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/GVN/rle.ll

404 lines
8.3 KiB
LLVM
Raw Normal View History

enhance GVN to forward substitute a stored value to a load (and load -> load) when the base pointers must alias but when they are different types. This occurs very very frequently in 176.gcc and other code that uses bitfields a lot. llvm-svn: 82399
2009-09-21 03:03:47 +08:00
; RUN: opt < %s -gvn -S | FileCheck %s
; 32-bit little endian target.
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-f80:128:128"
;; Trivial RLE test.
define i32 @test0(i32 %V, i32* %P) {
store i32 %V, i32* %P
%A = load i32* %P
ret i32 %A
; CHECK: @test0
; CHECK: ret i32 %V
}
fix PR5016, a crash I introduced in GVN handing first class arrays and structs, which cannot be bitcast to integers. llvm-svn: 82460
2009-09-22 01:24:04 +08:00
;;===----------------------------------------------------------------------===;;
;; Tests for crashers
;;===----------------------------------------------------------------------===;;
;; PR5016
define i8 @crash0({i32, i32} %A, {i32, i32}* %P) {
store {i32, i32} %A, {i32, i32}* %P
%X = bitcast {i32, i32}* %P to i8*
%Y = load i8* %X
ret i8 %Y
}
enhance GVN to forward substitute a stored value to a load (and load -> load) when the base pointers must alias but when they are different types. This occurs very very frequently in 176.gcc and other code that uses bitfields a lot. llvm-svn: 82399
2009-09-21 03:03:47 +08:00
;;===----------------------------------------------------------------------===;;
;; Store -> Load and Load -> Load forwarding where src and dst are different
;; types, but where the base pointer is a must alias.
;;===----------------------------------------------------------------------===;;
;; i32 -> f32 forwarding.
define float @coerce_mustalias1(i32 %V, i32* %P) {
store i32 %V, i32* %P
%P2 = bitcast i32* %P to float*
%A = load float* %P2
ret float %A
; CHECK: @coerce_mustalias1
; CHECK-NOT: load
; CHECK: ret float
}
;; i32* -> float forwarding.
define float @coerce_mustalias2(i32* %V, i32** %P) {
store i32* %V, i32** %P
%P2 = bitcast i32** %P to float*
%A = load float* %P2
ret float %A
; CHECK: @coerce_mustalias2
; CHECK-NOT: load
; CHECK: ret float
}
;; float -> i32* forwarding.
define i32* @coerce_mustalias3(float %V, float* %P) {
store float %V, float* %P
%P2 = bitcast float* %P to i32**
%A = load i32** %P2
ret i32* %A
; CHECK: @coerce_mustalias3
; CHECK-NOT: load
; CHECK: ret i32*
}
;; i32 -> f32 load forwarding.
define float @coerce_mustalias4(i32* %P, i1 %cond) {
%A = load i32* %P
Move CoerceAvailableValueToLoadType earlier in GVN.cpp. Hook it up so that nonlocal and partially redundant loads can use it as well. The testcase shows examples of craziness this can handle. This triggers *many* times in 176.gcc. llvm-svn: 82403
2009-09-21 04:09:34 +08:00
enhance GVN to forward substitute a stored value to a load (and load -> load) when the base pointers must alias but when they are different types. This occurs very very frequently in 176.gcc and other code that uses bitfields a lot. llvm-svn: 82399
2009-09-21 03:03:47 +08:00
%P2 = bitcast i32* %P to float*
%B = load float* %P2
Move CoerceAvailableValueToLoadType earlier in GVN.cpp. Hook it up so that nonlocal and partially redundant loads can use it as well. The testcase shows examples of craziness this can handle. This triggers *many* times in 176.gcc. llvm-svn: 82403
2009-09-21 04:09:34 +08:00
br i1 %cond, label %T, label %F
T:
enhance GVN to forward substitute a stored value to a load (and load -> load) when the base pointers must alias but when they are different types. This occurs very very frequently in 176.gcc and other code that uses bitfields a lot. llvm-svn: 82399
2009-09-21 03:03:47 +08:00
ret float %B
F:
%X = bitcast i32 %A to float
ret float %X
; CHECK: @coerce_mustalias4
; CHECK: %A = load i32* %P
; CHECK-NOT: load
; CHECK: ret float
; CHECK: F:
}
;; i32 -> i8 forwarding
define i8 @coerce_mustalias5(i32 %V, i32* %P) {
store i32 %V, i32* %P
%P2 = bitcast i32* %P to i8*
%A = load i8* %P2
ret i8 %A
; CHECK: @coerce_mustalias5
; CHECK-NOT: load
; CHECK: ret i8
}
;; i64 -> float forwarding
define float @coerce_mustalias6(i64 %V, i64* %P) {
store i64 %V, i64* %P
%P2 = bitcast i64* %P to float*
%A = load float* %P2
ret float %A
; CHECK: @coerce_mustalias6
; CHECK-NOT: load
; CHECK: ret float
}
;; i64 -> i8* (32-bit) forwarding
define i8* @coerce_mustalias7(i64 %V, i64* %P) {
store i64 %V, i64* %P
%P2 = bitcast i64* %P to i8**
%A = load i8** %P2
ret i8* %A
; CHECK: @coerce_mustalias7
; CHECK-NOT: load
; CHECK: ret i8*
}
Handle forwarding local memsets to loads. For example, we optimize this: short x(short *A) { memset(A, 1, sizeof(*A)*100); return A[42]; } to 'return 257' instead of doing the load. llvm-svn: 90695
2009-12-06 09:57:02 +08:00
; memset -> i16 forwarding.
define signext i16 @memset_to_i16_local(i16* %A) nounwind ssp {
entry:
%conv = bitcast i16* %A to i8*
tail call void @llvm.memset.i64(i8* %conv, i8 1, i64 200, i32 1)
%arrayidx = getelementptr inbounds i16* %A, i64 42
%tmp2 = load i16* %arrayidx
ret i16 %tmp2
; CHECK: @memset_to_i16_local
; CHECK-NOT: load
; CHECK: ret i16 257
}
; memset -> float forwarding.
define float @memset_to_float_local(float* %A, i8 %Val) nounwind ssp {
entry:
%conv = bitcast float* %A to i8* ; <i8*> [#uses=1]
tail call void @llvm.memset.i64(i8* %conv, i8 %Val, i64 400, i32 1)
%arrayidx = getelementptr inbounds float* %A, i64 42 ; <float*> [#uses=1]
%tmp2 = load float* %arrayidx ; <float> [#uses=1]
ret float %tmp2
; CHECK: @memset_to_float_local
; CHECK-NOT: load
; CHECK: zext
; CHECK-NEXT: shl
; CHECK-NEXT: or
; CHECK-NEXT: shl
; CHECK-NEXT: or
; CHECK-NEXT: bitcast
; CHECK-NEXT: ret float
}
add support for forwarding mem intrinsic values to non-local loads. llvm-svn: 90697
2009-12-06 12:54:31 +08:00
;; non-local memset -> i16 load forwarding.
define i16 @memset_to_i16_nonlocal0(i16* %P, i1 %cond) {
%P3 = bitcast i16* %P to i8*
br i1 %cond, label %T, label %F
T:
tail call void @llvm.memset.i64(i8* %P3, i8 1, i64 400, i32 1)
br label %Cont
F:
tail call void @llvm.memset.i64(i8* %P3, i8 2, i64 400, i32 1)
br label %Cont
Cont:
%P2 = getelementptr i16* %P, i32 4
%A = load i16* %P2
ret i16 %A
; CHECK: @memset_to_i16_nonlocal0
; CHECK: Cont:
; CHECK-NEXT: %A = phi i16 [ 514, %F ], [ 257, %T ]
; CHECK-NOT: load
; CHECK: ret i16 %A
}
Handle forwarding local memsets to loads. For example, we optimize this: short x(short *A) { memset(A, 1, sizeof(*A)*100); return A[42]; } to 'return 257' instead of doing the load. llvm-svn: 90695
2009-12-06 09:57:02 +08:00
declare void @llvm.memset.i64(i8* nocapture, i8, i64, i32) nounwind
Move CoerceAvailableValueToLoadType earlier in GVN.cpp. Hook it up so that nonlocal and partially redundant loads can use it as well. The testcase shows examples of craziness this can handle. This triggers *many* times in 176.gcc. llvm-svn: 82403
2009-09-21 04:09:34 +08:00
;; non-local i32/float -> i8 load forwarding.
define i8 @coerce_mustalias_nonlocal0(i32* %P, i1 %cond) {
%P2 = bitcast i32* %P to float*
%P3 = bitcast i32* %P to i8*
br i1 %cond, label %T, label %F
T:
store i32 42, i32* %P
br label %Cont
F:
store float 1.0, float* %P2
br label %Cont
Cont:
%A = load i8* %P3
ret i8 %A
; CHECK: @coerce_mustalias_nonlocal0
; CHECK: Cont:
; CHECK: %A = phi i8 [
; CHECK-NOT: load
; CHECK: ret i8 %A
}
add support for forwarding mem intrinsic values to non-local loads. llvm-svn: 90697
2009-12-06 12:54:31 +08:00
Improve GVN to be able to forward substitute a small load from a piece of a large store when both are in the same block. This allows clang to compile the testcase in PR4216 to this code: _test_bitfield: movl 4(%esp), %eax movl %eax, %ecx andl $-65536, %ecx orl $32962, %eax andl $40186, %eax orl %ecx, %eax ret This is not ideal, but is a whole lot better than the code produced by llvm-gcc: _test_bitfield: movw $-32574, %ax orw 4(%esp), %ax andw $-25350, %ax movw %ax, 4(%esp) movw 7(%esp), %cx shlw $8, %cx movzbl 6(%esp), %edx orw %cx, %dx movzwl %dx, %ecx shll $16, %ecx movzwl %ax, %eax orl %ecx, %eax ret and dramatically better than that produced by gcc 4.2: _test_bitfield: pushl %ebx call L3 "L00000000001$pb": L3: popl %ebx movl 8(%esp), %eax leal 0(,%eax,4), %edx sarb $7, %dl movl %eax, %ecx andl $7168, %ecx andl $-7201, %ebx movzbl %dl, %edx andl $1, %edx sall $5, %edx orl %ecx, %ebx orl %edx, %ebx andl $24, %eax andl $-58336, %ebx orl %eax, %ebx orl $32962, %ebx movl %ebx, %eax popl %ebx ret llvm-svn: 82439
2009-09-21 13:57:11 +08:00
;; non-local i32/float -> i8 load forwarding. This also tests that the "P3"
;; bitcast equivalence can be properly phi translated.
define i8 @coerce_mustalias_nonlocal1(i32* %P, i1 %cond) {
%P2 = bitcast i32* %P to float*
br i1 %cond, label %T, label %F
T:
store i32 42, i32* %P
br label %Cont
F:
store float 1.0, float* %P2
br label %Cont
Cont:
%P3 = bitcast i32* %P to i8*
%A = load i8* %P3
ret i8 %A
;; FIXME: This is disabled because this caused a miscompile in the llvm-gcc
;; bootstrap, see r82411
;
; HECK: @coerce_mustalias_nonlocal1
; HECK: Cont:
; HECK: %A = phi i8 [
; HECK-NOT: load
; HECK: ret i8 %A
}
Move CoerceAvailableValueToLoadType earlier in GVN.cpp. Hook it up so that nonlocal and partially redundant loads can use it as well. The testcase shows examples of craziness this can handle. This triggers *many* times in 176.gcc. llvm-svn: 82403
2009-09-21 04:09:34 +08:00
;; non-local i32 -> i8 partial redundancy load forwarding.
define i8 @coerce_mustalias_pre0(i32* %P, i1 %cond) {
%P3 = bitcast i32* %P to i8*
br i1 %cond, label %T, label %F
T:
store i32 42, i32* %P
br label %Cont
F:
br label %Cont
Cont:
%A = load i8* %P3
ret i8 %A
; CHECK: @coerce_mustalias_pre0
; CHECK: F:
; CHECK: load i8* %P3
; CHECK: Cont:
; CHECK: %A = phi i8 [
; CHECK-NOT: load
; CHECK: ret i8 %A
}
Improve GVN to be able to forward substitute a small load from a piece of a large store when both are in the same block. This allows clang to compile the testcase in PR4216 to this code: _test_bitfield: movl 4(%esp), %eax movl %eax, %ecx andl $-65536, %ecx orl $32962, %eax andl $40186, %eax orl %ecx, %eax ret This is not ideal, but is a whole lot better than the code produced by llvm-gcc: _test_bitfield: movw $-32574, %ax orw 4(%esp), %ax andw $-25350, %ax movw %ax, 4(%esp) movw 7(%esp), %cx shlw $8, %cx movzbl 6(%esp), %edx orw %cx, %dx movzwl %dx, %ecx shll $16, %ecx movzwl %ax, %eax orl %ecx, %eax ret and dramatically better than that produced by gcc 4.2: _test_bitfield: pushl %ebx call L3 "L00000000001$pb": L3: popl %ebx movl 8(%esp), %eax leal 0(,%eax,4), %edx sarb $7, %dl movl %eax, %ecx andl $7168, %ecx andl $-7201, %ebx movzbl %dl, %edx andl $1, %edx sall $5, %edx orl %ecx, %ebx orl %edx, %ebx andl $24, %eax andl $-58336, %ebx orl %eax, %ebx orl $32962, %ebx movl %ebx, %eax popl %ebx ret llvm-svn: 82439
2009-09-21 13:57:11 +08:00
;;===----------------------------------------------------------------------===;;
;; Store -> Load and Load -> Load forwarding where src and dst are different
;; types, and the reload is an offset from the store pointer.
;;===----------------------------------------------------------------------===;;
enable non-local analysis and PRE of large store -> little load. This doesn't kick in too much because of phi translation issues, but this can be resolved in the future. llvm-svn: 82447
2009-09-21 14:48:08 +08:00
;; i32 -> i8 forwarding.
add pr# llvm-svn: 82440
2009-09-21 13:57:47 +08:00
;; PR4216
Improve GVN to be able to forward substitute a small load from a piece of a large store when both are in the same block. This allows clang to compile the testcase in PR4216 to this code: _test_bitfield: movl 4(%esp), %eax movl %eax, %ecx andl $-65536, %ecx orl $32962, %eax andl $40186, %eax orl %ecx, %eax ret This is not ideal, but is a whole lot better than the code produced by llvm-gcc: _test_bitfield: movw $-32574, %ax orw 4(%esp), %ax andw $-25350, %ax movw %ax, 4(%esp) movw 7(%esp), %cx shlw $8, %cx movzbl 6(%esp), %edx orw %cx, %dx movzwl %dx, %ecx shll $16, %ecx movzwl %ax, %eax orl %ecx, %eax ret and dramatically better than that produced by gcc 4.2: _test_bitfield: pushl %ebx call L3 "L00000000001$pb": L3: popl %ebx movl 8(%esp), %eax leal 0(,%eax,4), %edx sarb $7, %dl movl %eax, %ecx andl $7168, %ecx andl $-7201, %ebx movzbl %dl, %edx andl $1, %edx sall $5, %edx orl %ecx, %ebx orl %edx, %ebx andl $24, %eax andl $-58336, %ebx orl %eax, %ebx orl $32962, %ebx movl %ebx, %eax popl %ebx ret llvm-svn: 82439
2009-09-21 13:57:11 +08:00
define i8 @coerce_offset0(i32 %V, i32* %P) {
store i32 %V, i32* %P
%P2 = bitcast i32* %P to i8*
%P3 = getelementptr i8* %P2, i32 2
%A = load i8* %P3
ret i8 %A
; CHECK: @coerce_offset0
; CHECK-NOT: load
; CHECK: ret i8
}
enable non-local analysis and PRE of large store -> little load. This doesn't kick in too much because of phi translation issues, but this can be resolved in the future. llvm-svn: 82447
2009-09-21 14:48:08 +08:00
;; non-local i32/float -> i8 load forwarding.
define i8 @coerce_offset_nonlocal0(i32* %P, i1 %cond) {
%P2 = bitcast i32* %P to float*
%P3 = bitcast i32* %P to i8*
%P4 = getelementptr i8* %P3, i32 2
br i1 %cond, label %T, label %F
T:
store i32 42, i32* %P
br label %Cont
F:
store float 1.0, float* %P2
br label %Cont
Cont:
%A = load i8* %P4
ret i8 %A
; CHECK: @coerce_offset_nonlocal0
; CHECK: Cont:
; CHECK: %A = phi i8 [
; CHECK-NOT: load
; CHECK: ret i8 %A
}
;; non-local i32 -> i8 partial redundancy load forwarding.
define i8 @coerce_offset_pre0(i32* %P, i1 %cond) {
%P3 = bitcast i32* %P to i8*
%P4 = getelementptr i8* %P3, i32 2
br i1 %cond, label %T, label %F
T:
store i32 42, i32* %P
br label %Cont
F:
br label %Cont
Cont:
%A = load i8* %P4
ret i8 %A
; CHECK: @coerce_offset_pre0
; CHECK: F:
; CHECK: load i8* %P4
; CHECK: Cont:
; CHECK: %A = phi i8 [
; CHECK-NOT: load
; CHECK: ret i8 %A
}
Improve GVN to be able to forward substitute a small load from a piece of a large store when both are in the same block. This allows clang to compile the testcase in PR4216 to this code: _test_bitfield: movl 4(%esp), %eax movl %eax, %ecx andl $-65536, %ecx orl $32962, %eax andl $40186, %eax orl %ecx, %eax ret This is not ideal, but is a whole lot better than the code produced by llvm-gcc: _test_bitfield: movw $-32574, %ax orw 4(%esp), %ax andw $-25350, %ax movw %ax, 4(%esp) movw 7(%esp), %cx shlw $8, %cx movzbl 6(%esp), %edx orw %cx, %dx movzwl %dx, %ecx shll $16, %ecx movzwl %ax, %eax orl %ecx, %eax ret and dramatically better than that produced by gcc 4.2: _test_bitfield: pushl %ebx call L3 "L00000000001$pb": L3: popl %ebx movl 8(%esp), %eax leal 0(,%eax,4), %edx sarb $7, %dl movl %eax, %ecx andl $7168, %ecx andl $-7201, %ebx movzbl %dl, %edx andl $1, %edx sall $5, %edx orl %ecx, %ebx orl %edx, %ebx andl $24, %eax andl $-58336, %ebx orl %eax, %ebx orl $32962, %ebx movl %ebx, %eax popl %ebx ret llvm-svn: 82439
2009-09-21 13:57:11 +08:00
merge two tests. llvm-svn: 90691
2009-12-06 09:47:24 +08:00
define i32 @chained_load(i32** %p) {
block1:
%z = load i32** %p
br i1 true, label %block2, label %block3
block2:
%a = load i32** %p
br label %block4
block3:
%b = load i32** %p
br label %block4
block4:
%c = load i32** %p
%d = load i32* %c
ret i32 %d
; CHECK: @chained_load
; CHECK: %z = load i32** %p
; CHECK-NOT: load
; CHECK: %d = load i32* %z
; CHECK-NEXT: ret i32 %d
}
Improve GVN to be able to forward substitute a small load from a piece of a large store when both are in the same block. This allows clang to compile the testcase in PR4216 to this code: _test_bitfield: movl 4(%esp), %eax movl %eax, %ecx andl $-65536, %ecx orl $32962, %eax andl $40186, %eax orl %ecx, %eax ret This is not ideal, but is a whole lot better than the code produced by llvm-gcc: _test_bitfield: movw $-32574, %ax orw 4(%esp), %ax andw $-25350, %ax movw %ax, 4(%esp) movw 7(%esp), %cx shlw $8, %cx movzbl 6(%esp), %edx orw %cx, %dx movzwl %dx, %ecx shll $16, %ecx movzwl %ax, %eax orl %ecx, %eax ret and dramatically better than that produced by gcc 4.2: _test_bitfield: pushl %ebx call L3 "L00000000001$pb": L3: popl %ebx movl 8(%esp), %eax leal 0(,%eax,4), %edx sarb $7, %dl movl %eax, %ecx andl $7168, %ecx andl $-7201, %ebx movzbl %dl, %edx andl $1, %edx sall $5, %edx orl %ecx, %ebx orl %edx, %ebx andl $24, %eax andl $-58336, %ebx orl %eax, %ebx orl $32962, %ebx movl %ebx, %eax popl %ebx ret llvm-svn: 82439
2009-09-21 13:57:11 +08:00
Small and carefully crafted testcase showing a miscompilation by GVN that I'm working on. This is manifesting as a miscompile of 255.vortex on some targets. No check lines yet because it fails. llvm-svn: 90520
2009-12-04 10:12:12 +08:00
declare i1 @cond() readonly
declare i1 @cond2() readonly
define i32 @phi_trans2() {
entry:
%P = alloca i32, i32 400
br label %F1
F1:
%A = phi i32 [1, %entry], [2, %F]
%cond2 = call i1 @cond()
br i1 %cond2, label %T1, label %TY
T1:
%P2 = getelementptr i32* %P, i32 %A
%x = load i32* %P2
%cond = call i1 @cond2()
br i1 %cond, label %TX, label %F
F:
%P3 = getelementptr i32* %P, i32 2
store i32 17, i32* %P3
store i32 42, i32* %P2 ; Provides "P[A]".
br label %F1
TX:
ret i32 %x ;; SHOULD NOT BE COMPILED TO 'ret i32 42'.
TY:
ret i32 0
}