[ARM] Rearrange SizeReduction when using -Oz

Move the Thumb2SizeReduce pass to before IfConversion when optimising
for minimal code size.

Running the Thumb2SizeReduction pass before IfConversionallows T1
instructions to propagate to the final output, rather than the
ifConverter modifying T2 instructions and preventing them from being
reduced later.

This change does introduce a regression regarding execution time, so
it's only applied when optimising for size.

Running the LLVM Test Suite with this change produces a geomean
difference of -0.1% for the size..text metric.

Differential Revision: https://reviews.llvm.org/D82439

diff --git a/llvm/lib/Target/ARM/ARMTargetMachine.cpp b/llvm/lib/Target/ARM/ARMTargetMachine.cpp
index 538ec44..9ead5fa 100644 (file)
--- a/llvm/lib/Target/ARM/ARMTargetMachine.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetMachine.cpp
@@ -518,9 +518,12 @@ void ARMPassConfig::addPreSched2() {
   addPass(createARMExpandPseudoPass());
 
   if (getOptLevel() != CodeGenOpt::None) {
-    // in v8, IfConversion depends on Thumb instruction widths
+    // When optimising for size, always run the Thumb2SizeReduction pass before
+    // IfConversion. Otherwise, check whether IT blocks are restricted
+    // (e.g. in v8, IfConversion depends on Thumb instruction widths)
     addPass(createThumb2SizeReductionPass([this](const Function &F) {
-      return this->TM->getSubtarget<ARMSubtarget>(F).restrictIT();
+      return this->TM->getSubtarget<ARMSubtarget>(F).hasMinSize() ||
+             this->TM->getSubtarget<ARMSubtarget>(F).restrictIT();
     }));
 
     addPass(createIfConverter([](const MachineFunction &MF) {

diff --git a/llvm/test/CodeGen/ARM/t2-shrink-ldrpost.ll b/llvm/test/CodeGen/ARM/t2-shrink-ldrpost.ll
index e26f384..e7b1780 100644 (file)
--- a/llvm/test/CodeGen/ARM/t2-shrink-ldrpost.ll
+++ b/llvm/test/CodeGen/ARM/t2-shrink-ldrpost.ll
@@ -1,13 +1,24 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s | FileCheck %s
 
 target datalayout = "e-m:e-p:32:32-i1:8:32-i8:8:32-i16:16:32-f64:32:64-v64:32:64-v128:32:128-a:0:32-n32-S32"
 target triple = "thumbv7m--linux-gnu"
 
-; CHECK-LABEL: f:
-; CHECK: ldm   r{{[0-9]}}!, {r[[x:[0-9]]]}
-; CHECK: add.w r[[x]], r[[x]], #3
-; CHECK: stm   r{{[0-9]}}!, {r[[x]]}
+; NOTE: When optimising for minimum size, an LDM is expected to be generated
 define void @f(i32 %n, i32* nocapture %a, i32* nocapture readonly %b) optsize minsize {
+; CHECK-LABEL: f:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    cmp r0, #1
+; CHECK-NEXT:    blt .LBB0_2
+; CHECK-NEXT:  .LBB0_1: @ %.lr.ph
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    ldm r2!, {r3}
+; CHECK-NEXT:    adds r3, #3
+; CHECK-NEXT:    stm r1!, {r3}
+; CHECK-NEXT:    subs r0, #1
+; CHECK-NEXT:    bne .LBB0_1
+; CHECK-NEXT:  .LBB0_2: @ %._crit_edge
+; CHECK-NEXT:    bx lr
   %1 = icmp sgt i32 %n, 0
   br i1 %1, label %.lr.ph, label %._crit_edge
 
@@ -28,9 +39,22 @@ define void @f(i32 %n, i32* nocapture %a, i32* nocapture readonly %b) optsize mi
   ret void
 }
 
-; CHECK-LABEL: f_nominsize:
-; CHECK-NOT: ldm
+; NOTE: When not optimising for minimum size, an LDM is expected not to be generated
 define void @f_nominsize(i32 %n, i32* nocapture %a, i32* nocapture readonly %b) optsize {
+; CHECK-LABEL: f_nominsize:
+; CHECK:       @ %bb.0:
+; CHECK-NEXT:    cmp r0, #1
+; CHECK-NEXT:    it lt
+; CHECK-NEXT:    bxlt lr
+; CHECK-NEXT:  .LBB1_1: @ %.lr.ph
+; CHECK-NEXT:    @ =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    ldr r3, [r2], #4
+; CHECK-NEXT:    subs r0, #1
+; CHECK-NEXT:    add.w r3, r3, #3
+; CHECK-NEXT:    str r3, [r1], #4
+; CHECK-NEXT:    bne .LBB1_1
+; CHECK-NEXT:  @ %bb.2: @ %._crit_edge
+; CHECK-NEXT:    bx lr
   %1 = icmp sgt i32 %n, 0
   br i1 %1, label %.lr.ph, label %._crit_edge
 

diff --git a/llvm/test/CodeGen/Thumb2/constant-hoisting.ll b/llvm/test/CodeGen/Thumb2/constant-hoisting.ll
index a106900..5c8f934 100644 (file)
--- a/llvm/test/CodeGen/Thumb2/constant-hoisting.ll
+++ b/llvm/test/CodeGen/Thumb2/constant-hoisting.ll
@@ -37,25 +37,26 @@ define i32 @test_values(i32 %a, i32 %b) minsize optsize {
 ; CHECK-V7M:         mov r2, r0
 ; CHECK-V7M-NEXT:    ldr r0, .LCPI0_0
 ; CHECK-V7M-NEXT:    cmp r2, #50
-; CHECK-V7M-NEXT:    beq .LBB0_3
+; CHECK-V7M-NEXT:    beq .LBB0_5
 ; CHECK-V7M-NEXT:    cmp r2, #1
-; CHECK-V7M-NEXT:    ittt eq
-; CHECK-V7M-NEXT:    addeq r0, r1
-; CHECK-V7M-NEXT:    addeq r0, #1
-; CHECK-V7M-NEXT:    bxeq lr
+; CHECK-V7M-NEXT:    beq .LBB0_7
 ; CHECK-V7M-NEXT:    cmp r2, #30
-; CHECK-V7M-NEXT:    ittt eq
-; CHECK-V7M-NEXT:    addeq r0, r1
-; CHECK-V7M-NEXT:    addeq r0, #2
-; CHECK-V7M-NEXT:    bxeq lr
-; CHECK-V7M-NEXT:    cbnz r2, .LBB0_4
-; CHECK-V7M-NEXT:  .LBB0_2:
+; CHECK-V7M-NEXT:    beq .LBB0_8
+; CHECK-V7M-NEXT:    cbnz r2, .LBB0_6
 ; CHECK-V7M-NEXT:    add r0, r1
 ; CHECK-V7M-NEXT:    bx lr
-; CHECK-V7M-NEXT:  .LBB0_3:
+; CHECK-V7M-NEXT:  .LBB0_5:
 ; CHECK-V7M-NEXT:    add r0, r1
 ; CHECK-V7M-NEXT:    adds r0, #4
-; CHECK-V7M-NEXT:  .LBB0_4:
+; CHECK-V7M-NEXT:  .LBB0_6:
+; CHECK-V7M-NEXT:    bx lr
+; CHECK-V7M-NEXT:  .LBB0_7:
+; CHECK-V7M-NEXT:    add r0, r1
+; CHECK-V7M-NEXT:    adds r0, #1
+; CHECK-V7M-NEXT:    bx lr
+; CHECK-V7M-NEXT:  .LBB0_8:
+; CHECK-V7M-NEXT:    add r0, r1
+; CHECK-V7M-NEXT:    adds r0, #2
 ; CHECK-V7M-NEXT:    bx lr
 ; CHECK-V7M-NEXT:    .p2align 2
 ; CHECK-V7M-NEXT:  .LCPI0_0: