-- C.4 and C.5 statements, when NSAA is not equal to SP.
-- C.1.cp statement for VA functions. Note: There are no VFP CPRCs in a
variadic procedure.
Before this patch "NSAA != 0" means "don't use GPRs anymore ". But there are
some exceptions in AAPCS.
1. For non VA function: allocate all VFP regs for CPRC. When all VFPs are allocated
CPRCs would be sent to stack, while non CPRCs may be still allocated in GRPs.
2. Check that for VA functions all params uses GPRs and then stack.
No exceptions, no CPRCs here.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180011 91177308-0d34-0410-b5e6-96231b3b80d8
This reverts commit r179840 with a fix to test/DebugInfo/two-cus-from-same-file.ll
I'm not sure why that test only failed on ARM & MIPS and not X86 Linux, even
though the debug info was clearly invalid on all of them, but this ought to fix
it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179996 91177308-0d34-0410-b5e6-96231b3b80d8
Rather than just splitting the input type and hoping for the best, apply
a bit more cleverness. Just splitting the types until the source is
legal often leads to an illegal result time, which is then widened and a
scalarization step is introduced which leads to truly horrible code
generation. With the loop vectorizer, these sorts of operations are much
more common, and so it's worth extra effort to do them well.
Add a legalization hook for the operands of a TRUNCATE node, which will
be encountered after the result type has been legalized, but if the
operand type is still illegal. If simple splitting of both types
ends up with the result type of each half still being legal, just
do that (v16i16 -> v16i8 on ARM, for example). If, however, that would
result in an illegal result type (v8i32 -> v8i8 on ARM, for example),
we can get more clever with power-two vectors. Specifically,
split the input type, but also widen the result element size, then
concatenate the halves and truncate again. For example on ARM,
To perform a "%res = v8i8 trunc v8i32 %in" we transform to:
%inlo = v4i32 extract_subvector %in, 0
%inhi = v4i32 extract_subvector %in, 4
%lo16 = v4i16 trunc v4i32 %inlo
%hi16 = v4i16 trunc v4i32 %inhi
%in16 = v8i16 concat_vectors v4i16 %lo16, v4i16 %hi16
%res = v8i8 trunc v8i16 %in16
This allows instruction selection to generate three VMOVN instructions
instead of a sequences of moves, stores and loads.
Update the ARMTargetTransformInfo to take this improved legalization
into account.
Consider the simplified IR:
define <16 x i8> @test1(<16 x i32>* %ap) {
%a = load <16 x i32>* %ap
%tmp = trunc <16 x i32> %a to <16 x i8>
ret <16 x i8> %tmp
}
define <8 x i8> @test2(<8 x i32>* %ap) {
%a = load <8 x i32>* %ap
%tmp = trunc <8 x i32> %a to <8 x i8>
ret <8 x i8> %tmp
}
Previously, we would generate the truly hideous:
.syntax unified
.section __TEXT,__text,regular,pure_instructions
.globl _test1
.align 2
_test1: @ @test1
@ BB#0:
push {r7}
mov r7, sp
sub sp, sp, #20
bic sp, sp, #7
add r1, r0, #48
add r2, r0, #32
vld1.64 {d24, d25}, [r0:128]
vld1.64 {d16, d17}, [r1:128]
vld1.64 {d18, d19}, [r2:128]
add r1, r0, #16
vmovn.i32 d22, q8
vld1.64 {d16, d17}, [r1:128]
vmovn.i32 d20, q9
vmovn.i32 d18, q12
vmov.u16 r0, d22[3]
strb r0, [sp, #15]
vmov.u16 r0, d22[2]
strb r0, [sp, #14]
vmov.u16 r0, d22[1]
strb r0, [sp, #13]
vmov.u16 r0, d22[0]
vmovn.i32 d16, q8
strb r0, [sp, #12]
vmov.u16 r0, d20[3]
strb r0, [sp, #11]
vmov.u16 r0, d20[2]
strb r0, [sp, #10]
vmov.u16 r0, d20[1]
strb r0, [sp, #9]
vmov.u16 r0, d20[0]
strb r0, [sp, #8]
vmov.u16 r0, d18[3]
strb r0, [sp, #3]
vmov.u16 r0, d18[2]
strb r0, [sp, #2]
vmov.u16 r0, d18[1]
strb r0, [sp, #1]
vmov.u16 r0, d18[0]
strb r0, [sp]
vmov.u16 r0, d16[3]
strb r0, [sp, #7]
vmov.u16 r0, d16[2]
strb r0, [sp, #6]
vmov.u16 r0, d16[1]
strb r0, [sp, #5]
vmov.u16 r0, d16[0]
strb r0, [sp, #4]
vldmia sp, {d16, d17}
vmov r0, r1, d16
vmov r2, r3, d17
mov sp, r7
pop {r7}
bx lr
.globl _test2
.align 2
_test2: @ @test2
@ BB#0:
push {r7}
mov r7, sp
sub sp, sp, #12
bic sp, sp, #7
vld1.64 {d16, d17}, [r0:128]
add r0, r0, #16
vld1.64 {d20, d21}, [r0:128]
vmovn.i32 d18, q8
vmov.u16 r0, d18[3]
vmovn.i32 d16, q10
strb r0, [sp, #3]
vmov.u16 r0, d18[2]
strb r0, [sp, #2]
vmov.u16 r0, d18[1]
strb r0, [sp, #1]
vmov.u16 r0, d18[0]
strb r0, [sp]
vmov.u16 r0, d16[3]
strb r0, [sp, #7]
vmov.u16 r0, d16[2]
strb r0, [sp, #6]
vmov.u16 r0, d16[1]
strb r0, [sp, #5]
vmov.u16 r0, d16[0]
strb r0, [sp, #4]
ldm sp, {r0, r1}
mov sp, r7
pop {r7}
bx lr
Now, however, we generate the much more straightforward:
.syntax unified
.section __TEXT,__text,regular,pure_instructions
.globl _test1
.align 2
_test1: @ @test1
@ BB#0:
add r1, r0, #48
add r2, r0, #32
vld1.64 {d20, d21}, [r0:128]
vld1.64 {d16, d17}, [r1:128]
add r1, r0, #16
vld1.64 {d18, d19}, [r2:128]
vld1.64 {d22, d23}, [r1:128]
vmovn.i32 d17, q8
vmovn.i32 d16, q9
vmovn.i32 d18, q10
vmovn.i32 d19, q11
vmovn.i16 d17, q8
vmovn.i16 d16, q9
vmov r0, r1, d16
vmov r2, r3, d17
bx lr
.globl _test2
.align 2
_test2: @ @test2
@ BB#0:
vld1.64 {d16, d17}, [r0:128]
add r0, r0, #16
vld1.64 {d18, d19}, [r0:128]
vmovn.i32 d16, q8
vmovn.i32 d17, q9
vmovn.i16 d16, q8
vmov r0, r1, d16
bx lr
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179989 91177308-0d34-0410-b5e6-96231b3b80d8
With a little help from the frontend, it looks like the standard va_*
intrinsics can do the job.
Also clean up an old bitcast hack in LowerVAARG that dealt with
unaligned double loads. Load SDNodes can specify an alignment now.
Still missing: Calling varargs functions with float arguments.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179961 91177308-0d34-0410-b5e6-96231b3b80d8
Previously, when spilling 64-bit paired registers, an LDMIA with both
a FrameIndex and an offset was produced. This kind of instruction
shouldn't exist, and the extra operand was being confused with the
predicate, causing aborts later on.
This removes the invalid 0-offset from the instruction being
produced.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179956 91177308-0d34-0410-b5e6-96231b3b80d8
When matching a compare with a subtract where the arguments of the compare are
swapped w.r.t. the arguments of the subtract, we need to negate the predicates
(or CR bit indices) of the users. This, however, is not the same as inverting
the predicate (negating LT -> GT, but inverting LT -> GE, for example). The ARM
backend seems to do this correctly, but when I adapted the code for the PPC
backend, I introduced an error in this logic.
Comparison optimization is now enabled again by default.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179899 91177308-0d34-0410-b5e6-96231b3b80d8
Adding another CU-wide list, in this case of imported_modules (since they
should be relatively rare, it seemed better to add a list where each element
had a "context" value, rather than add a (usually empty) list to every scope).
This takes care of DW_TAG_imported_module, but to fully address PR14606 we'll
need to expand this to cover DW_TAG_imported_declaration too.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179836 91177308-0d34-0410-b5e6-96231b3b80d8
This seems to cause a stage-2 LLVM compile failure (by crashing TableGen); do
I'm disabling this for now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179807 91177308-0d34-0410-b5e6-96231b3b80d8
Many PPC instructions have a so-called 'record form' which stores to a specific
condition register the result of comparing the result of the instruction with
zero (always as a signed comparison). For integer operations on PPC64, this is
always a 64-bit comparison.
This implementation is derived from the implementation in the ARM backend;
there are some differences because PPC condition registers are allocatable
virtual registers (although the record forms always use a specific one), and we
look for a matching subtraction instruction after the compare (but before the
first use) in addition to before it.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179802 91177308-0d34-0410-b5e6-96231b3b80d8
In X86FastISel::X86SelectStore(), improperly aligned stores are rejected and
handled by the DAG-based ISel. However, X86FastISel::X86SelectLoad() makes
no such requirement. There doesn't appear to be an x86 architectural
correctness issue with allowing potentially unaligned store instructions.
This patch removes this restriction.
Patch by Jim Stichnot.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179774 91177308-0d34-0410-b5e6-96231b3b80d8
for the sdiv/srem/udiv/urem bitcode instructions. This is done for the i8,
i16, and i32 types, as well as i64 for the x86_64 target.
Patch by Jim Stichnoth
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179715 91177308-0d34-0410-b5e6-96231b3b80d8
Instead of emitting config values in a predefined order, the code
emitter will now emit a 32-bit register index followed by the 32-bit
config value.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179546 91177308-0d34-0410-b5e6-96231b3b80d8
This fixes an ABI bug for non-Darwin PPC64. For the callee-saved condition
registers, the spill location is specified relative to the stack pointer (SP +
8). However, this is not relative to the SP after the new stack frame is
established, but instead relative to the caller's stack pointer (it is stored
into the linkage area of the parent's stack frame).
So, like with the link register, we don't directly spill the CRs with other
callee-saved registers, but just mark them to be spilled during prologue
generation.
In practice, this reverts r179457 for PPC64 (but leaves it in place for PPC32).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179500 91177308-0d34-0410-b5e6-96231b3b80d8
This is the default model for non-PIC 64-bit code. It supports
text+data+bss linked anywhere in the low 16 TB of the address space.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179473 91177308-0d34-0410-b5e6-96231b3b80d8
Currently, only abs32 and pic32 are implemented. Add a test case for
abs32 with 64-bit code. 64-bit PIC code is currently broken.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179463 91177308-0d34-0410-b5e6-96231b3b80d8