Age | Commit message (Collapse) | Author |
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22828 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Nate noticed in yacr2 (and I know occurs in other places as well).
This is still rough, as the critical edge blocks are not intelligently placed
but is added to get some idea to see if this improves performance.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22825 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22822 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
legalizer. PowerPC now uses this expansion instead of ISel version.
Example:
// signed integer to double conversion
double f1(signed x) {
return (double)x;
}
// unsigned integer to double conversion
double f2(unsigned x) {
return (double)x;
}
// signed integer to float conversion
float f3(signed x) {
return (float)x;
}
// unsigned integer to float conversion
float f4(unsigned x) {
return (float)x;
}
Byte Code:
internal fastcc double %_Z2f1i(int %x) {
entry:
%tmp.1 = cast int %x to double ; <double> [#uses=1]
ret double %tmp.1
}
internal fastcc double %_Z2f2j(uint %x) {
entry:
%tmp.1 = cast uint %x to double ; <double> [#uses=1]
ret double %tmp.1
}
internal fastcc float %_Z2f3i(int %x) {
entry:
%tmp.1 = cast int %x to float ; <float> [#uses=1]
ret float %tmp.1
}
internal fastcc float %_Z2f4j(uint %x) {
entry:
%tmp.1 = cast uint %x to float ; <float> [#uses=1]
ret float %tmp.1
}
internal fastcc double %_Z2g1i(int %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.2 = cast int %x to uint ; <uint> [#uses=1]
%tmp.3 = xor uint %tmp.2, 2147483648 ; <uint> [#uses=1]
%tmp.5 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %tmp.3, uint* %tmp.5
%tmp.9 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.10 = load double* %tmp.9 ; <double> [#uses=1]
%tmp.13 = load double* cast (long* %signed_bias to double*) ; <double> [#uses=1]
%tmp.14 = sub double %tmp.10, %tmp.13 ; <double> [#uses=1]
ret double %tmp.14
}
internal fastcc double %_Z2g2j(uint %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.1 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %x, uint* %tmp.1
%tmp.4 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.5 = load double* %tmp.4 ; <double> [#uses=1]
%tmp.8 = load double* cast (long* %unsigned_bias to double*) ; <double> [#uses=1]
%tmp.9 = sub double %tmp.5, %tmp.8 ; <double> [#uses=1]
ret double %tmp.9
}
internal fastcc float %_Z2g3i(int %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.2 = cast int %x to uint ; <uint> [#uses=1]
%tmp.3 = xor uint %tmp.2, 2147483648 ; <uint> [#uses=1]
%tmp.5 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %tmp.3, uint* %tmp.5
%tmp.9 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.10 = load double* %tmp.9 ; <double> [#uses=1]
%tmp.13 = load double* cast (long* %signed_bias to double*) ; <double> [#uses=1]
%tmp.14 = sub double %tmp.10, %tmp.13 ; <double> [#uses=1]
%tmp.16 = cast double %tmp.14 to float ; <float> [#uses=1]
ret float %tmp.16
}
internal fastcc float %_Z2g4j(uint %x) {
entry:
%buffer = alloca [2 x uint] ; <[2 x uint]*> [#uses=3]
%tmp.0 = getelementptr [2 x uint]* %buffer, int 0, int 0 ; <uint*> [#uses=1]
store uint 1127219200, uint* %tmp.0
%tmp.1 = getelementptr [2 x uint]* %buffer, int 0, int 1 ; <uint*> [#uses=1]
store uint %x, uint* %tmp.1
%tmp.4 = cast [2 x uint]* %buffer to double* ; <double*> [#uses=1]
%tmp.5 = load double* %tmp.4 ; <double> [#uses=1]
%tmp.8 = load double* cast (long* %unsigned_bias to double*) ; <double> [#uses=1]
%tmp.9 = sub double %tmp.5, %tmp.8 ; <double> [#uses=1]
%tmp.11 = cast double %tmp.9 to float ; <float> [#uses=1]
ret float %tmp.11
}
PowerPC Code:
.machine ppc970
.const
.align 2
.CPIl1__Z2f1i_0: ; float 0x4330000080000000
.long 1501560836 ; float 4.5036e+15
.text
.align 2
.globl l1__Z2f1i
l1__Z2f1i:
.LBBl1__Z2f1i_0: ; entry
xoris r2, r3, 32768
stw r2, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl1__Z2f1i_0)
lfs f1, lo16(.CPIl1__Z2f1i_0)(r2)
fsub f1, f0, f1
blr
.const
.align 2
.CPIl2__Z2f2j_0: ; float 0x4330000000000000
.long 1501560832 ; float 4.5036e+15
.text
.align 2
.globl l2__Z2f2j
l2__Z2f2j:
.LBBl2__Z2f2j_0: ; entry
stw r3, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl2__Z2f2j_0)
lfs f1, lo16(.CPIl2__Z2f2j_0)(r2)
fsub f1, f0, f1
blr
.const
.align 2
.CPIl3__Z2f3i_0: ; float 0x4330000080000000
.long 1501560836 ; float 4.5036e+15
.text
.align 2
.globl l3__Z2f3i
l3__Z2f3i:
.LBBl3__Z2f3i_0: ; entry
xoris r2, r3, 32768
stw r2, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl3__Z2f3i_0)
lfs f1, lo16(.CPIl3__Z2f3i_0)(r2)
fsub f0, f0, f1
frsp f1, f0
blr
.const
.align 2
.CPIl4__Z2f4j_0: ; float 0x4330000000000000
.long 1501560832 ; float 4.5036e+15
.text
.align 2
.globl l4__Z2f4j
l4__Z2f4j:
.LBBl4__Z2f4j_0: ; entry
stw r3, -4(r1)
lis r2, 17200
stw r2, -8(r1)
lfd f0, -8(r1)
lis r2, ha16(.CPIl4__Z2f4j_0)
lfs f1, lo16(.CPIl4__Z2f4j_0)(r2)
fsub f0, f0, f1
frsp f1, f0
blr
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22814 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22813 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
used to tack a register number onto the node.
Instead of doing this, make a new node, RegisterSDNode, which is a leaf
containing a register number. These three operations just become normal
DAG nodes now, instead of requiring special handling.
Note that with this change, it is no longer correct to make illegal
CopyFromReg/CopyToReg nodes. The legalizer will not touch them, and this
is bad, so don't do it. :)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22806 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
fixme from the PowerPC backend. Emit slightly better code for legalizing
select_cc.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22805 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
when printing a node, use it to render target operations with their
target instruction name instead of "<<unknown>>".
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22804 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22802 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Split RemoveNodeFromCSEMaps out of DeleteNodesIfDead to do it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22801 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
1. Not selecting the false value of a select_cc in the false arm, which
isn't legal for nested selects.
2. Actually returning the node we created and Legalized in the FP_TO_UINT
Expander.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22789 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Teach the legalizer to promote FP_TO_UINT to FP_TO_SINT if the wider
FP_TO_UINT is also illegal. This allows us on PPC to codegen
unsigned short foo(float a) { return a; }
as:
_foo:
.LBB_foo_0: ; entry
fctiwz f0, f1
stfd f0, -8(r1)
lwz r2, -4(r1)
rlwinm r3, r2, 0, 16, 31
blr
instead of:
_foo:
.LBB_foo_0: ; entry
fctiwz f0, f1
stfd f0, -8(r1)
lwz r2, -4(r1)
lis r3, ha16(.CPI_foo_0)
lfs f0, lo16(.CPI_foo_0)(r3)
fcmpu cr0, f1, f0
blt .LBB_foo_2 ; entry
.LBB_foo_1: ; entry
fsubs f0, f1, f0
fctiwz f0, f0
stfd f0, -16(r1)
lwz r2, -12(r1)
xoris r2, r2, 32768
.LBB_foo_2: ; entry
rlwinm r3, r2, 0, 16, 31
blr
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22785 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
assert when creating a select_cc node.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22780 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
out into SimplifySelectCC. This allows both ISD::SELECT and ISD::SELECT_CC
to use the same set of simplifying folds.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22779 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
e.g. (X & 7) >> 3 -> 0
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22774 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
integer MPEG encoding loop by a factor of two.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22758 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
1. move assertions for node creation to getNode()
2. legalize the values returned in ExpandOp immediately
3. Move select_cc optimizations from SELECT's getNode() to SELECT_CC's,
allowing them to be cleaned up significantly.
This paves the way to pick up additional optimizations on SELECT_CC, such
as sum-of-absolute-differences.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22757 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
implement SELECT.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22755 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22753 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22734 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22731 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
CC out of the SetCC operation, making SETCC a standard ternary operation and
CC's a standard DAG leaf. This will make it possible for other node to use
CC's as operands in the future...
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22728 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22696 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22691 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
avoid revisiting nodes more than once. This eliminates a source of
potentially exponential behavior. For a small function in 191.fma3d
(hexah_stress_divergence_), this speeds up isel from taking > 20mins to
taking 0.07s.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22680 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22679 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
yesterday. This fixes whetstone and a bunch of programs in the External tests.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22678 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22661 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
* Add comments to #endif pragmas for readability
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22647 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
the sequence used for integer ops
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22629 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
Patch contributed by Jim Laskey!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22594 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22570 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22565 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22563 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
both the src and dest values are legal
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22555 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22548 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
a larger integer destination.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22547 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
subcases inside, break things out earlier.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22546 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22542 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22529 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22528 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22523 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22469 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This is the first incremental patch to implement this feature. It adds no
functionality to LLVM but setup up the information needed from targets in
order to implement the optimization correctly. Each target needs to specify
the maximum number of store operations for conversion of the llvm.memset,
llvm.memcpy, and llvm.memmove intrinsics into a sequence of store operations.
The limit needs to be chosen at the threshold of performance for such an
optimization (generally smallish). The target also needs to specify whether
the target can support unaligned stores for multi-byte store operations.
This helps ensure the optimization doesn't generate code that will trap on
an alignment errors.
More patches to follow.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22468 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
expand the code to work for all integer datatypes. This should unbreak
alpha.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22464 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
This allows is to not emit empty sections when .data or .bss is not used.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22457 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22455 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
vector that represents the .o file at once, build up a vector for each
section of the .o file. This is needed because the .o file writer needs
to be able to switch between sections as it emits them (e.g. switch
between the .text section and the .rel section when emitting code).
This patch has no functionality change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22453 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
the target natively supports. This eliminates some special-case code from
the x86 backend and generates better code as well.
For an i8 to f64 conversion, before & after:
_x87 before:
subl $2, %esp
movb 6(%esp), %al
movsbw %al, %ax
movw %ax, (%esp)
filds (%esp)
addl $2, %esp
ret
_x87 after:
subl $2, %esp
movsbw 6(%esp), %ax
movw %ax, (%esp)
filds (%esp)
addl $2, %esp
ret
_sse before:
subl $12, %esp
movb 16(%esp), %al
movsbl %al, %eax
cvtsi2sd %eax, %xmm0
addl $12, %esp
ret
_sse after:
subl $12, %esp
movsbl 16(%esp), %eax
cvtsi2sd %eax, %xmm0
addl $12, %esp
ret
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22452 91177308-0d34-0410-b5e6-96231b3b80d8
|
|
SelectionDAGLegalize::ExpandLegalUINT_TO_FP method.
Add a new method, PromoteLegalUINT_TO_FP, which allows targets to request
that UINT_TO_FP operations be promoted to a larger input type. This is
useful for targets that have some UINT_TO_FP or SINT_TO_FP operations but
not all of them (like X86).
The same should be done with SINT_TO_FP, but this patch does not do that
yet.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@22447 91177308-0d34-0410-b5e6-96231b3b80d8
|