mul nsw <4 x i32> %wide.masked.gather, %wide.masked.load
|
||
|
|
call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %6, <4 x i32*> %5, i32 4, <4 x i1> %active.lane.mask)
|
||
|
|
%7 = add <4 x i32> %vec.phi, %6
|
||
|
|
%index.next = add i32 %index, 4
|
||
|
|
%vec.ind.next = add <4 x i32> %vec.ind, <i32 4, i32 4, i32 4, i32 4>
|
||
|
|
%8 = icmp eq i32 %index.next, 5000
|
||
|
|
br i1 %8, label %middle.block, label %vector.body
|
||
|
|
middle.block: ; preds = %vector.body
|
||
|
|
%9 = select <4 x i1> %active.lane.mask, <4 x i32> %7, <4 x i32> %vec.phi
|
||
|
|
%10 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %9)
|
||
|
|
store i32 %10, i32* %arrayidx.us.us, align 4
|
||
|
|
%inc21.us.us = add nuw i32 4, 1
|
||
|
|
%exitcond81.not = icmp eq i32 %inc21.us.us, %n
|
||
|
|
br label %end
|
||
|
|
end: ; preds = %middle.block
|
||
|
|
ret void
|
||
|
|
}
|
||
|
|
define dso_local void @mve_scatter_qi(i32* noalias nocapture readonly %A, i32* noalias nocapture readonly %B, i32* noalias nocapture %C, i32 %n, i32 %m, i32 %l) {
|
||
|
|
; CHECK-LABEL: mve_scatter_qi:
|
||
|
|
; CHECK: @ %bb.0: @ %entry
|
||
|
|
; CHECK-NEXT: .save {r4, lr}
|
||
|
|
; CHECK-NEXT: push {r4, lr}
|
||
|
|
; CHECK-NEXT: adr r4, .LCPI2_0
|
||
|
|
; CHECK-NEXT: add.w r12, r0, r3, lsl #2
|
||
|
|
; CHECK-NEXT: vldrw.u32 q0, [r4]
|
||
|
|
; CHECK-NEXT: adds r0, r3, #1
|
||
|
|
; CHECK-NEXT: vmov.i32 q3, #0x0
|
||
|
|
; CHECK-NEXT: vadd.i32 q0, q0, r1
|
||
|
|
; CHECK-NEXT: adds r1, r3, #4
|
||
|
|
; CHECK-NEXT: vmov.i32 q2, #0x3
|
||
|
|
; CHECK-NEXT: dlstp.32 lr, r0
|
||
|
|
; CHECK-NEXT: .LBB2_1: @ %vector.body
|
||
|
|
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
|
||
|
|
; CHECK-NEXT: vldrw.u32 q1, [r12], #16
|
||
|
|
; CHECK-NEXT: vmul.i32 q1, q1, q2
|
||
|
|
; CHECK-NEXT: vstrw.32 q1, [q0, #80]!
|
||
|
|
; CHECK-NEXT: vadd.i32 q3, q3, q1
|
||
|
|
; CHECK-NEXT: letp lr, .LBB2_1
|
||
|
|
; CHECK-NEXT: @ %bb.2: @ %middle.block
|
||
|
|
; CHECK-NEXT: vmov q0, q3
|
||
|
|
; CHECK-NEXT: vaddv.u32 r0, q0
|
||
|
|
; CHECK-NEXT: str.w r0, [r2, r1, lsl #2]
|
||
|
|
; CHECK-NEXT: pop {r4, pc}
|
||
|
|
; CHECK-NEXT: .p2align 4
|
||
|
|
; CHECK-NEXT: @ %bb.3:
|
||
|
|
; CHECK-NEXT: .LCPI2_0:
|
||
|
|
; CHECK-NEXT: .long 4294967228 @ 0xffffffbc
|
||
|
|
; CHECK-NEXT: .long 4294967248 @ 0xffffffd0
|
||
|
|
; CHECK-NEXT: .long 4294967268 @ 0xffffffe4
|
||
|
|
; CHECK-NEXT: .long 4294967288 @ 0xfffffff8
|
||
|
|
entry: ; preds = %middle.
|
||
|
|
%add.us.us = add i32 4, %n
|
||
|
|
%arrayidx.us.us = getelementptr inbounds i32, i32* %C, i32 %add.us.us
|
||
|
|
br label %vector.body
|
||
|
|
vector.body: ; preds = %vector.body, %entry
|
||
|
|
%index = phi i32 [ 0, %entry ], [ %index.next, %vector.body ]
|
||
|
|
%vec.phi = phi <4 x i32> [ zeroinitializer, %entry ], [ %7, %vector.body ]
|
||
|
|
%vec.ind = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %entry ], [ %vec.ind.next, %vector.body ]
|
||
|
|
%0 = add i32 %index, %n
|
||
|
|
%1 = getelementptr inbounds i32, i32* %A, i32 %0
|
||
|
|
%active.lane.mask = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %n)
|
||
|
|
%2 = bitcast i32* %1 to <4 x i32>*
|
||
|
|
%wide.masked.load = call <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>* %2, i32 4, <4 x i1> %active.lane.mask, <4 x i32> undef)
|
||
|
|
%3 = mul <4 x i32> %vec.ind, <i32 5, i32 5, i32 5, i32 5>
|
||
|
|
%4 = add <4 x i32> %3, <i32 3, i32 3, i32 3, i32 3>
|
||
|
|
%5 = getelementptr inbounds i32, i32* %B, <4 x i32> %4
|
||
|
|
%6 = mul nsw <4 x i32> <i32 3, i32 3, i32 3, i32 3>, %wide.masked.load
|
||
|
|
call void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32> %6, <4 x i32*> %5, i32 4, <4 x i1> %active.lane.mask)
|
||
|
|
%7 = add <4 x i32> %vec.phi, %6
|
||
|
|
%index.next = add i32 %index, 4
|
||
|
|
%vec.ind.next = add <4 x i32> %vec.ind, <i32 4, i32 4, i32 4, i32 4>
|
||
|
|
%8 = icmp eq i32 %index.next, 5000
|
||
|
|
br i1 %8, label %middle.block, label %vector.body
|
||
|
|
middle.block: ; preds = %vector.body
|
||
|
|
%9 = select <4 x i1> %active.lane.mask, <4 x i32> %7, <4 x i32> %vec.phi
|
||
|
|
%10 = call i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32> %9)
|
||
|
|
store i32 %10, i32* %arrayidx.us.us, align 4
|
||
|
|
%inc21.us.us = add nuw i32 4, 1
|
||
|
|
%exitcond81.not = icmp eq i32 %inc21.us.us, %n
|
||
|
|
br label %end
|
||
|
|
end: ; preds = %middle.block
|
||
|
|
ret void
|
||
|
|
}
|
||
|
|
|
||
|
|
declare i32 @llvm.experimental.vector.reduce.add.v4i32(<4 x i32>)
|
||
|
|
declare <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*>, i32, <4 x i1>, <4 x i32>)
|
||
|
|
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
|
||
|
|
declare <4 x i32> @llvm.masked.load.v4i32.p0v4i32(<4 x i32>*, i32, <4 x i1>, <4 x i32>)
|
||
|
|
declare void @llvm.masked.scatter.v4i32.v4p0i32(<4 x i32>, <4 x i32*>, i32, <4 x i1>)
|