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/AArch64/arm64-abi.ll

235 lines
8.5 KiB
LLVM
Raw Normal View History

[FastISel][AArch64] Use the correct register class to make the MI verifier happy. This is mostly achieved by providing the correct register class manually, because getRegClassFor always returns the GPR*AllRegClass for MVT::i32 and MVT::i64. Also cleanup the code to use the FastEmitInst_* method whenever possible. This makes sure that the operands' register class is properly constrained. For all the remaining cases this adds the missing constrainOperandRegClass calls for each operand. llvm-svn: 216225
2014-08-22 04:57:57 +08:00
; RUN: llc -mtriple=arm64-apple-darwin -mcpu=cyclone -enable-misched=false < %s | FileCheck %s
; RUN: llc -O0 -mtriple=arm64-apple-darwin < %s | FileCheck --check-prefix=FAST %s
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; rdar://9932559
define i64 @i8i16callee(i64 %a1, i64 %a2, i64 %a3, i8 signext %a4, i16 signext %a5, i64 %a6, i64 %a7, i64 %a8, i8 signext %b1, i16 signext %b2, i8 signext %b3, i8 signext %b4) nounwind readnone noinline {
entry:
; CHECK-LABEL: i8i16callee:
; The 8th, 9th, 10th and 11th arguments are passed at sp, sp+2, sp+4, sp+5.
; They are i8, i16, i8 and i8.
AArch64: mark small types (i1, i8, i16) as promoted This means the output of LowerFormalArguments returns a lowered SDValue with the correct type (expected in SelectionDAGBuilder). Without this, an assertion under a DEBUG macro triggers when those types are passed on the stack. llvm-svn: 210102
2014-06-03 21:54:53 +08:00
; CHECK-DAG: ldrsb {{w[0-9]+}}, [sp, #5]
; CHECK-DAG: ldrsb {{w[0-9]+}}, [sp, #4]
; CHECK-DAG: ldrsh {{w[0-9]+}}, [sp, #2]
; CHECK-DAG: ldrsb {{w[0-9]+}}, [sp]
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; FAST-LABEL: i8i16callee:
AArch64: mark small types (i1, i8, i16) as promoted This means the output of LowerFormalArguments returns a lowered SDValue with the correct type (expected in SelectionDAGBuilder). Without this, an assertion under a DEBUG macro triggers when those types are passed on the stack. llvm-svn: 210102
2014-06-03 21:54:53 +08:00
; FAST-DAG: ldrsb {{w[0-9]+}}, [sp, #5]
; FAST-DAG: ldrsb {{w[0-9]+}}, [sp, #4]
; FAST-DAG: ldrsh {{w[0-9]+}}, [sp, #2]
; FAST-DAG: ldrsb {{w[0-9]+}}, [sp]
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%conv = sext i8 %a4 to i64
%conv3 = sext i16 %a5 to i64
%conv8 = sext i8 %b1 to i64
%conv9 = sext i16 %b2 to i64
%conv11 = sext i8 %b3 to i64
%conv13 = sext i8 %b4 to i64
%add10 = add i64 %a2, %a1
%add12 = add i64 %add10, %a3
%add14 = add i64 %add12, %conv
%add = add i64 %add14, %conv3
%add1 = add i64 %add, %a6
%add2 = add i64 %add1, %a7
%add4 = add i64 %add2, %a8
%add5 = add i64 %add4, %conv8
%add6 = add i64 %add5, %conv9
%add7 = add i64 %add6, %conv11
%add15 = add i64 %add7, %conv13
%sext = shl i64 %add15, 32
%conv17 = ashr exact i64 %sext, 32
ret i64 %conv17
}
define i32 @i8i16caller() nounwind readnone {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: i8i16caller
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; The 8th, 9th, 10th and 11th arguments are passed at sp, sp+2, sp+4, sp+5.
; They are i8, i16, i8 and i8.
AArch64: mark small types (i1, i8, i16) as promoted This means the output of LowerFormalArguments returns a lowered SDValue with the correct type (expected in SelectionDAGBuilder). Without this, an assertion under a DEBUG macro triggers when those types are passed on the stack. llvm-svn: 210102
2014-06-03 21:54:53 +08:00
; CHECK-DAG: strb {{w[0-9]+}}, [sp, #5]
; CHECK-DAG: strb {{w[0-9]+}}, [sp, #4]
; CHECK-DAG: strh {{w[0-9]+}}, [sp, #2]
; CHECK-DAG: strb {{w[0-9]+}}, [sp]
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: bl
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; FAST-LABEL: i8i16caller
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; FAST: strb {{w[0-9]+}}, [sp]
; FAST: strh {{w[0-9]+}}, [sp, #2]
; FAST: strb {{w[0-9]+}}, [sp, #4]
; FAST: strb {{w[0-9]+}}, [sp, #5]
; FAST: bl
%call = tail call i64 @i8i16callee(i64 0, i64 1, i64 2, i8 signext 3, i16 signext 4, i64 5, i64 6, i64 7, i8 signext 97, i16 signext 98, i8 signext 99, i8 signext 100)
%conv = trunc i64 %call to i32
ret i32 %conv
}
; rdar://12651543
define double @circle_center([2 x float] %a) nounwind ssp {
%call = tail call double @ext([2 x float] %a) nounwind
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: circle_center
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: bl
ret double %call
}
declare double @ext([2 x float])
; rdar://12656141
; 16-byte vector should be aligned at 16-byte when passing on stack.
; A double argument will be passed on stack, so vecotr should be at sp+16.
define double @fixed_4i(<4 x i32>* nocapture %in) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: fixed_4i
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: str [[REG_1:q[0-9]+]], [sp, #16]
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; FAST-LABEL: fixed_4i
[FastIsel][AArch64] Add support for the FastLowerCall and FastLowerIntrinsicCall target-hooks. This commit modifies the existing call lowering functions to be used as the FastLowerCall and FastLowerIntrinsicCall target-hooks instead. This enables patchpoint intrinsic lowering for AArch64. This fixes <rdar://problem/17733076> llvm-svn: 213704
2014-07-23 07:14:58 +08:00
; FAST: sub sp, sp
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; FAST: mov x[[ADDR:[0-9]+]], sp
; FAST: str [[REG_1:q[0-9]+]], [x[[ADDR]], #16]
[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
%0 = load <4 x i32>, <4 x i32>* %in, align 16
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%call = tail call double @args_vec_4i(double 3.000000e+00, <4 x i32> %0, <4 x i32> %0, <4 x i32> %0, <4 x i32> %0, <4 x i32> %0, <4 x i32> %0, <4 x i32> %0, double 3.000000e+00, <4 x i32> %0, i8 signext 3)
ret double %call
}
declare double @args_vec_4i(double, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, <4 x i32>, double, <4 x i32>, i8 signext)
; rdar://12695237
; d8 at sp, i in register w0.
@g_d = common global double 0.000000e+00, align 8
define void @test1(float %f1, double %d1, double %d2, double %d3, double %d4,
double %d5, double %d6, double %d7, double %d8, i32 %i) nounwind ssp {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test1
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: ldr [[REG_1:d[0-9]+]], [sp]
; CHECK: scvtf [[REG_2:s[0-9]+]], w0
; CHECK: fadd s0, [[REG_2]], s0
%conv = sitofp i32 %i to float
%add = fadd float %conv, %f1
%conv1 = fpext float %add to double
%add2 = fadd double %conv1, %d7
%add3 = fadd double %add2, %d8
store double %add3, double* @g_d, align 8
ret void
}
; i9 at sp, d1 in register s0.
define void @test2(i32 %i1, i32 %i2, i32 %i3, i32 %i4, i32 %i5, i32 %i6,
i32 %i7, i32 %i8, i32 %i9, float %d1) nounwind ssp {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test2
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: scvtf [[REG_2:s[0-9]+]], w0
; CHECK: fadd s0, [[REG_2]], s0
; CHECK: ldr [[REG_1:s[0-9]+]], [sp]
%conv = sitofp i32 %i1 to float
%add = fadd float %conv, %d1
%conv1 = fpext float %add to double
%conv2 = sitofp i32 %i8 to double
%add3 = fadd double %conv2, %conv1
%conv4 = sitofp i32 %i9 to double
%add5 = fadd double %conv4, %add3
store double %add5, double* @g_d, align 8
ret void
}
; rdar://12648441
; Check alignment on stack for v64, f64, i64, f32, i32.
define double @test3(<2 x i32>* nocapture %in) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test3
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: str [[REG_1:d[0-9]+]], [sp, #8]
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; FAST-LABEL: test3
[AArch64] Combine callee-save and local stack SP adjustment instructions. Summary: If a function needs to allocate both callee-save stack memory and local stack memory, we currently decrement/increment the SP in two steps: first for the callee-save area, and then for the local stack area. This changes the code to allocate them both at once at the very beginning/end of the function. This has two benefits: 1) there is one fewer sub/add micro-op in the prologue/epilogue 2) the stack adjustment instructions act as a scheduling barrier, so moving them to the very beginning/end of the function increases post-RA scheduler's ability to move instructions (that only depend on argument registers) before any of the callee-save stores This change can cause an increase in instructions if the original local stack SP decrement could be folded into the first store to the stack. This occurs when the first local stack store is to stack offset 0. In this case we are trading off one more sub instruction for one fewer sub micro-op (along with benefits (2) and (3) above). Reviewers: t.p.northover Subscribers: aemerson, rengolin, mcrosier, llvm-commits Differential Revision: http://reviews.llvm.org/D18619 llvm-svn: 268746
2016-05-07 00:34:59 +08:00
; FAST: sub sp, sp, #48
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; FAST: mov x[[ADDR:[0-9]+]], sp
; FAST: str [[REG_1:d[0-9]+]], [x[[ADDR]], #8]
[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
%0 = load <2 x i32>, <2 x i32>* %in, align 8
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%call = tail call double @args_vec_2i(double 3.000000e+00, <2 x i32> %0,
<2 x i32> %0, <2 x i32> %0, <2 x i32> %0, <2 x i32> %0, <2 x i32> %0,
<2 x i32> %0, float 3.000000e+00, <2 x i32> %0, i8 signext 3)
ret double %call
}
declare double @args_vec_2i(double, <2 x i32>, <2 x i32>, <2 x i32>, <2 x i32>,
<2 x i32>, <2 x i32>, <2 x i32>, float, <2 x i32>, i8 signext)
define double @test4(double* nocapture %in) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test4
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: str [[REG_1:d[0-9]+]], [sp, #8]
; CHECK: str [[REG_2:w[0-9]+]], [sp]
; CHECK: orr w0, wzr, #0x3
[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
%0 = load double, double* %in, align 8
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%call = tail call double @args_f64(double 3.000000e+00, double %0, double %0,
double %0, double %0, double %0, double %0, double %0,
float 3.000000e+00, double %0, i8 signext 3)
ret double %call
}
declare double @args_f64(double, double, double, double, double, double, double,
double, float, double, i8 signext)
define i64 @test5(i64* nocapture %in) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test5
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: strb [[REG_3:w[0-9]+]], [sp, #16]
; CHECK: str [[REG_1:x[0-9]+]], [sp, #8]
; CHECK: str [[REG_2:w[0-9]+]], [sp]
[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
%0 = load i64, i64* %in, align 8
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%call = tail call i64 @args_i64(i64 3, i64 %0, i64 %0, i64 %0, i64 %0, i64 %0,
i64 %0, i64 %0, i32 3, i64 %0, i8 signext 3)
ret i64 %call
}
declare i64 @args_i64(i64, i64, i64, i64, i64, i64, i64, i64, i32, i64,
i8 signext)
define i32 @test6(float* nocapture %in) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test6
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: strb [[REG_2:w[0-9]+]], [sp, #8]
; CHECK: str [[REG_1:s[0-9]+]], [sp, #4]
; CHECK: strh [[REG_3:w[0-9]+]], [sp]
[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
%0 = load float, float* %in, align 4
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%call = tail call i32 @args_f32(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6,
i32 7, i32 8, float 1.0, float 2.0, float 3.0, float 4.0, float 5.0,
float 6.0, float 7.0, float 8.0, i16 signext 3, float %0,
i8 signext 3)
ret i32 %call
}
declare i32 @args_f32(i32, i32, i32, i32, i32, i32, i32, i32,
float, float, float, float, float, float, float, float,
i16 signext, float, i8 signext)
define i32 @test7(i32* nocapture %in) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test7
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: strb [[REG_2:w[0-9]+]], [sp, #8]
; CHECK: str [[REG_1:w[0-9]+]], [sp, #4]
; CHECK: strh [[REG_3:w[0-9]+]], [sp]
[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
%0 = load i32, i32* %in, align 4
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
%call = tail call i32 @args_i32(i32 3, i32 %0, i32 %0, i32 %0, i32 %0, i32 %0,
i32 %0, i32 %0, i16 signext 3, i32 %0, i8 signext 4)
ret i32 %call
}
declare i32 @args_i32(i32, i32, i32, i32, i32, i32, i32, i32, i16 signext, i32,
i8 signext)
define i32 @test8(i32 %argc, i8** nocapture %argv) nounwind {
entry:
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; CHECK-LABEL: test8
In visitSTORE, always use FindBetterChain, rather than only when UseAA is enabled. Retrying after fixing after removing load-store factoring through token factors in favor of improved token factor operand pruning Simplify Consecutive Merge Store Candidate Search Now that address aliasing is much less conservative, push through simplified store merging search which only checks for parallel stores through the chain subgraph. This is cleaner as the separation of non-interfering loads/stores from the store-merging logic. Whem merging stores, search up the chain through a single load, and finds all possible stores by looking down from through a load and a TokenFactor to all stores visited. This improves the quality of the output SelectionDAG and generally the output CodeGen (with some exceptions). Additional Minor Changes: 1. Finishes removing unused AliasLoad code 2. Unifies the the chain aggregation in the merged stores across code paths 3. Re-add the Store node to the worklist after calling SimplifyDemandedBits. 4. Increase GatherAllAliasesMaxDepth from 6 to 18. That number is arbitrary, but seemed sufficient to not cause regressions in tests. This finishes the change Matt Arsenault started in r246307 and jyknight's original patch. Many tests required some changes as memory operations are now reorderable. Some tests relying on the order were changed to use volatile memory operations Noteworthy tests: CodeGen/AArch64/argument-blocks.ll - It's not entirely clear what the test_varargs_stackalign test is supposed to be asserting, but the new code looks right. CodeGen/AArch64/arm64-memset-inline.lli - CodeGen/AArch64/arm64-stur.ll - CodeGen/ARM/memset-inline.ll - The backend now generates *worse* code due to store merging succeeding, as we do do a 16-byte constant-zero store efficiently. CodeGen/AArch64/merge-store.ll - Improved, but there still seems to be an extraneous vector insert from an element to itself? CodeGen/PowerPC/ppc64-align-long-double.ll - Worse code emitted in this case, due to the improved store->load forwarding. CodeGen/X86/dag-merge-fast-accesses.ll - CodeGen/X86/MergeConsecutiveStores.ll - CodeGen/X86/stores-merging.ll - CodeGen/Mips/load-store-left-right.ll - Restored correct merging of non-aligned stores CodeGen/AMDGPU/promote-alloca-stored-pointer-value.ll - Improved. Correctly merges buffer_store_dword calls CodeGen/AMDGPU/si-triv-disjoint-mem-access.ll - Improved. Sidesteps loading a stored value and merges two stores CodeGen/X86/pr18023.ll - This test has been removed, as it was asserting incorrect behavior. Non-volatile stores *CAN* be moved past volatile loads, and now are. CodeGen/X86/vector-idiv.ll - CodeGen/X86/vector-lzcnt-128.ll - It's basically impossible to tell what these tests are actually testing. But, looks like the code got better due to the memory operations being recognized as non-aliasing. CodeGen/X86/win32-eh.ll - Both loads of the securitycookie are now merged. Reviewers: arsenm, hfinkel, tstellarAMD, jyknight, nhaehnle Subscribers: wdng, nhaehnle, nemanjai, arsenm, weimingz, niravd, RKSimon, aemerson, qcolombet, dsanders, resistor, tstellarAMD, t.p.northover, spatel Differential Revision: https://reviews.llvm.org/D14834 llvm-svn: 289659
2016-12-14 23:44:26 +08:00
; CHECK: str w8, [sp]
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; CHECK: bl
[AArch64] Use CHECK-LABEL in ARM64 ABI unit tests. llvm-svn: 213703
2014-07-23 07:14:54 +08:00
; FAST-LABEL: test8
ARM64: initial backend import This adds a second implementation of the AArch64 architecture to LLVM, accessible in parallel via the "arm64" triple. The plan over the coming weeks & months is to merge the two into a single backend, during which time thorough code review should naturally occur. Everything will be easier with the target in-tree though, hence this commit. llvm-svn: 205090
2014-03-29 18:18:08 +08:00
; FAST: strb {{w[0-9]+}}, [sp]
; FAST: strb {{w[0-9]+}}, [sp, #1]
; FAST: strb {{w[0-9]+}}, [sp, #2]
; FAST: strb {{w[0-9]+}}, [sp, #3]
; FAST: bl
tail call void @args_i1(i1 zeroext false, i1 zeroext true, i1 zeroext false,
i1 zeroext true, i1 zeroext false, i1 zeroext true,
i1 zeroext false, i1 zeroext true, i1 zeroext false,
i1 zeroext true, i1 zeroext false, i1 zeroext true)
ret i32 0
}
declare void @args_i1(i1 zeroext, i1 zeroext, i1 zeroext, i1 zeroext,
i1 zeroext, i1 zeroext, i1 zeroext, i1 zeroext,
i1 zeroext, i1 zeroext, i1 zeroext, i1 zeroext)
define i32 @i1_stack_incoming(i64 %a, i64 %b, i64 %c, i64 %d, i64 %e, i64 %f,
i64 %g, i64 %h, i64 %i, i1 zeroext %j) {
; CHECK-LABEL: i1_stack_incoming:
; CHECK: ldrb w0, [sp, #8]
; CHECK: ret
%v = zext i1 %j to i32
ret i32 %v
}