maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/Transforms/LowerSwitch/feature.ll

105 lines
3.6 KiB
LLVM
Raw Normal View History

PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
; RUN: opt < %s -lowerswitch -S | FileCheck %s
; We have switch on input.
; On output we should got binary comparison tree. Check that all is fine.
LowerSwitch: track bounding range for the condition tree. When LowerSwitch transforms a switch instruction into a tree of ifs it is actually performing a binary search into the various case ranges, to see if the current value falls into one cases range of values. So, if we have a program with something like this: switch (a) { case 0: do0(); break; case 1: do1(); break; case 2: do2(); break; default: break; } the code produced is something like this: if (a < 1) { if (a == 0) { do0(); } } else { if (a < 2) { if (a == 1) { do1(); } } else { if (a == 2) { do2(); } } } This code is inefficient because the check (a == 1) to execute do1() is not needed. The reason is that because we already checked that (a >= 1) initially by checking that also (a < 2) we basically already inferred that (a == 1) without the need of an extra basic block spawned to check if actually (a == 1). The patch addresses this problem by keeping track of already checked bounds in the LowerSwitch algorithm, so that when the time arrives to produce a Leaf Block that checks the equality with the case value / range the algorithm can decide if that block is really needed depending on the already checked bounds . For example, the above with "a = 1" would work like this: the bounds start as LB: NONE , UB: NONE as (a < 1) is emitted the bounds for the else path become LB: 1 UB: NONE. This happens because by failing the test (a < 1) we know that the value "a" cannot be smaller than 1 if we enter the else branch. After the emitting the check (a < 2) the bounds in the if branch become LB: 1 UB: 1. This is because by checking that "a" is smaller than 2 then the upper bound becomes 2 - 1 = 1. When it is time to emit the leaf block for "case 1:" we notice that 1 can be squeezed exactly in between the LB and UB, which means that if we arrived to that block there is no need to emit a block that checks if (a == 1). Patch by: Marcello Maggioni <hayarms@gmail.com> llvm-svn: 211038
2014-06-17 00:55:20 +08:00
;CHECK: entry:
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK-NEXT: br label %NodeBlock19
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock19: ; preds = %entry
;CHECK-NEXT: %Pivot20 = icmp slt i32 %tmp158, 10
;CHECK-NEXT: br i1 %Pivot20, label %NodeBlock5, label %NodeBlock17
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock17: ; preds = %NodeBlock19
;CHECK-NEXT: %Pivot18 = icmp slt i32 %tmp158, 13
;CHECK-NEXT: br i1 %Pivot18, label %NodeBlock9, label %NodeBlock15
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock15: ; preds = %NodeBlock17
;CHECK-NEXT: %Pivot16 = icmp slt i32 %tmp158, 14
;CHECK-NEXT: br i1 %Pivot16, label %bb330, label %NodeBlock13
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock13: ; preds = %NodeBlock15
;CHECK-NEXT: %Pivot14 = icmp slt i32 %tmp158, 15
;CHECK-NEXT: br i1 %Pivot14, label %bb332, label %LeafBlock11
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: LeafBlock11: ; preds = %NodeBlock13
LowerSwitch: track bounding range for the condition tree. When LowerSwitch transforms a switch instruction into a tree of ifs it is actually performing a binary search into the various case ranges, to see if the current value falls into one cases range of values. So, if we have a program with something like this: switch (a) { case 0: do0(); break; case 1: do1(); break; case 2: do2(); break; default: break; } the code produced is something like this: if (a < 1) { if (a == 0) { do0(); } } else { if (a < 2) { if (a == 1) { do1(); } } else { if (a == 2) { do2(); } } } This code is inefficient because the check (a == 1) to execute do1() is not needed. The reason is that because we already checked that (a >= 1) initially by checking that also (a < 2) we basically already inferred that (a == 1) without the need of an extra basic block spawned to check if actually (a == 1). The patch addresses this problem by keeping track of already checked bounds in the LowerSwitch algorithm, so that when the time arrives to produce a Leaf Block that checks the equality with the case value / range the algorithm can decide if that block is really needed depending on the already checked bounds . For example, the above with "a = 1" would work like this: the bounds start as LB: NONE , UB: NONE as (a < 1) is emitted the bounds for the else path become LB: 1 UB: NONE. This happens because by failing the test (a < 1) we know that the value "a" cannot be smaller than 1 if we enter the else branch. After the emitting the check (a < 2) the bounds in the if branch become LB: 1 UB: 1. This is because by checking that "a" is smaller than 2 then the upper bound becomes 2 - 1 = 1. When it is time to emit the leaf block for "case 1:" we notice that 1 can be squeezed exactly in between the LB and UB, which means that if we arrived to that block there is no need to emit a block that checks if (a == 1). Patch by: Marcello Maggioni <hayarms@gmail.com> llvm-svn: 211038
2014-06-17 00:55:20 +08:00
;CHECK-NEXT: %SwitchLeaf12 = icmp eq i32 %tmp158, 15
;CHECK-NEXT: br i1 %SwitchLeaf12, label %bb334, label %NewDefault
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock9: ; preds = %NodeBlock17
;CHECK-NEXT: %Pivot10 = icmp slt i32 %tmp158, 11
;CHECK-NEXT: br i1 %Pivot10, label %bb324, label %NodeBlock7
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock7: ; preds = %NodeBlock9
;CHECK-NEXT: %Pivot8 = icmp slt i32 %tmp158, 12
;CHECK-NEXT: br i1 %Pivot8, label %bb326, label %bb328
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock5: ; preds = %NodeBlock19
;CHECK-NEXT: %Pivot6 = icmp slt i32 %tmp158, 7
;CHECK-NEXT: br i1 %Pivot6, label %NodeBlock, label %NodeBlock3
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock3: ; preds = %NodeBlock5
;CHECK-NEXT: %Pivot4 = icmp slt i32 %tmp158, 8
;CHECK-NEXT: br i1 %Pivot4, label %bb, label %NodeBlock1
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock1: ; preds = %NodeBlock3
;CHECK-NEXT: %Pivot2 = icmp slt i32 %tmp158, 9
;CHECK-NEXT: br i1 %Pivot2, label %bb338, label %bb322
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Have a single way for creating unique value names. We had two code paths. One would create names like "foo.1" and the other names like "foo1". For globals it is important to use "foo.1" to help C++ name demangling. For locals there is no strong reason to go one way or the other so I kept the most common mangling (foo1). llvm-svn: 253804
2015-11-22 08:16:24 +08:00
;CHECK: NodeBlock: ; preds = %NodeBlock5
LowerSwitch: track bounding range for the condition tree. When LowerSwitch transforms a switch instruction into a tree of ifs it is actually performing a binary search into the various case ranges, to see if the current value falls into one cases range of values. So, if we have a program with something like this: switch (a) { case 0: do0(); break; case 1: do1(); break; case 2: do2(); break; default: break; } the code produced is something like this: if (a < 1) { if (a == 0) { do0(); } } else { if (a < 2) { if (a == 1) { do1(); } } else { if (a == 2) { do2(); } } } This code is inefficient because the check (a == 1) to execute do1() is not needed. The reason is that because we already checked that (a >= 1) initially by checking that also (a < 2) we basically already inferred that (a == 1) without the need of an extra basic block spawned to check if actually (a == 1). The patch addresses this problem by keeping track of already checked bounds in the LowerSwitch algorithm, so that when the time arrives to produce a Leaf Block that checks the equality with the case value / range the algorithm can decide if that block is really needed depending on the already checked bounds . For example, the above with "a = 1" would work like this: the bounds start as LB: NONE , UB: NONE as (a < 1) is emitted the bounds for the else path become LB: 1 UB: NONE. This happens because by failing the test (a < 1) we know that the value "a" cannot be smaller than 1 if we enter the else branch. After the emitting the check (a < 2) the bounds in the if branch become LB: 1 UB: 1. This is because by checking that "a" is smaller than 2 then the upper bound becomes 2 - 1 = 1. When it is time to emit the leaf block for "case 1:" we notice that 1 can be squeezed exactly in between the LB and UB, which means that if we arrived to that block there is no need to emit a block that checks if (a == 1). Patch by: Marcello Maggioni <hayarms@gmail.com> llvm-svn: 211038
2014-06-17 00:55:20 +08:00
;CHECK-NEXT: %Pivot = icmp slt i32 %tmp158, 0
;CHECK-NEXT: br i1 %Pivot, label %LeafBlock, label %bb338
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
LowerSwitch: track bounding range for the condition tree. When LowerSwitch transforms a switch instruction into a tree of ifs it is actually performing a binary search into the various case ranges, to see if the current value falls into one cases range of values. So, if we have a program with something like this: switch (a) { case 0: do0(); break; case 1: do1(); break; case 2: do2(); break; default: break; } the code produced is something like this: if (a < 1) { if (a == 0) { do0(); } } else { if (a < 2) { if (a == 1) { do1(); } } else { if (a == 2) { do2(); } } } This code is inefficient because the check (a == 1) to execute do1() is not needed. The reason is that because we already checked that (a >= 1) initially by checking that also (a < 2) we basically already inferred that (a == 1) without the need of an extra basic block spawned to check if actually (a == 1). The patch addresses this problem by keeping track of already checked bounds in the LowerSwitch algorithm, so that when the time arrives to produce a Leaf Block that checks the equality with the case value / range the algorithm can decide if that block is really needed depending on the already checked bounds . For example, the above with "a = 1" would work like this: the bounds start as LB: NONE , UB: NONE as (a < 1) is emitted the bounds for the else path become LB: 1 UB: NONE. This happens because by failing the test (a < 1) we know that the value "a" cannot be smaller than 1 if we enter the else branch. After the emitting the check (a < 2) the bounds in the if branch become LB: 1 UB: 1. This is because by checking that "a" is smaller than 2 then the upper bound becomes 2 - 1 = 1. When it is time to emit the leaf block for "case 1:" we notice that 1 can be squeezed exactly in between the LB and UB, which means that if we arrived to that block there is no need to emit a block that checks if (a == 1). Patch by: Marcello Maggioni <hayarms@gmail.com> llvm-svn: 211038
2014-06-17 00:55:20 +08:00
;CHECK: LeafBlock: ; preds = %NodeBlock
;CHECK-NEXT: %tmp158.off = add i32 %tmp158, 6
;CHECK-NEXT: %SwitchLeaf = icmp ule i32 %tmp158.off, 4
;CHECK-NEXT: br i1 %SwitchLeaf, label %bb338, label %NewDefault
Use range tests in LowerSwitch, where possible llvm-svn: 35057
2007-03-11 00:46:28 +08:00
define i32 @main(i32 %tmp158) {
entry:
PR1255 related changes (case ranges): LowerSwitch::Clusterify : main functinality was replaced with CRSBuilder::optimize, so big part of Clusterify's code was reduced. test/Transform/LowerSwitch/feature.ll - this test was refactored: grep + count was replaced with FileCheck usage. llvm-svn: 157384
2012-05-24 17:33:20 +08:00
Use range tests in LowerSwitch, where possible llvm-svn: 35057
2007-03-11 00:46:28 +08:00
switch i32 %tmp158, label %bb336 [
i32 -2, label %bb338
i32 -3, label %bb338
i32 -4, label %bb338
i32 -5, label %bb338
i32 -6, label %bb338
i32 0, label %bb338
i32 1, label %bb338
i32 2, label %bb338
i32 3, label %bb338
i32 4, label %bb338
i32 5, label %bb338
i32 6, label %bb338
i32 7, label %bb
i32 8, label %bb338
i32 9, label %bb322
i32 10, label %bb324
i32 11, label %bb326
i32 12, label %bb328
i32 13, label %bb330
i32 14, label %bb332
i32 15, label %bb334
]
bb:
ret i32 2
bb322:
ret i32 3
bb324:
ret i32 4
bb326:
ret i32 5
bb328:
ret i32 6
bb330:
ret i32 7
bb332:
ret i32 8
bb334:
ret i32 9
bb336:
ret i32 10
bb338:
ret i32 11
}