[ARM][LowOverheadLoops] Allow tail predication on predicated instructions with unknow...

values

The effects of unpredicated vector instruction with unknown
lanes cannot be predicted and therefore cannot be tail predicated. This
does not apply to predicated vector instructions and so this patch
allows tail predication on them.

Differential Revision: https://reviews.llvm.org/D87376

diff --git a/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp b/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
index 69e188f..755c2e5 100644 (file)
--- a/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
+++ b/llvm/lib/Target/ARM/ARMLowOverheadLoops.cpp
@@ -723,7 +723,7 @@ bool LowOverheadLoop::ValidateLiveOuts() {
       continue;
     else if (!isPredicated && retainsOrReduces)
       return false;
-    else
+    else if (!isPredicated)
       FalseLanesUnknown.insert(&MI);
   }
 

diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/predicated-liveout-unknown-lanes.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/predicated-liveout-unknown-lanes.ll
new file mode 100644 (file)
index 0000000..f6e175d
--- /dev/null
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/predicated-liveout-unknown-lanes.ll
@@ -0,0 +1,44 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=thumbv8.1m.main-none-none-eabi -mattr=+mve.fp -O3 -tail-predication=force-enabled-no-reductions %s -o - | FileCheck %s
+
+define arm_aapcs_vfpcc <4 x float> @arm_max_no_idx_f32_mve(float* %pSrc, i32 %blockSize, float* nocapture %pResult) {
+; CHECK-LABEL: arm_max_no_idx_f32_mve:
+; CHECK:       @ %bb.0: @ %entry
+; CHECK-NEXT:    .save {r7, lr}
+; CHECK-NEXT:    push {r7, lr}
+; CHECK-NEXT:    subs r2, r1, #4
+; CHECK-NEXT:    adr r3, .LCPI0_0
+; CHECK-NEXT:    vldrw.u32 q0, [r3]
+; CHECK-NEXT:    dlstp.32 lr, r1
+; CHECK-NEXT:  .LBB0_1: @ %do.body
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    vldrw.u32 q1, [r0], #16
+; CHECK-NEXT:    vmaxnm.f32 q0, q1, q0
+; CHECK-NEXT:    letp lr, .LBB0_1
+; CHECK-NEXT:  @ %bb.2: @ %do.end
+; CHECK-NEXT:    pop {r7, pc}
+entry:
+  br label %do.body
+
+do.body:                                          ; preds = %do.body, %entry
+  %blockSize.addr.0 = phi i32 [ %blockSize, %entry ], [ %sub, %do.body ]
+  %curExtremValVec.0 = phi <4 x float> [ <float 0xFFF0000000000000, float 0xFFF0000000000000, float 0xFFF0000000000000, float 0xFFF0000000000000>, %entry ], [ %3, %do.body ]
+  %pSrc.addr.0 = phi float* [ %pSrc, %entry ], [ %add.ptr, %do.body ]
+  %0 = tail call <4 x i1> @llvm.arm.mve.vctp32(i32 %blockSize.addr.0)
+  %1 = bitcast float* %pSrc.addr.0 to <4 x float>*
+  %2 = tail call fast <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>* %1, i32 4, <4 x i1> %0, <4 x float> zeroinitializer)
+  %3 = tail call fast <4 x float> @llvm.arm.mve.max.predicated.v4f32.v4i1(<4 x float> %2, <4 x float> %curExtremValVec.0, i32 0, <4 x i1> %0, <4 x float> %curExtremValVec.0)
+  %add.ptr = getelementptr inbounds float, float* %pSrc.addr.0, i32 4
+  %sub = add i32 %blockSize.addr.0, -4
+  %cmp = icmp sgt i32 %sub, 0
+  br i1 %cmp, label %do.body, label %do.end
+
+do.end:                                           ; preds = %do.body
+  ret <4 x float> %3
+}
+
+declare <4 x i1> @llvm.arm.mve.vctp32(i32)
+
+declare <4 x float> @llvm.masked.load.v4f32.p0v4f32(<4 x float>*, i32 immarg, <4 x i1>, <4 x float>)
+
+declare <4 x float> @llvm.arm.mve.max.predicated.v4f32.v4i1(<4 x float>, <4 x float>, i32, <4 x i1>, <4 x float>)

diff --git a/llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll b/llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
index ed7e84a..311a06a 100644 (file)
--- a/llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-pred-vctpvpsel.ll
@@ -9,32 +9,22 @@ define void @arm_min_helium_f32(float* %pSrc, i32 %blockSize, float* nocapture %
 ; CHECK-NEXT:    .vsave {d8, d9}
 ; CHECK-NEXT:    vpush {d8, d9}
 ; CHECK-NEXT:    movs r6, #0
-; CHECK-NEXT:    mov r12, r1
 ; CHECK-NEXT:    vidup.u32 q2, r6, #1
-; CHECK-NEXT:    cmp r1, #4
-; CHECK-NEXT:    it ge
-; CHECK-NEXT:    movge.w r12, #4
-; CHECK-NEXT:    sub.w r6, r1, r12
-; CHECK-NEXT:    adds r6, #3
-; CHECK-NEXT:    mov.w lr, #1
 ; CHECK-NEXT:    adr r4, .LCPI0_0
 ; CHECK-NEXT:    vmov.i32 q0, #0x0
-; CHECK-NEXT:    add.w lr, lr, r6, lsr #2
 ; CHECK-NEXT:    vldrw.u32 q1, [r4]
 ; CHECK-NEXT:    vmov.i32 q3, #0x4
 ; CHECK-NEXT:    mov r12, r1
-; CHECK-NEXT:    dls lr, lr
+; CHECK-NEXT:    dlstp.32 lr, r12
 ; CHECK-NEXT:  .LBB0_1: @ %do.body
 ; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT:    vctp.32 r12
-; CHECK-NEXT:    sub.w r12, r12, #4
-; CHECK-NEXT:    vpstttt
-; CHECK-NEXT:    vldrwt.u32 q4, [r0], #16
-; CHECK-NEXT:    vcmpt.f32 ge, q1, q4
+; CHECK-NEXT:    vldrw.u32 q4, [r0], #16
+; CHECK-NEXT:    vcmp.f32 ge, q1, q4
+; CHECK-NEXT:    vpstt
 ; CHECK-NEXT:    vmovt q1, q4
 ; CHECK-NEXT:    vmovt q0, q2
 ; CHECK-NEXT:    vadd.i32 q2, q2, q3
-; CHECK-NEXT:    le lr, .LBB0_1
+; CHECK-NEXT:    letp lr, .LBB0_1
 ; CHECK-NEXT:  @ %bb.2: @ %do.end
 ; CHECK-NEXT:    vldr s8, .LCPI0_1
 ; CHECK-NEXT:    vdup.32 q3, r1