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/X86/divide-by-constant.ll

97 lines
2.1 KiB
LLVM
Raw Normal View History

Instruction scheduling itinerary for Intel Atom. Adds an instruction itinerary to all x86 instructions, giving each a default latency of 1, using the InstrItinClass IIC_DEFAULT. Sets specific latencies for Atom for the instructions in files X86InstrCMovSetCC.td, X86InstrArithmetic.td, X86InstrControl.td, and X86InstrShiftRotate.td. The Atom latencies for the remainder of the x86 instructions will be set in subsequent patches. Adds a test to verify that the scheduler is working. Also changes the scheduling preference to "Hybrid" for i386 Atom, while leaving x86_64 as ILP. Patch by Preston Gurd! llvm-svn: 149558
2012-02-02 07:20:51 +08:00
; RUN: llc < %s -mcpu=generic -mtriple=i686-pc-linux-gnu -asm-verbose=0 | FileCheck %s
Fix for PR2164: allow transforming arbitrary-width unsigned divides into multiplies. Some more cleverness would be nice, though. It would be nice if we could do this transformation on illegal types. Also, we would prefer a narrower constant when possible so that we can use a narrower multiply, which can be cheaper. llvm-svn: 60283
2008-11-30 14:02:26 +08:00
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:32:32"
target triple = "i686-pc-linux-gnu"
Add a couple dag combines to transform mulhi/mullo into a wider multiply when the wider type is legal. This allows us to compile: define zeroext i16 @test1(i16 zeroext %x) nounwind { entry: %div = udiv i16 %x, 33 ret i16 %div } into: test1: # @test1 movzwl 4(%esp), %eax imull $63551, %eax, %eax # imm = 0xF83F shrl $21, %eax ret instead of: test1: # @test1 movw $-1985, %ax # imm = 0xFFFFFFFFFFFFF83F mulw 4(%esp) andl $65504, %edx # imm = 0xFFE0 movl %edx, %eax shrl $5, %eax ret Implementing rdar://8760399 and example #4 from: http://blog.regehr.org/archives/320 We should implement the same thing for [su]mul_hilo, but I don't have immediate plans to do this. llvm-svn: 121696
2010-12-13 16:39:01 +08:00
define zeroext i16 @test1(i16 zeroext %x) nounwind {
Fix for PR2164: allow transforming arbitrary-width unsigned divides into multiplies. Some more cleverness would be nice, though. It would be nice if we could do this transformation on illegal types. Also, we would prefer a narrower constant when possible so that we can use a narrower multiply, which can be cheaper. llvm-svn: 60283
2008-11-30 14:02:26 +08:00
entry:
Add a couple dag combines to transform mulhi/mullo into a wider multiply when the wider type is legal. This allows us to compile: define zeroext i16 @test1(i16 zeroext %x) nounwind { entry: %div = udiv i16 %x, 33 ret i16 %div } into: test1: # @test1 movzwl 4(%esp), %eax imull $63551, %eax, %eax # imm = 0xF83F shrl $21, %eax ret instead of: test1: # @test1 movw $-1985, %ax # imm = 0xFFFFFFFFFFFFF83F mulw 4(%esp) andl $65504, %edx # imm = 0xFFE0 movl %edx, %eax shrl $5, %eax ret Implementing rdar://8760399 and example #4 from: http://blog.regehr.org/archives/320 We should implement the same thing for [su]mul_hilo, but I don't have immediate plans to do this. llvm-svn: 121696
2010-12-13 16:39:01 +08:00
%div = udiv i16 %x, 33
ret i16 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test1:
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: imull $63551, %eax
Add a couple dag combines to transform mulhi/mullo into a wider multiply when the wider type is legal. This allows us to compile: define zeroext i16 @test1(i16 zeroext %x) nounwind { entry: %div = udiv i16 %x, 33 ret i16 %div } into: test1: # @test1 movzwl 4(%esp), %eax imull $63551, %eax, %eax # imm = 0xF83F shrl $21, %eax ret instead of: test1: # @test1 movw $-1985, %ax # imm = 0xFFFFFFFFFFFFF83F mulw 4(%esp) andl $65504, %edx # imm = 0xFFE0 movl %edx, %eax shrl $5, %eax ret Implementing rdar://8760399 and example #4 from: http://blog.regehr.org/archives/320 We should implement the same thing for [su]mul_hilo, but I don't have immediate plans to do this. llvm-svn: 121696
2010-12-13 16:39:01 +08:00
; CHECK-NEXT: shrl $21, %eax
; CHECK-NEXT: ret
}
define zeroext i16 @test2(i8 signext %x, i16 zeroext %c) nounwind readnone ssp noredzone {
entry:
%div = udiv i16 %c, 3
ret i16 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test2:
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: imull $43691, %eax
Add a couple dag combines to transform mulhi/mullo into a wider multiply when the wider type is legal. This allows us to compile: define zeroext i16 @test1(i16 zeroext %x) nounwind { entry: %div = udiv i16 %x, 33 ret i16 %div } into: test1: # @test1 movzwl 4(%esp), %eax imull $63551, %eax, %eax # imm = 0xF83F shrl $21, %eax ret instead of: test1: # @test1 movw $-1985, %ax # imm = 0xFFFFFFFFFFFFF83F mulw 4(%esp) andl $65504, %edx # imm = 0xFFE0 movl %edx, %eax shrl $5, %eax ret Implementing rdar://8760399 and example #4 from: http://blog.regehr.org/archives/320 We should implement the same thing for [su]mul_hilo, but I don't have immediate plans to do this. llvm-svn: 121696
2010-12-13 16:39:01 +08:00
; CHECK-NEXT: shrl $17, %eax
; CHECK-NEXT: ret
}
define zeroext i8 @test3(i8 zeroext %x, i8 zeroext %c) nounwind readnone ssp noredzone {
entry:
%div = udiv i8 %c, 3
ret i8 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test3:
Reapply 122353-122355 with fixes. 122354 was wrong; the shift type was needed one place, the shift count type another. The transform in 123555 had the same problem. llvm-svn: 122366
2010-12-22 05:55:50 +08:00
; CHECK: movzbl 8(%esp), %eax
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK-NEXT: imull $171, %eax
[SDAG] Make the DAGCombine worklist not grow endlessly due to duplicate insertions. The old behavior could cause arbitrarily bad memory usage in the DAG combiner if there was heavy traffic of adding nodes already on the worklist to it. This commit switches the DAG combine worklist to work the same way as the instcombine worklist where we null-out removed entries and only add new entries to the worklist. My measurements of codegen time shows slight improvement. The memory utilization is unsurprisingly dominated by other factors (the IR and DAG itself I suspect). This change results in subtle, frustrating churn in the particular order in which DAG combines are applied which causes a number of minor regressions where we fail to match a pattern previously matched by accident. AFAICT, all of these should be using AddToWorklist to directly or should be written in a less brittle way. None of the changes seem drastically bad, and a few of the changes seem distinctly better. A major change required to make this work is to significantly harden the way in which the DAG combiner handle nodes which become dead (zero-uses). Previously, we relied on the ability to "priority-bump" them on the combine worklist to achieve recursive deletion of these nodes and ensure that the frontier of remaining live nodes all were added to the worklist. Instead, I've introduced a routine to just implement that precise logic with no indirection. It is a significantly simpler operation than that of the combiner worklist proper. I suspect this will also fix some other problems with the combiner. I think the x86 changes are really minor and uninteresting, but the avx512 change at least is hiding a "regression" (despite the test case being just noise, not testing some performance invariant) that might be looked into. Not sure if any of the others impact specific "important" code paths, but they didn't look terribly interesting to me, or the changes were really minor. The consensus in review is to fix any regressions that show up after the fact here. Thanks to the other reviewers for checking the output on other architectures. There is a specific regression on ARM that Tim already has a fix prepped to commit. Differential Revision: http://reviews.llvm.org/D4616 llvm-svn: 213727
2014-07-23 15:08:53 +08:00
; CHECK-NEXT: andl $65024, %eax
Reapply 122353-122355 with fixes. 122354 was wrong; the shift type was needed one place, the shift count type another. The transform in 123555 had the same problem. llvm-svn: 122366
2010-12-22 05:55:50 +08:00
; CHECK-NEXT: shrl $9, %eax
Add a couple dag combines to transform mulhi/mullo into a wider multiply when the wider type is legal. This allows us to compile: define zeroext i16 @test1(i16 zeroext %x) nounwind { entry: %div = udiv i16 %x, 33 ret i16 %div } into: test1: # @test1 movzwl 4(%esp), %eax imull $63551, %eax, %eax # imm = 0xF83F shrl $21, %eax ret instead of: test1: # @test1 movw $-1985, %ax # imm = 0xFFFFFFFFFFFFF83F mulw 4(%esp) andl $65504, %edx # imm = 0xFFE0 movl %edx, %eax shrl $5, %eax ret Implementing rdar://8760399 and example #4 from: http://blog.regehr.org/archives/320 We should implement the same thing for [su]mul_hilo, but I don't have immediate plans to do this. llvm-svn: 121696
2010-12-13 16:39:01 +08:00
; CHECK-NEXT: ret
}
define signext i16 @test4(i16 signext %x) nounwind {
entry:
%div = sdiv i16 %x, 33 ; <i32> [#uses=1]
Fix for PR2164: allow transforming arbitrary-width unsigned divides into multiplies. Some more cleverness would be nice, though. It would be nice if we could do this transformation on illegal types. Also, we would prefer a narrower constant when possible so that we can use a narrower multiply, which can be cheaper. llvm-svn: 60283
2008-11-30 14:02:26 +08:00
ret i16 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test4:
TableGen: use PrintMethods to print more aliases llvm-svn: 208607
2014-05-13 02:04:06 +08:00
; CHECK: imull $1986, %eax
Fix for PR2164: allow transforming arbitrary-width unsigned divides into multiplies. Some more cleverness would be nice, though. It would be nice if we could do this transformation on illegal types. Also, we would prefer a narrower constant when possible so that we can use a narrower multiply, which can be cheaper. llvm-svn: 60283
2008-11-30 14:02:26 +08:00
}
merge two tests llvm-svn: 121847
2010-12-15 13:58:59 +08:00
define i32 @test5(i32 %A) nounwind {
%tmp1 = udiv i32 %A, 1577682821 ; <i32> [#uses=1]
ret i32 %tmp1
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test5:
merge two tests llvm-svn: 121847
2010-12-15 13:58:59 +08:00
; CHECK: movl $365384439, %eax
; CHECK: mull 4(%esp)
}
Teach DAGCombine to fold fold (sra (trunc (sr x, c1)), c2) -> (trunc (sra x, c1+c2) when c1 equals the amount of bits that are truncated off. This happens all the time when a smul is promoted to a larger type. On x86-64 we now compile "int test(int x) { return x/10; }" into movslq %edi, %rax imulq $1717986919, %rax, %rax movq %rax, %rcx shrq $63, %rcx sarq $34, %rax <- used to be "shrq $32, %rax; sarl $2, %eax" addl %ecx, %eax This fires 96 times in gcc.c on x86-64. llvm-svn: 124559
2011-01-31 00:38:43 +08:00
define signext i16 @test6(i16 signext %x) nounwind {
entry:
%div = sdiv i16 %x, 10
ret i16 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test6:
[SDAG] Make the DAGCombine worklist not grow endlessly due to duplicate insertions. The old behavior could cause arbitrarily bad memory usage in the DAG combiner if there was heavy traffic of adding nodes already on the worklist to it. This commit switches the DAG combine worklist to work the same way as the instcombine worklist where we null-out removed entries and only add new entries to the worklist. My measurements of codegen time shows slight improvement. The memory utilization is unsurprisingly dominated by other factors (the IR and DAG itself I suspect). This change results in subtle, frustrating churn in the particular order in which DAG combines are applied which causes a number of minor regressions where we fail to match a pattern previously matched by accident. AFAICT, all of these should be using AddToWorklist to directly or should be written in a less brittle way. None of the changes seem drastically bad, and a few of the changes seem distinctly better. A major change required to make this work is to significantly harden the way in which the DAG combiner handle nodes which become dead (zero-uses). Previously, we relied on the ability to "priority-bump" them on the combine worklist to achieve recursive deletion of these nodes and ensure that the frontier of remaining live nodes all were added to the worklist. Instead, I've introduced a routine to just implement that precise logic with no indirection. It is a significantly simpler operation than that of the combiner worklist proper. I suspect this will also fix some other problems with the combiner. I think the x86 changes are really minor and uninteresting, but the avx512 change at least is hiding a "regression" (despite the test case being just noise, not testing some performance invariant) that might be looked into. Not sure if any of the others impact specific "important" code paths, but they didn't look terribly interesting to me, or the changes were really minor. The consensus in review is to fix any regressions that show up after the fact here. Thanks to the other reviewers for checking the output on other architectures. There is a specific regression on ARM that Tim already has a fix prepped to commit. Differential Revision: http://reviews.llvm.org/D4616 llvm-svn: 213727
2014-07-23 15:08:53 +08:00
; CHECK: imull $26215, %eax
; CHECK: movl %eax, %ecx
; CHECK: shrl $31, %ecx
; CHECK: sarl $18, %eax
Teach DAGCombine to fold fold (sra (trunc (sr x, c1)), c2) -> (trunc (sra x, c1+c2) when c1 equals the amount of bits that are truncated off. This happens all the time when a smul is promoted to a larger type. On x86-64 we now compile "int test(int x) { return x/10; }" into movslq %edi, %rax imulq $1717986919, %rax, %rax movq %rax, %rcx shrq $63, %rcx sarq $34, %rax <- used to be "shrq $32, %rax; sarl $2, %eax" addl %ecx, %eax This fires 96 times in gcc.c on x86-64. llvm-svn: 124559
2011-01-31 00:38:43 +08:00
}
BuildUDIV: If the divisor is even we can simplify the fixup of the multiplied value by introducing an early shift. This allows us to compile "unsigned foo(unsigned x) { return x/28; }" into shrl $2, %edi imulq $613566757, %rdi, %rax shrq $32, %rax ret instead of movl %edi, %eax imulq $613566757, %rax, %rcx shrq $32, %rcx subl %ecx, %eax shrl %eax addl %ecx, %eax shrl $4, %eax on x86_64 llvm-svn: 127829
2011-03-18 04:39:14 +08:00
define i32 @test7(i32 %x) nounwind {
%div = udiv i32 %x, 28
ret i32 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test7:
BuildUDIV: If the divisor is even we can simplify the fixup of the multiplied value by introducing an early shift. This allows us to compile "unsigned foo(unsigned x) { return x/28; }" into shrl $2, %edi imulq $613566757, %rdi, %rax shrq $32, %rax ret instead of movl %edi, %eax imulq $613566757, %rax, %rcx shrq $32, %rcx subl %ecx, %eax shrl %eax addl %ecx, %eax shrl $4, %eax on x86_64 llvm-svn: 127829
2011-03-18 04:39:14 +08:00
; CHECK: shrl $2
; CHECK: movl $613566757
; CHECK: mull
; CHECK-NOT: shrl
; CHECK: ret
}
PR13326: Fix a subtle edge case in the udiv -> magic multiply generator. This caused 6 of 65k possible 8 bit udivs to be wrong. llvm-svn: 160058
2012-07-12 02:31:59 +08:00
; PR13326
define i8 @test8(i8 %x) nounwind {
%div = udiv i8 %x, 78
ret i8 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test8:
PR13326: Fix a subtle edge case in the udiv -> magic multiply generator. This caused 6 of 65k possible 8 bit udivs to be wrong. llvm-svn: 160058
2012-07-12 02:31:59 +08:00
; CHECK: shrb %
; CHECK: imull $211
; CHECK: shrl $13
; CHECK: ret
}
define i8 @test9(i8 %x) nounwind {
%div = udiv i8 %x, 116
ret i8 %div
Convert CodeGen/*/*.ll tests to use the new CHECK-LABEL for easier debugging. No functionality change and all tests pass after conversion. This was done with the following sed invocation to catch label lines demarking function boundaries: sed -i '' "s/^;\( *\)\([A-Z0-9_]*\):\( *\)test\([A-Za-z0-9_-]*\):\( *\)$/;\1\2-LABEL:\3test\4:\5/g" test/CodeGen/*/*.ll which was written conservatively to avoid false positives rather than false negatives. I scanned through all the changes and everything looks correct. llvm-svn: 186258
2013-07-14 04:38:47 +08:00
; CHECK-LABEL: test9:
PR13326: Fix a subtle edge case in the udiv -> magic multiply generator. This caused 6 of 65k possible 8 bit udivs to be wrong. llvm-svn: 160058
2012-07-12 02:31:59 +08:00
; CHECK: shrb $2
; CHECK: imull $71
; CHECK: shrl $11
; CHECK: ret
}