maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/ARM/ldrd.ll

98 lines
3.9 KiB
LLVM
Raw Normal View History

Add extra CHECK prefix to tests with explicit prefix These tests mistakenly assume that CHECK is still available even if an explicit prefix is specified. llvm-svn: 201492
2014-02-16 21:28:15 +08:00
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -regalloc=fast -optimize-regalloc=0 | FileCheck %s -check-prefix=A8 -check-prefix=CHECK
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-m3 -regalloc=fast -optimize-regalloc=0 | FileCheck %s -check-prefix=M3 -check-prefix=CHECK
Add workaround for Cortex-M3 errata 602117 by replacing ldrd x, y, [x] with ldm or ldr pairs. llvm-svn: 144123
2011-11-09 05:21:09 +08:00
; rdar://6949835
Add extra CHECK prefix to tests with explicit prefix These tests mistakenly assume that CHECK is still available even if an explicit prefix is specified. llvm-svn: 201492
2014-02-16 21:28:15 +08:00
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -regalloc=basic | FileCheck %s -check-prefix=BASIC -check-prefix=CHECK
; RUN: llc < %s -mtriple=thumbv7-apple-ios -mcpu=cortex-a8 -regalloc=greedy | FileCheck %s -check-prefix=GREEDY -check-prefix=CHECK
Part 1. - Change register allocation hint to a pair of unsigned integers. The hint type is zero (which means prefer the register specified as second part of the pair) or entirely target dependent. - Allow targets to specify alternative register allocation orders based on allocation hint. Part 2. - Use the register allocation hint system to implement more aggressive load / store multiple formation. - Aggressively form LDRD / STRD. These are formed *before* register allocation. It has to be done this way to shorten live interval of base and offset registers. e.g. v1025 = LDR v1024, 0 v1026 = LDR v1024, 0 => v1025,v1026 = LDRD v1024, 0 If this transformation isn't done before allocation, v1024 will overlap v1025 which means it more difficult to allocate a register pair. - Even with the register allocation hint, it may not be possible to get the desired allocation. In that case, the post-allocation load / store multiple pass must fix the ldrd / strd instructions. They can either become ldm / stm instructions or back to a pair of ldr / str instructions. This is work in progress, not yet enabled. llvm-svn: 73381
2009-06-15 16:28:29 +08:00
Add workaround for Cortex-M3 errata 602117 by replacing ldrd x, y, [x] with ldm or ldr pairs. llvm-svn: 144123
2011-11-09 05:21:09 +08:00
; Magic ARM pair hints works best with linearscan / fast.
; Cortex-M3 errata 602117: LDRD with base in list may result in incorrect base
; register when interrupted or faulted.
Fix ARM tests to be register allocator independent. llvm-svn: 128680
2011-04-01 06:14:03 +08:00
Part 1. - Change register allocation hint to a pair of unsigned integers. The hint type is zero (which means prefer the register specified as second part of the pair) or entirely target dependent. - Allow targets to specify alternative register allocation orders based on allocation hint. Part 2. - Use the register allocation hint system to implement more aggressive load / store multiple formation. - Aggressively form LDRD / STRD. These are formed *before* register allocation. It has to be done this way to shorten live interval of base and offset registers. e.g. v1025 = LDR v1024, 0 v1026 = LDR v1024, 0 => v1025,v1026 = LDRD v1024, 0 If this transformation isn't done before allocation, v1024 will overlap v1025 which means it more difficult to allocate a register pair. - Even with the register allocation hint, it may not be possible to get the desired allocation. In that case, the post-allocation load / store multiple pass must fix the ldrd / strd instructions. They can either become ldm / stm instructions or back to a pair of ldr / str instructions. This is work in progress, not yet enabled. llvm-svn: 73381
2009-06-15 16:28:29 +08:00
@b = external global i64*
define i64 @t(i64 %a) nounwind readonly {
entry:
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; A8-LABEL: t:
Add workaround for Cortex-M3 errata 602117 by replacing ldrd x, y, [x] with ldm or ldr pairs. llvm-svn: 144123
2011-11-09 05:21:09 +08:00
; A8: ldrd r2, r3, [r2]
Convert test to filecheck. llvm-svn: 82835
2009-09-26 10:41:17 +08:00
Mass update to CodeGen tests to use CHECK-LABEL for labels corresponding to function definitions for more informative error messages. No functionality change and all updated tests passed locally. This update was done with the following bash script: find test/CodeGen -name "*.ll" | \ while read NAME; do echo "$NAME" if ! grep -q "^; *RUN: *llc.*debug" $NAME; then TEMP=`mktemp -t temp` cp $NAME $TEMP sed -n "s/^define [^@]*@\([A-Za-z0-9_]*\)(.*$/\1/p" < $NAME | \ while read FUNC; do sed -i '' "s/;\(.*\)\([A-Za-z0-9_-]*\):\( *\)$FUNC: *\$/;\1\2-LABEL:\3$FUNC:/g" $TEMP done sed -i '' "s/;\(.*\)-LABEL-LABEL:/;\1-LABEL:/" $TEMP sed -i '' "s/;\(.*\)-NEXT-LABEL:/;\1-NEXT:/" $TEMP sed -i '' "s/;\(.*\)-NOT-LABEL:/;\1-NOT:/" $TEMP sed -i '' "s/;\(.*\)-DAG-LABEL:/;\1-DAG:/" $TEMP mv $TEMP $NAME fi done llvm-svn: 186280
2013-07-14 14:24:09 +08:00
; M3-LABEL: t:
Add workaround for Cortex-M3 errata 602117 by replacing ldrd x, y, [x] with ldm or ldr pairs. llvm-svn: 144123
2011-11-09 05:21:09 +08:00
; M3-NOT: ldrd
Convert test to filecheck. llvm-svn: 82835
2009-09-26 10:41:17 +08:00
Part 1. - Change register allocation hint to a pair of unsigned integers. The hint type is zero (which means prefer the register specified as second part of the pair) or entirely target dependent. - Allow targets to specify alternative register allocation orders based on allocation hint. Part 2. - Use the register allocation hint system to implement more aggressive load / store multiple formation. - Aggressively form LDRD / STRD. These are formed *before* register allocation. It has to be done this way to shorten live interval of base and offset registers. e.g. v1025 = LDR v1024, 0 v1026 = LDR v1024, 0 => v1025,v1026 = LDRD v1024, 0 If this transformation isn't done before allocation, v1024 will overlap v1025 which means it more difficult to allocate a register pair. - Even with the register allocation hint, it may not be possible to get the desired allocation. In that case, the post-allocation load / store multiple pass must fix the ldrd / strd instructions. They can either become ldm / stm instructions or back to a pair of ldr / str instructions. This is work in progress, not yet enabled. llvm-svn: 73381
2009-06-15 16:28:29 +08:00
%0 = load i64** @b, align 4
%1 = load i64* %0, align 4
%2 = mul i64 %1, %a
ret i64 %2
}
ARM Ld/St Optimizer fix. Allow LDRD to be formed from pairs with different LDR encodings. This was the original intention of the pass. Somewhere along the way, the LDR opcodes were refined which broke the optimization. We really don't care what the original opcodes are as long as they both map to the same LDRD and the immediate still fits. Fixes rdar://10435045 ARMLoadStoreOptimization cannot handle mixed LDRi8/LDRi12 llvm-svn: 147922
2012-01-11 11:56:08 +08:00
; rdar://10435045 mixed LDRi8/LDRi12
;
; In this case, LSR generate a sequence of LDRi8/LDRi12. We should be
; able to generate an LDRD pair here, but this is highly sensitive to
; regalloc hinting. So, this doubles as a register allocation
; test. RABasic currently does a better job within the inner loop
; because of its *lack* of hinting ability. Whereas RAGreedy keeps
; R0/R1/R2 live as the three arguments, forcing the LDRD's odd
; destination into R3. We then sensibly split LDRD again rather then
; evict another live range or use callee saved regs. Sorry if the test
; is sensitive to Regalloc changes, but it is an interesting case.
;
; BASIC: @f
; BASIC: %bb
; BASIC: ldrd
; BASIC: str
; GREEDY: @f
; GREEDY: %bb
Allocate virtual registers in ascending order. This is just the fallback tie-breaker ordering, the main allocation order is still descending size. Patch by Shamil Kurmangaleev! llvm-svn: 153904
2012-04-03 06:30:39 +08:00
; GREEDY: ldrd
ARM Ld/St Optimizer fix. Allow LDRD to be formed from pairs with different LDR encodings. This was the original intention of the pass. Somewhere along the way, the LDR opcodes were refined which broke the optimization. We really don't care what the original opcodes are as long as they both map to the same LDRD and the immediate still fits. Fixes rdar://10435045 ARMLoadStoreOptimization cannot handle mixed LDRi8/LDRi12 llvm-svn: 147922
2012-01-11 11:56:08 +08:00
; GREEDY: str
define void @f(i32* nocapture %a, i32* nocapture %b, i32 %n) nounwind {
entry:
%0 = add nsw i32 %n, -1 ; <i32> [#uses=2]
%1 = icmp sgt i32 %0, 0 ; <i1> [#uses=1]
br i1 %1, label %bb, label %return
bb: ; preds = %bb, %entry
%i.03 = phi i32 [ %tmp, %bb ], [ 0, %entry ] ; <i32> [#uses=3]
%scevgep = getelementptr i32* %a, i32 %i.03 ; <i32*> [#uses=1]
%scevgep4 = getelementptr i32* %b, i32 %i.03 ; <i32*> [#uses=1]
%tmp = add i32 %i.03, 1 ; <i32> [#uses=3]
%scevgep5 = getelementptr i32* %a, i32 %tmp ; <i32*> [#uses=1]
%2 = load i32* %scevgep, align 4 ; <i32> [#uses=1]
%3 = load i32* %scevgep5, align 4 ; <i32> [#uses=1]
%4 = add nsw i32 %3, %2 ; <i32> [#uses=1]
store i32 %4, i32* %scevgep4, align 4
%exitcond = icmp eq i32 %tmp, %0 ; <i1> [#uses=1]
br i1 %exitcond, label %return, label %bb
return: ; preds = %bb, %entry
ret void
}
ARM: Remove a (false) dependency on the memoryoperand's value as we do not use it at the moment. This allows to form more paired loads even when stack coloring pass destroys the memoryoperand's value. <rdar://problem/13978317> llvm-svn: 184492
2013-06-21 06:51:44 +08:00
; rdar://13978317
; Pair of loads not formed when lifetime markers are set.
%struct.Test = type { i32, i32, i32 }
@TestVar = external global %struct.Test
define void @Func1() nounwind ssp {
; CHECK: @Func1
entry:
; A8: movw [[BASE:r[0-9]+]], :lower16:{{.*}}TestVar{{.*}}
; A8: movt [[BASE]], :upper16:{{.*}}TestVar{{.*}}
; A8: ldrd [[FIELD1:r[0-9]+]], [[FIELD2:r[0-9]+]], {{\[}}[[BASE]], #4]
; A8-NEXT: add [[FIELD1]], [[FIELD2]]
; A8-NEXT: str [[FIELD1]], {{\[}}[[BASE]]{{\]}}
%orig_blocks = alloca [256 x i16], align 2
%0 = bitcast [256 x i16]* %orig_blocks to i8*call void @llvm.lifetime.start(i64 512, i8* %0) nounwind
%tmp1 = load i32* getelementptr inbounds (%struct.Test* @TestVar, i32 0, i32 1), align 4
%tmp2 = load i32* getelementptr inbounds (%struct.Test* @TestVar, i32 0, i32 2), align 4
%add = add nsw i32 %tmp2, %tmp1
store i32 %add, i32* getelementptr inbounds (%struct.Test* @TestVar, i32 0, i32 0), align 4
call void @llvm.lifetime.end(i64 512, i8* %0) nounwind
ret void
}
declare void @llvm.lifetime.start(i64, i8* nocapture) nounwind
declare void @llvm.lifetime.end(i64, i8* nocapture) nounwind