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/spill-q.ll

92 lines
5.2 KiB
LLVM
Raw Normal View History

ARM & AArch64: make use of common cmpxchg idioms after expansion The C and C++ semantics for compare_exchange require it to return a bool indicating success. This gets mapped to LLVM IR which follows each cmpxchg with an icmp of the value loaded against the desired value. When lowered to ldxr/stxr loops, this extra comparison is redundant: its results are implicit in the control-flow of the function. This commit makes two changes: it replaces that icmp with appropriate PHI nodes, and then makes sure earlyCSE is called after expansion to actually make use of the opportunities revealed. I've also added -{arm,aarch64}-enable-atomic-tidy options, so that existing fragile tests aren't perturbed too much by the change. Many of them either rely on undef/unreachable too pervasively to be restored to something well-defined (particularly while making sure they test the same obscure assert from many years ago), or depend on a particular CFG shape, which is disrupted by SimplifyCFG. rdar://problem/16227836 llvm-svn: 209883
2014-05-30 18:09:59 +08:00
; RUN: llc < %s -mtriple=armv7-elf -mattr=+neon -arm-atomic-cfg-tidy=0 | FileCheck %s
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
; PR4789
%bar = type { float, float, float }
%baz = type { i32, [16 x %bar], [16 x float], [16 x i32], i8 }
%foo = type { <4 x float> }
%quux = type { i32 (...)**, %baz*, i32 }
%quuz = type { %quux, i32, %bar, [128 x i8], [16 x %foo], %foo, %foo, %foo }
Add alignment arguments to all the NEON load/store intrinsics. Update all the tests using those intrinsics and add support for auto-upgrading bitcode files with the old versions of the intrinsics. llvm-svn: 112271
2010-08-28 01:13:24 +08:00
declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*, i32) nounwind readonly
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
Remove arm_apcscc from the test files. It is the default and doing this matches what llvm-gcc and clang now produce. llvm-svn: 106221
2010-06-17 23:18:27 +08:00
define void @aaa(%quuz* %this, i8* %block) {
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
; CHECK-LABEL: aaa:
Fix large stack alignment codegen for ARM and Thumb2 targets This partially fixes PR13007 (ARM CodeGen fails with large stack alignment): for ARM and Thumb2 targets, but not for Thumb1, as it seems stack alignment for Thumb1 targets hasn't been supported at all. Producing an aligned stack pointer is done by zero-ing out the lower bits of the stack pointer. The BIC instruction was used for this. However, the immediate field of the BIC instruction only allows to encode an immediate that can zero out up to a maximum of the 8 lower bits. When a larger alignment is requested, a BIC instruction cannot be used; llvm was silently producing incorrect code in this case. This commit fixes code generation for large stack aligments by using the BFC instruction instead, when the BFC instruction is available. When not, it uses 2 instructions: a right shift, followed by a left shift to zero out the lower bits. The lowering of ARM::Int_eh_sjlj_dispatchsetup still has code that unconditionally uses BIC to realign the stack pointer, so it very likely has the same problem. However, I wasn't able to produce a test case for that. This commit adds an assert so that the compiler will fail the assert instead of silently generating wrong code if this is ever reached. llvm-svn: 225446
2015-01-08 23:09:14 +08:00
; CHECK: bfc {{.*}}, #0, #4
Make ARMAsmPrinter generate the correct alignment specifier syntax in instructions. The Printer will now print instructions with the correct alignment specifier syntax, like vld1.8 {d16}, [r0:64] llvm-svn: 175884
2013-02-22 18:01:33 +08:00
; CHECK: vst1.64 {{.*}}sp:128
; CHECK: vld1.64 {{.*}}sp:128
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
entry:
Add ARM patterns to match EXTRACT_SUBVECTOR nodes. Also fix an off-by-one in SelectionDAGBuilder that was preventing shuffle vectors from being translated to EXTRACT_SUBVECTOR. Patch by Tim Northover. The test changes are needed to keep those spill-q tests from testing aligned spills and restores. If the only aligned stack objects are spill slots, we no longer realign the stack frame. Prior to this patch, an EXTRACT_SUBVECTOR was legalized by loading from the stack, which created an aligned frame index. Now, however, there is nothing except the spill slot in the stack frame, so I added an aligned alloca. llvm-svn: 122995
2011-01-07 12:59:04 +08:00
%aligned_vec = alloca <4 x float>, align 16
%"alloca point" = bitcast i32 0 to i32
%vecptr = bitcast <4 x float>* %aligned_vec to i8*
%0 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* %vecptr, i32 1) nounwind ; <<4 x float>> [#uses=1]
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
store float 6.300000e+01, float* undef, align 4
Add alignment arguments to all the NEON load/store intrinsics. Update all the tests using those intrinsics and add support for auto-upgrading bitcode files with the old versions of the intrinsics. llvm-svn: 112271
2010-08-28 01:13:24 +08:00
%1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1]
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
store float 0.000000e+00, float* undef, align 4
Add alignment arguments to all the NEON load/store intrinsics. Update all the tests using those intrinsics and add support for auto-upgrading bitcode files with the old versions of the intrinsics. llvm-svn: 112271
2010-08-28 01:13:24 +08:00
%2 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1]
Change register allocation order for ARM VFP and NEON registers to put the callee-saved registers at the end of the lists. Also prefer to avoid using the low registers that are in register subclasses required by certain instructions, so that those registers will more likely be available when needed. This change makes a huge improvement in spilling in some cases. Thanks to Jakob for helping me realize the problem. Most of this patch is fixing the testsuite. There are quite a few places where we're checking for specific registers. I changed those to wildcards in places where that doesn't weaken the tests. The spill-q.ll and thumb2-spill-q.ll tests stopped spilling with this change, so I added a bunch of live values to force spills on those tests. llvm-svn: 116055
2010-10-08 14:15:13 +08:00
%ld3 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld4 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld5 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld6 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld7 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld8 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld9 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld10 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld11 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
%ld12 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
[opaque pointer type] Add textual IR support for explicit type parameter to load instruction Essentially the same as the GEP change in r230786. A similar migration script can be used to update test cases, though a few more test case improvements/changes were required this time around: (r229269-r229278) import fileinput import sys import re pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)") for line in sys.stdin: sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line)) Reviewers: rafael, dexonsmith, grosser Differential Revision: http://reviews.llvm.org/D7649 llvm-svn: 230794
2015-02-28 05:17:42 +08:00
%val173 = load <4 x float>, <4 x float>* undef ; <<4 x float>> [#uses=1]
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
br label %bb4
bb4: ; preds = %bb193, %entry
%besterror.0.2264 = phi <4 x float> [ undef, %entry ], [ %besterror.0.0, %bb193 ] ; <<4 x float>> [#uses=2]
%part0.0.0261 = phi <4 x float> [ zeroinitializer, %entry ], [ %23, %bb193 ] ; <<4 x float>> [#uses=2]
%3 = fmul <4 x float> zeroinitializer, %0 ; <<4 x float>> [#uses=2]
%4 = fadd <4 x float> %3, %part0.0.0261 ; <<4 x float>> [#uses=1]
%5 = shufflevector <4 x float> %3, <4 x float> undef, <2 x i32> <i32 2, i32 3> ; <<2 x float>> [#uses=1]
%6 = shufflevector <2 x float> %5, <2 x float> undef, <4 x i32> <i32 1, i32 1, i32 1, i32 1> ; <<4 x float>> [#uses=1]
%7 = fmul <4 x float> %1, undef ; <<4 x float>> [#uses=1]
%8 = fadd <4 x float> %7, <float 5.000000e-01, float 5.000000e-01, float 5.000000e-01, float 5.000000e-01> ; <<4 x float>> [#uses=1]
%9 = fptosi <4 x float> %8 to <4 x i32> ; <<4 x i32>> [#uses=1]
%10 = sitofp <4 x i32> %9 to <4 x float> ; <<4 x float>> [#uses=1]
%11 = fmul <4 x float> %10, %2 ; <<4 x float>> [#uses=1]
%12 = fmul <4 x float> undef, %6 ; <<4 x float>> [#uses=1]
%13 = fmul <4 x float> %11, %4 ; <<4 x float>> [#uses=1]
%14 = fsub <4 x float> %12, %13 ; <<4 x float>> [#uses=1]
%15 = fsub <4 x float> %14, undef ; <<4 x float>> [#uses=1]
%16 = fmul <4 x float> %15, <float 2.000000e+00, float 2.000000e+00, float 2.000000e+00, float 2.000000e+00> ; <<4 x float>> [#uses=1]
%17 = fadd <4 x float> %16, undef ; <<4 x float>> [#uses=1]
%18 = fmul <4 x float> %17, %val173 ; <<4 x float>> [#uses=1]
%19 = shufflevector <4 x float> %18, <4 x float> undef, <2 x i32> <i32 2, i32 3> ; <<2 x float>> [#uses=1]
%20 = shufflevector <2 x float> %19, <2 x float> undef, <4 x i32> zeroinitializer ; <<4 x float>> [#uses=1]
Change register allocation order for ARM VFP and NEON registers to put the callee-saved registers at the end of the lists. Also prefer to avoid using the low registers that are in register subclasses required by certain instructions, so that those registers will more likely be available when needed. This change makes a huge improvement in spilling in some cases. Thanks to Jakob for helping me realize the problem. Most of this patch is fixing the testsuite. There are quite a few places where we're checking for specific registers. I changed those to wildcards in places where that doesn't weaken the tests. The spill-q.ll and thumb2-spill-q.ll tests stopped spilling with this change, so I added a bunch of live values to force spills on those tests. llvm-svn: 116055
2010-10-08 14:15:13 +08:00
%tmp1 = fadd <4 x float> %20, %ld3
%tmp2 = fadd <4 x float> %tmp1, %ld4
%tmp3 = fadd <4 x float> %tmp2, %ld5
%tmp4 = fadd <4 x float> %tmp3, %ld6
%tmp5 = fadd <4 x float> %tmp4, %ld7
%tmp6 = fadd <4 x float> %tmp5, %ld8
%tmp7 = fadd <4 x float> %tmp6, %ld9
%tmp8 = fadd <4 x float> %tmp7, %ld10
%tmp9 = fadd <4 x float> %tmp8, %ld11
%21 = fadd <4 x float> %tmp9, %ld12
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
%22 = fcmp ogt <4 x float> %besterror.0.2264, %21 ; <<4 x i1>> [#uses=0]
Recognize more BUILD_VECTORs and VECTOR_SHUFFLEs that can be implemented by copying VFP subregs. This exposed a bunch of dead code in the *spill-q.ll tests, so I tweaked those tests to keep that code from being optimized away. Radar 7872877. llvm-svn: 104415
2010-05-22 08:23:12 +08:00
%tmp = extractelement <4 x i1> %22, i32 0
br i1 %tmp, label %bb193, label %bb186
Fix PR4789. Teach eliminateFrameIndex how to handle VLDRQ and VSTRQ which cannot fold any immediate offset. llvm-svn: 80191
2009-08-27 09:23:50 +08:00
bb186: ; preds = %bb4
br label %bb193
bb193: ; preds = %bb186, %bb4
%besterror.0.0 = phi <4 x float> [ %21, %bb186 ], [ %besterror.0.2264, %bb4 ] ; <<4 x float>> [#uses=1]
%23 = fadd <4 x float> %part0.0.0261, zeroinitializer ; <<4 x float>> [#uses=1]
br label %bb4
}