6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2024-09-02 11:30:10 +00:00
Code Issues Projects Releases Wiki Activity
beac0c1403
llvm-6502/test/CodeGen/PowerPC/ppc64le-aggregates.ll
Ulrich Weigand d4542a8cdc [PowerPC] ELFv2 aggregate passing support 
This patch adds infrastructure support for passing array types
directly.  These can be used by the front-end to pass aggregate
types (coerced to an appropriate array type).  The details of the
array type being used inform the back-end about ABI-relevant
properties.  Specifically, the array element type encodes:
- whether the parameter should be passed in FPRs, VRs, or just
  GPRs/stack slots  (for float / vector / integer element types,
  respectively)
- what the alignment requirements of the parameter are when passed in
  GPRs/stack slots  (8 for float / 16 for vector / the element type
  size for integer element types) -- this corresponds to the
  "byval align" field

Using the infrastructure provided by this patch, a companion patch
to clang will enable two features:
- In the ELFv2 ABI, pass (and return) "homogeneous" floating-point
  or vector aggregates in FPRs and VRs (this is similar to the ARM
  homogeneous aggregate ABI)
- As an optimization for both ELFv1 and ELFv2 ABIs, pass aggregates
  that fit fully in registers without using the "byval" mechanism

The patch uses the functionArgumentNeedsConsecutiveRegisters callback
to encode that special treatment is required for all directly-passed
array types.  The isInConsecutiveRegs / isInConsecutiveRegsLast bits set
as a results are then used to implement the required size and alignment
rules in CalculateStackSlotSize / CalculateStackSlotAlignment etc.

As a related change, the ABI routines have to be modified to support
passing floating-point types in GPRs.  This is necessary because with
homogeneous aggregates of 4-byte float type we can now run out of FPRs
*before* we run out of the 64-byte argument save area that is shadowed
by GPRs.  Any extra floating-point arguments that no longer fit in FPRs
must now be passed in GPRs until we run out of those too.

Note that there was already code to pass floating-point arguments in
GPRs used with vararg parameters, which was done by writing the argument
out to the argument save area first and then reloading into GPRs.  The
patch re-implements this, however, in favor of code packing float arguments
directly via extension/truncation, BITCAST, and BUILD_PAIR operations.

This is required to support the ELFv2 ABI, since we cannot unconditionally
write to the argument save area (which the caller might not have allocated).
The change does, however, affect ELFv1 varags routines too; but even here
the overall effect should be advantageous: Instead of loading the argument
into the FPR, then storing the argument to the stack slot, and finally
reloading the argument from the stack slot into a GPR, the new code now
just loads the argument into the FPR, and subsequently loads the argument
into the GPR (via BITCAST).  That BITCAST might imply a save/reload from
a stack temporary (in which case we're no worse than before); but it
might be implemented more efficiently in some cases.

The final part of the patch enables up to 8 FPRs and VRs for argument
return in PPCCallingConv.td; this is required to support returning
ELFv2 homogeneous aggregates.  (Note that this doesn't affect other ABIs
since LLVM wil only look for which register to use if the parameter is
marked as "direct" return anyway.)

Reviewed by Hal Finkel.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@213493 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-21 00:13:26 +00:00

330 lines
8.1 KiB
LLVM
Raw Blame History

; RUN: llc < %s -march=ppc64le -mcpu=pwr8 -mattr=+altivec | FileCheck %s
target datalayout = "e-m:e-i64:64-n32:64"
target triple = "powerpc64le-unknown-linux-gnu"
;
; Verify use of registers for float/vector aggregate return.
;
define [8 x float] @return_float([8 x float] %x) {
entry:
ret [8 x float] %x
}
; CHECK-LABEL: @return_float
; CHECK: %entry
; CHECK-NEXT: blr
define [8 x double] @return_double([8 x double] %x) {
entry:
ret [8 x double] %x
}
; CHECK-LABEL: @return_double
; CHECK: %entry
; CHECK-NEXT: blr
define [4 x ppc_fp128] @return_ppcf128([4 x ppc_fp128] %x) {
entry:
ret [4 x ppc_fp128] %x
}
; CHECK-LABEL: @return_ppcf128
; CHECK: %entry
; CHECK-NEXT: blr
define [8 x <4 x i32>] @return_v4i32([8 x <4 x i32>] %x) {
entry:
ret [8 x <4 x i32>] %x
}
; CHECK-LABEL: @return_v4i32
; CHECK: %entry
; CHECK-NEXT: blr
;
; Verify amount of space taken up by aggregates in the parameter save area.
;
define i64 @callee_float([7 x float] %a, [7 x float] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_float
; CHECK: ld 3, 96(1)
; CHECK: blr
define void @caller_float(i64 %x, [7 x float] %y) {
entry:
tail call void @test_float([7 x float] %y, [7 x float] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_float
; CHECK: std 3, 96(1)
; CHECK: bl test_float
declare void @test_float([7 x float], [7 x float], i64)
define i64 @callee_double(i64 %a, [7 x double] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_double
; CHECK: ld 3, 96(1)
; CHECK: blr
define void @caller_double(i64 %x, [7 x double] %y) {
entry:
tail call void @test_double(i64 %x, [7 x double] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_double
; CHECK: std 3, 96(1)
; CHECK: bl test_double
declare void @test_double(i64, [7 x double], i64)
define i64 @callee_ppcf128(i64 %a, [4 x ppc_fp128] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_ppcf128
; CHECK: ld 3, 104(1)
; CHECK: blr
define void @caller_ppcf128(i64 %x, [4 x ppc_fp128] %y) {
entry:
tail call void @test_ppcf128(i64 %x, [4 x ppc_fp128] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_ppcf128
; CHECK: std 3, 104(1)
; CHECK: bl test_ppcf128
declare void @test_ppcf128(i64, [4 x ppc_fp128], i64)
define i64 @callee_i64(i64 %a, [7 x i64] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_i64
; CHECK: ld 3, 96(1)
; CHECK: blr
define void @caller_i64(i64 %x, [7 x i64] %y) {
entry:
tail call void @test_i64(i64 %x, [7 x i64] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_i64
; CHECK: std 3, 96(1)
; CHECK: bl test_i64
declare void @test_i64(i64, [7 x i64], i64)
define i64 @callee_i128(i64 %a, [4 x i128] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_i128
; CHECK: ld 3, 112(1)
; CHECK: blr
define void @caller_i128(i64 %x, [4 x i128] %y) {
entry:
tail call void @test_i128(i64 %x, [4 x i128] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_i128
; CHECK: std 3, 112(1)
; CHECK: bl test_i128
declare void @test_i128(i64, [4 x i128], i64)
define i64 @callee_v4i32(i64 %a, [4 x <4 x i32>] %b, i64 %c) {
entry:
ret i64 %c
}
; CHECK-LABEL: @callee_v4i32
; CHECK: ld 3, 112(1)
; CHECK: blr
define void @caller_v4i32(i64 %x, [4 x <4 x i32>] %y) {
entry:
tail call void @test_v4i32(i64 %x, [4 x <4 x i32>] %y, i64 %x)
ret void
}
; CHECK-LABEL: @caller_v4i32
; CHECK: std 3, 112(1)
; CHECK: bl test_v4i32
declare void @test_v4i32(i64, [4 x <4 x i32>], i64)
;
; Verify handling of floating point arguments in GPRs
;
%struct.float8 = type { [8 x float] }
%struct.float5 = type { [5 x float] }
%struct.float2 = type { [2 x float] }
@g8 = common global %struct.float8 zeroinitializer, align 4
@g5 = common global %struct.float5 zeroinitializer, align 4
@g2 = common global %struct.float2 zeroinitializer, align 4
define float @callee0([7 x float] %a, [7 x float] %b) {
entry:
%b.extract = extractvalue [7 x float] %b, 6
ret float %b.extract
}
; CHECK-LABEL: @callee0
; CHECK: stw 10, [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller0([7 x float] %a) {
entry:
tail call void @test0([7 x float] %a, [7 x float] %a)
ret void
}
; CHECK-LABEL: @caller0
; CHECK-DAG: fmr 8, 1
; CHECK-DAG: fmr 9, 2
; CHECK-DAG: fmr 10, 3
; CHECK-DAG: fmr 11, 4
; CHECK-DAG: fmr 12, 5
; CHECK-DAG: fmr 13, 6
; CHECK-DAG: stfs 7, [[OFF:[0-9]+]](1)
; CHECK-DAG: lwz 10, [[OFF]](1)
; CHECK: bl test0
declare void @test0([7 x float], [7 x float])
define float @callee1([8 x float] %a, [8 x float] %b) {
entry:
%b.extract = extractvalue [8 x float] %b, 7
ret float %b.extract
}
; CHECK-LABEL: @callee1
; CHECK: rldicl [[REG:[0-9]+]], 10, 32, 32
; CHECK: stw [[REG]], [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller1([8 x float] %a) {
entry:
tail call void @test1([8 x float] %a, [8 x float] %a)
ret void
}
; CHECK-LABEL: @caller1
; CHECK-DAG: fmr 9, 1
; CHECK-DAG: fmr 10, 2
; CHECK-DAG: fmr 11, 3
; CHECK-DAG: fmr 12, 4
; CHECK-DAG: fmr 13, 5
; CHECK-DAG: stfs 5, [[OFF0:[0-9]+]](1)
; CHECK-DAG: stfs 6, [[OFF1:[0-9]+]](1)
; CHECK-DAG: stfs 7, [[OFF2:[0-9]+]](1)
; CHECK-DAG: stfs 8, [[OFF3:[0-9]+]](1)
; CHECK-DAG: lwz [[REG0:[0-9]+]], [[OFF0]](1)
; CHECK-DAG: lwz [[REG1:[0-9]+]], [[OFF1]](1)
; CHECK-DAG: lwz [[REG2:[0-9]+]], [[OFF2]](1)
; CHECK-DAG: lwz [[REG3:[0-9]+]], [[OFF3]](1)
; CHECK-DAG: sldi [[REG1]], [[REG1]], 32
; CHECK-DAG: sldi [[REG3]], [[REG3]], 32
; CHECK-DAG: or 9, [[REG0]], [[REG1]]
; CHECK-DAG: or 10, [[REG2]], [[REG3]]
; CHECK: bl test1
declare void @test1([8 x float], [8 x float])
define float @callee2([8 x float] %a, [5 x float] %b, [2 x float] %c) {
entry:
%c.extract = extractvalue [2 x float] %c, 1
ret float %c.extract
}
; CHECK-LABEL: @callee2
; CHECK: rldicl [[REG:[0-9]+]], 10, 32, 32
; CHECK: stw [[REG]], [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller2() {
entry:
%0 = load [8 x float]* getelementptr inbounds (%struct.float8* @g8, i64 0, i32 0), align 4
%1 = load [5 x float]* getelementptr inbounds (%struct.float5* @g5, i64 0, i32 0), align 4
%2 = load [2 x float]* getelementptr inbounds (%struct.float2* @g2, i64 0, i32 0), align 4
tail call void @test2([8 x float] %0, [5 x float] %1, [2 x float] %2)
ret void
}
; CHECK-LABEL: @caller2
; CHECK: ld [[REG:[0-9]+]], .LC
; CHECK-DAG: lfs 1, 0([[REG]])
; CHECK-DAG: lfs 2, 4([[REG]])
; CHECK-DAG: lfs 3, 8([[REG]])
; CHECK-DAG: lfs 4, 12([[REG]])
; CHECK-DAG: lfs 5, 16([[REG]])
; CHECK-DAG: lfs 6, 20([[REG]])
; CHECK-DAG: lfs 7, 24([[REG]])
; CHECK-DAG: lfs 8, 28([[REG]])
; CHECK: ld [[REG:[0-9]+]], .LC
; CHECK-DAG: lfs 9, 0([[REG]])
; CHECK-DAG: lfs 10, 4([[REG]])
; CHECK-DAG: lfs 11, 8([[REG]])
; CHECK-DAG: lfs 12, 12([[REG]])
; CHECK-DAG: lfs 13, 16([[REG]])
; CHECK: ld [[REG:[0-9]+]], .LC
; CHECK-DAG: lwz [[REG0:[0-9]+]], 0([[REG]])
; CHECK-DAG: lwz [[REG1:[0-9]+]], 4([[REG]])
; CHECK-DAG: sldi [[REG1]], [[REG1]], 32
; CHECK-DAG: or 10, [[REG0]], [[REG1]]
; CHECK: bl test2
declare void @test2([8 x float], [5 x float], [2 x float])
define double @callee3([8 x float] %a, [5 x float] %b, double %c) {
entry:
ret double %c
}
; CHECK-LABEL: @callee3
; CHECK: std 10, [[OFF:.*]](1)
; CHECK: lfd 1, [[OFF]](1)
; CHECK: blr
define void @caller3(double %d) {
entry:
%0 = load [8 x float]* getelementptr inbounds (%struct.float8* @g8, i64 0, i32 0), align 4
%1 = load [5 x float]* getelementptr inbounds (%struct.float5* @g5, i64 0, i32 0), align 4
tail call void @test3([8 x float] %0, [5 x float] %1, double %d)
ret void
}
; CHECK-LABEL: @caller3
; CHECK: stfd 1, [[OFF:.*]](1)
; CHECK: ld 10, [[OFF]](1)
; CHECK: bl test3
declare void @test3([8 x float], [5 x float], double)
define float @callee4([8 x float] %a, [5 x float] %b, float %c) {
entry:
ret float %c
}
; CHECK-LABEL: @callee4
; CHECK: stw 10, [[OFF:.*]](1)
; CHECK: lfs 1, [[OFF]](1)
; CHECK: blr
define void @caller4(float %f) {
entry:
%0 = load [8 x float]* getelementptr inbounds (%struct.float8* @g8, i64 0, i32 0), align 4
%1 = load [5 x float]* getelementptr inbounds (%struct.float5* @g5, i64 0, i32 0), align 4
tail call void @test4([8 x float] %0, [5 x float] %1, float %f)
ret void
}
; CHECK-LABEL: @caller4
; CHECK: stfs 1, [[OFF:.*]](1)
; CHECK: lwz 10, [[OFF]](1)
; CHECK: bl test4
declare void @test4([8 x float], [5 x float], float)
Reference in New Issue View Git Blame Copy Permalink