[llvm] 7c65d22 - [AArch64] Improve access to fixed-width object when stack has SVE.

[Sander de Smalen via llvm-commits]

Author: Sander de Smalen
Date: 2022-03-04T09:33:59Z
New Revision: 7c65d2288bfd03ca3c3e829c7746b5e4e495357f

URL: https://github.com/llvm/llvm-project/commit/7c65d2288bfd03ca3c3e829c7746b5e4e495357f
DIFF: https://github.com/llvm/llvm-project/commit/7c65d2288bfd03ca3c3e829c7746b5e4e495357f.diff

LOG: [AArch64] Improve access to fixed-width object when stack has SVE.

When the stack has SVE objects, fixed-width objects are often better accessed
from the SP, instead of the FP, because part/all of the fixed-width offset
can be folded into the (non-scalable) addressing mode, where otherwise an
ADDVL would be required.

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D120738

Added: 
    

Modified: 
    llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
    llvm/test/CodeGen/AArch64/framelayout-sve-fixed-width-access.mir
    llvm/test/CodeGen/AArch64/stack-guard-sve.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
index d5c77e3afe74f..0ddfa9715f90a 100644
--- a/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64FrameLowering.cpp
@@ -2012,8 +2012,9 @@ StackOffset AArch64FrameLowering::resolveFrameOffsetReference(
   // right thing for the emergency spill slot.
   bool UseFP = false;
   if (AFI->hasStackFrame() && !isSVE) {
-    // We shouldn't prefer using the FP when there is an SVE area
-    // in between the FP and the non-SVE locals/spills.
+    // We shouldn't prefer using the FP to access fixed-sized stack objects when
+    // there are scalable (SVE) objects in between the FP and the fixed-sized
+    // objects.
     PreferFP &= !SVEStackSize;
 
     // Note: Keeping the following as multiple 'if' statements rather than
@@ -2034,7 +2035,7 @@ StackOffset AArch64FrameLowering::resolveFrameOffsetReference(
       // offsets is smaller than for positive ones. If an offset is available
       // via the FP and the SP, use whichever is closest.
       bool FPOffsetFits = !ForSimm || FPOffset >= -256;
-      PreferFP |= Offset > -FPOffset;
+      PreferFP |= Offset > -FPOffset && !SVEStackSize;
 
       if (MFI.hasVarSizedObjects()) {
         // If we have variable sized objects, we can use either FP or BP, as the

diff  --git a/llvm/test/CodeGen/AArch64/framelayout-sve-fixed-width-access.mir b/llvm/test/CodeGen/AArch64/framelayout-sve-fixed-width-access.mir
index 4de5ceb232d5e..e367a380f8ba9 100644
--- a/llvm/test/CodeGen/AArch64/framelayout-sve-fixed-width-access.mir
+++ b/llvm/test/CodeGen/AArch64/framelayout-sve-fixed-width-access.mir
@@ -10,9 +10,7 @@
   ; CHECK-NEXT:    addvl sp, sp, #-32
   ; CHECK-NEXT:    addvl sp, sp, #-28
   ; CHECK-NEXT:    sub sp, sp, #2064
-  ; CHECK-NEXT:    addvl x8, x29, #-32
-  ; CHECK-NEXT:    addvl x8, x8, #-28
-  ; CHECK-NEXT:    ldur x8, [x8, #-16]
+  ; CHECK-NEXT:    ldr x8, [sp, #2048]
   ; CHECK-NEXT:    addvl sp, sp, #31
   ; CHECK-NEXT:    addvl sp, sp, #29
   ; CHECK-NEXT:    add sp, sp, #2064

diff  --git a/llvm/test/CodeGen/AArch64/stack-guard-sve.ll b/llvm/test/CodeGen/AArch64/stack-guard-sve.ll
index a6696f4c96ccd..d7a6bca2b0cf1 100644
--- a/llvm/test/CodeGen/AArch64/stack-guard-sve.ll
+++ b/llvm/test/CodeGen/AArch64/stack-guard-sve.ll
@@ -152,15 +152,15 @@ entry:
 ; CHECK: sub sp, sp, #16, lsl #12
 ; CHECK: sub sp, sp, #16
 
-; Stack guard is placed below the SVE stack area
+; Stack guard is placed below the SVE stack area (and above all fixed-width objects)
+; CHECK-DAG: add [[STACK_GUARD_SPILL_PART_LOC:x[0-9]+]], sp, #8, lsl #12
+; CHECK-DAG: add [[STACK_GUARD_SPILL_PART_LOC]], [[STACK_GUARD_SPILL_PART_LOC]], #16
 ; CHECK-DAG: ldr [[STACK_GUARD:x[0-9]+]], [{{x[0-9]+}}, :lo12:__stack_chk_guard]
-; CHECK-DAG: addvl [[STACK_GUARD_POS:x[0-9]+]], x29, #-2
-; CHECK-DAG: stur [[STACK_GUARD]], [[[STACK_GUARD_POS]], #-8]
+; CHECK-DAG: str [[STACK_GUARD]], [[[STACK_GUARD_SPILL_PART_LOC]], #32760]
 
 ; char_arr is below the stack guard
-; CHECK-DAG: sub [[CHAR_ARR_1:x[0-9]+]], x29, #16
-; CHECK-DAG: addvl [[CHAR_ARR_2:x[0-9]+]], [[CHAR_ARR_1]], #-2
-; CHECK-DAG: strb wzr, [[[CHAR_ARR_2]]]
+; CHECK-DAG: add [[CHAR_ARR_LOC:x[0-9]+]], sp, #16, lsl #12
+; CHECK-DAG: strb wzr, [[[CHAR_ARR_LOC]]]
 
 ; large1 is accessed via a virtual base register
 ; CHECK-DAG: add [[LARGE1:x[0-9]+]], sp, #8, lsl #12
@@ -208,8 +208,9 @@ entry:
 ; CHECK-DAG: str [[STACK_GUARD]], [[[STACK_GUARD_POS]]]
 
 ; char_arr is below the SVE stack area
-; CHECK-DAG: addvl [[CHAR_ARR:x[0-9]+]], x29, #-3
-; CHECK-DAG: sturb wzr, [[[CHAR_ARR]], #-8]
+; CHECK-DAG: add [[CHAR_ARR:x[0-9]+]], sp, #15, lsl #12            // =61440
+; CHECK-DAG: add [[CHAR_ARR]], [[CHAR_ARR]], #9
+; CHECK-DAG: strb wzr, [[[CHAR_ARR]], #4095]
 
 ; large1 is accessed via a virtual base register
 ; CHECK-DAG: add [[LARGE1:x[0-9]+]], sp, #8, lsl #12