Skip to content

[SDAG] Only apply sincos/frexp stack slot folding to IR pointers #115346

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

[SDAG] Only apply sincos/frexp stack slot folding to IR pointers #115346

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
89153cf
[SDAG] Only apply sincos stack slot folding to IR pointers
MacDue Nov 7, 2024
7b86938
Update comment
MacDue Nov 11, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion llvm/lib/CodeGen/SelectionDAG/SelectionDAG.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2518,7 +2518,12 @@ bool SelectionDAG::expandMultipleResultFPLibCall(
SDValue StoreValue = ST->getValue();
unsigned ResNo = StoreValue.getResNo();
Type *StoreType = StoreValue.getValueType().getTypeForEVT(Ctx);
if (CallRetResNo == ResNo || !ST->isSimple() ||
// Limit this fold to IR pointers. Stores to areas such as the stack may be
// part of the setup for a call, which, if folded, could result in nested
// call sequences.
const Value *PointerValue =
dyn_cast_or_null<const Value *>(ST->getPointerInfo().V);
if (!PointerValue || CallRetResNo == ResNo || !ST->isSimple() ||
ST->getAddressSpace() != 0 ||
ST->getAlign() <
getDataLayout().getABITypeAlign(StoreType->getScalarType()) ||
Expand Down
192 changes: 112 additions & 80 deletions llvm/test/CodeGen/RISCV/llvm.frexp.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -543,42 +543,50 @@ define i32 @test_frexp_f32_i32_only_use_exp(float %a) nounwind {
define { <4 x float>, <4 x i32> } @test_frexp_v4f32_v4i32(<4 x float> %a) nounwind {
; RV32IFD-LABEL: test_frexp_v4f32_v4i32:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -48
; RV32IFD-NEXT: sw ra, 44(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: sw s0, 40(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: fsd fs0, 32(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs1, 24(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs2, 16(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs3, 8(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: addi sp, sp, -64
; RV32IFD-NEXT: sw ra, 60(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: sw s0, 56(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: fsd fs0, 48(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs1, 40(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs2, 32(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs3, 24(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fmv.s fs0, fa3
; RV32IFD-NEXT: fmv.s fs1, fa2
; RV32IFD-NEXT: fmv.s fs2, fa1
; RV32IFD-NEXT: mv s0, a0
; RV32IFD-NEXT: addi a0, a0, 16
; RV32IFD-NEXT: addi a0, sp, 8
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: fmv.s fs3, fa0
; RV32IFD-NEXT: addi a0, s0, 20
; RV32IFD-NEXT: addi a0, sp, 12
; RV32IFD-NEXT: fmv.s fa0, fs2
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: fmv.s fs2, fa0
; RV32IFD-NEXT: addi a0, s0, 24
; RV32IFD-NEXT: addi a0, sp, 16
; RV32IFD-NEXT: fmv.s fa0, fs1
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: fmv.s fs1, fa0
; RV32IFD-NEXT: addi a0, s0, 28
; RV32IFD-NEXT: addi a0, sp, 20
; RV32IFD-NEXT: fmv.s fa0, fs0
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: lw a0, 8(sp)
; RV32IFD-NEXT: lw a1, 12(sp)
; RV32IFD-NEXT: lw a2, 16(sp)
; RV32IFD-NEXT: lw a3, 20(sp)
; RV32IFD-NEXT: sw a0, 16(s0)
; RV32IFD-NEXT: sw a1, 20(s0)
; RV32IFD-NEXT: sw a2, 24(s0)
; RV32IFD-NEXT: sw a3, 28(s0)
; RV32IFD-NEXT: fsw fs3, 0(s0)
; RV32IFD-NEXT: fsw fs2, 4(s0)
; RV32IFD-NEXT: fsw fs1, 8(s0)
; RV32IFD-NEXT: fsw fa0, 12(s0)
; RV32IFD-NEXT: lw ra, 44(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: lw s0, 40(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: fld fs0, 32(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs1, 24(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs2, 16(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs3, 8(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 48
; RV32IFD-NEXT: lw ra, 60(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: lw s0, 56(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: fld fs0, 48(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs1, 40(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs2, 32(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs3, 24(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 64
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: test_frexp_v4f32_v4i32:
Expand Down Expand Up @@ -631,44 +639,52 @@ define { <4 x float>, <4 x i32> } @test_frexp_v4f32_v4i32(<4 x float> %a) nounwi
;
; RV32IZFINXZDINX-LABEL: test_frexp_v4f32_v4i32:
; RV32IZFINXZDINX: # %bb.0:
; RV32IZFINXZDINX-NEXT: addi sp, sp, -32
; RV32IZFINXZDINX-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s4, 8(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: addi sp, sp, -48
; RV32IZFINXZDINX-NEXT: sw ra, 44(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s0, 40(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s1, 36(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s2, 32(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s3, 28(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s4, 24(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: mv s0, a4
; RV32IZFINXZDINX-NEXT: mv s1, a3
; RV32IZFINXZDINX-NEXT: mv s2, a2
; RV32IZFINXZDINX-NEXT: mv a2, a1
; RV32IZFINXZDINX-NEXT: mv s3, a0
; RV32IZFINXZDINX-NEXT: addi a1, a0, 16
; RV32IZFINXZDINX-NEXT: addi a1, sp, 8
; RV32IZFINXZDINX-NEXT: mv a0, a2
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: mv s4, a0
; RV32IZFINXZDINX-NEXT: addi a1, s3, 20
; RV32IZFINXZDINX-NEXT: addi a1, sp, 12
; RV32IZFINXZDINX-NEXT: mv a0, s2
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: mv s2, a0
; RV32IZFINXZDINX-NEXT: addi a1, s3, 24
; RV32IZFINXZDINX-NEXT: addi a1, sp, 16
; RV32IZFINXZDINX-NEXT: mv a0, s1
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: mv s1, a0
; RV32IZFINXZDINX-NEXT: addi a1, s3, 28
; RV32IZFINXZDINX-NEXT: addi a1, sp, 20
; RV32IZFINXZDINX-NEXT: mv a0, s0
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: lw a1, 8(sp)
; RV32IZFINXZDINX-NEXT: lw a2, 12(sp)
; RV32IZFINXZDINX-NEXT: lw a3, 16(sp)
; RV32IZFINXZDINX-NEXT: lw a4, 20(sp)
; RV32IZFINXZDINX-NEXT: sw a1, 16(s3)
; RV32IZFINXZDINX-NEXT: sw a2, 20(s3)
; RV32IZFINXZDINX-NEXT: sw a3, 24(s3)
; RV32IZFINXZDINX-NEXT: sw a4, 28(s3)
; RV32IZFINXZDINX-NEXT: sw s4, 0(s3)
; RV32IZFINXZDINX-NEXT: sw s2, 4(s3)
; RV32IZFINXZDINX-NEXT: sw s1, 8(s3)
; RV32IZFINXZDINX-NEXT: sw a0, 12(s3)
; RV32IZFINXZDINX-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s4, 8(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: addi sp, sp, 32
; RV32IZFINXZDINX-NEXT: lw ra, 44(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s0, 40(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s1, 36(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s2, 32(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s3, 28(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s4, 24(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: addi sp, sp, 48
; RV32IZFINXZDINX-NEXT: ret
;
; RV64IZFINXZDINX-LABEL: test_frexp_v4f32_v4i32:
Expand Down Expand Up @@ -1080,34 +1096,41 @@ define <4 x float> @test_frexp_v4f32_v4i32_only_use_fract(<4 x float> %a) nounwi
define <4 x i32> @test_frexp_v4f32_v4i32_only_use_exp(<4 x float> %a) nounwind {
; RV32IFD-LABEL: test_frexp_v4f32_v4i32_only_use_exp:
; RV32IFD: # %bb.0:
; RV32IFD-NEXT: addi sp, sp, -32
; RV32IFD-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: fsd fs0, 16(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs1, 8(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs2, 0(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fmv.s fs0, fa2
; RV32IFD-NEXT: fmv.s fs1, fa1
; RV32IFD-NEXT: fmv.s fs2, fa0
; RV32IFD-NEXT: addi sp, sp, -48
; RV32IFD-NEXT: sw ra, 44(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: sw s0, 40(sp) # 4-byte Folded Spill
; RV32IFD-NEXT: fsd fs0, 32(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs1, 24(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fsd fs2, 16(sp) # 8-byte Folded Spill
; RV32IFD-NEXT: fmv.s fs0, fa3
; RV32IFD-NEXT: fmv.s fs1, fa2
; RV32IFD-NEXT: fmv.s fs2, fa1
; RV32IFD-NEXT: mv s0, a0
; RV32IFD-NEXT: addi a0, a0, 12
; RV32IFD-NEXT: fmv.s fa0, fa3
; RV32IFD-NEXT: mv a0, sp
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: addi a0, s0, 8
; RV32IFD-NEXT: fmv.s fa0, fs0
; RV32IFD-NEXT: addi a0, sp, 4
; RV32IFD-NEXT: fmv.s fa0, fs2
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: addi a0, s0, 4
; RV32IFD-NEXT: addi a0, sp, 8
; RV32IFD-NEXT: fmv.s fa0, fs1
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: fmv.s fa0, fs2
; RV32IFD-NEXT: mv a0, s0
; RV32IFD-NEXT: addi a0, sp, 12
; RV32IFD-NEXT: fmv.s fa0, fs0
; RV32IFD-NEXT: call frexpf
; RV32IFD-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: fld fs0, 16(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs1, 8(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs2, 0(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 32
; RV32IFD-NEXT: lw a0, 0(sp)
; RV32IFD-NEXT: lw a1, 4(sp)
; RV32IFD-NEXT: lw a2, 8(sp)
; RV32IFD-NEXT: lw a3, 12(sp)
; RV32IFD-NEXT: sw a0, 0(s0)
; RV32IFD-NEXT: sw a1, 4(s0)
; RV32IFD-NEXT: sw a2, 8(s0)
; RV32IFD-NEXT: sw a3, 12(s0)
; RV32IFD-NEXT: lw ra, 44(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: lw s0, 40(sp) # 4-byte Folded Reload
; RV32IFD-NEXT: fld fs0, 32(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs1, 24(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: fld fs2, 16(sp) # 8-byte Folded Reload
; RV32IFD-NEXT: addi sp, sp, 48
; RV32IFD-NEXT: ret
;
; RV64IFD-LABEL: test_frexp_v4f32_v4i32_only_use_exp:
Expand Down Expand Up @@ -1151,34 +1174,43 @@ define <4 x i32> @test_frexp_v4f32_v4i32_only_use_exp(<4 x float> %a) nounwind {
;
; RV32IZFINXZDINX-LABEL: test_frexp_v4f32_v4i32_only_use_exp:
; RV32IZFINXZDINX: # %bb.0:
; RV32IZFINXZDINX-NEXT: addi sp, sp, -32
; RV32IZFINXZDINX-NEXT: sw ra, 28(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s0, 24(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s1, 20(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s2, 16(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s3, 12(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: mv s0, a3
; RV32IZFINXZDINX-NEXT: mv s1, a2
; RV32IZFINXZDINX-NEXT: mv s2, a1
; RV32IZFINXZDINX-NEXT: addi sp, sp, -48
; RV32IZFINXZDINX-NEXT: sw ra, 44(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s0, 40(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s1, 36(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s2, 32(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: sw s3, 28(sp) # 4-byte Folded Spill
; RV32IZFINXZDINX-NEXT: mv s0, a4
; RV32IZFINXZDINX-NEXT: mv s1, a3
; RV32IZFINXZDINX-NEXT: mv s2, a2
; RV32IZFINXZDINX-NEXT: mv a2, a1
; RV32IZFINXZDINX-NEXT: mv s3, a0
; RV32IZFINXZDINX-NEXT: addi a1, a0, 12
; RV32IZFINXZDINX-NEXT: mv a0, a4
; RV32IZFINXZDINX-NEXT: addi a1, sp, 12
; RV32IZFINXZDINX-NEXT: mv a0, a2
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: addi a1, s3, 8
; RV32IZFINXZDINX-NEXT: mv a0, s0
; RV32IZFINXZDINX-NEXT: addi a1, sp, 16
; RV32IZFINXZDINX-NEXT: mv a0, s2
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: addi a1, s3, 4
; RV32IZFINXZDINX-NEXT: addi a1, sp, 20
; RV32IZFINXZDINX-NEXT: mv a0, s1
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: mv a0, s2
; RV32IZFINXZDINX-NEXT: mv a1, s3
; RV32IZFINXZDINX-NEXT: addi a1, sp, 24
; RV32IZFINXZDINX-NEXT: mv a0, s0
; RV32IZFINXZDINX-NEXT: call frexpf
; RV32IZFINXZDINX-NEXT: lw ra, 28(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s0, 24(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s1, 20(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s2, 16(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s3, 12(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: addi sp, sp, 32
; RV32IZFINXZDINX-NEXT: lw a0, 12(sp)
; RV32IZFINXZDINX-NEXT: lw a1, 16(sp)
; RV32IZFINXZDINX-NEXT: lw a2, 20(sp)
; RV32IZFINXZDINX-NEXT: lw a3, 24(sp)
; RV32IZFINXZDINX-NEXT: sw a0, 0(s3)
; RV32IZFINXZDINX-NEXT: sw a1, 4(s3)
; RV32IZFINXZDINX-NEXT: sw a2, 8(s3)
; RV32IZFINXZDINX-NEXT: sw a3, 12(s3)
; RV32IZFINXZDINX-NEXT: lw ra, 44(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s0, 40(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s1, 36(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s2, 32(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: lw s3, 28(sp) # 4-byte Folded Reload
; RV32IZFINXZDINX-NEXT: addi sp, sp, 48
; RV32IZFINXZDINX-NEXT: ret
;
; RV64IZFINXZDINX-LABEL: test_frexp_v4f32_v4i32_only_use_exp:
Expand Down
45 changes: 33 additions & 12 deletions llvm/test/CodeGen/X86/llvm.frexp.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -325,27 +325,28 @@ define { <4 x float>, <4 x i32> } @test_frexp_v4f32_v4i32(<4 x float> %a) {
;
; WIN32-LABEL: test_frexp_v4f32_v4i32:
; WIN32: # %bb.0:
; WIN32-NEXT: pushl %edi
; WIN32-NEXT: pushl %esi
; WIN32-NEXT: subl $44, %esp
; WIN32-NEXT: subl $60, %esp
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %esi
; WIN32-NEXT: leal 24(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: fstpl {{[-0-9]+}}(%e{{[sb]}}p) # 8-byte Folded Spill
; WIN32-NEXT: leal 20(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: fstpl {{[-0-9]+}}(%e{{[sb]}}p) # 8-byte Folded Spill
; WIN32-NEXT: leal 16(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: leal 28(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
Expand All @@ -360,13 +361,22 @@ define { <4 x float>, <4 x i32> } @test_frexp_v4f32_v4i32(<4 x float> %a) {
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %edx
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %edi
; WIN32-NEXT: movl %edi, 28(%esi)
; WIN32-NEXT: movl %edx, 24(%esi)
; WIN32-NEXT: movl %ecx, 20(%esi)
; WIN32-NEXT: movl %eax, 16(%esi)
; WIN32-NEXT: fstps 12(%esi)
; WIN32-NEXT: fstps 8(%esi)
; WIN32-NEXT: fstps 4(%esi)
; WIN32-NEXT: fstps (%esi)
; WIN32-NEXT: movl %esi, %eax
; WIN32-NEXT: addl $44, %esp
; WIN32-NEXT: addl $60, %esp
; WIN32-NEXT: popl %esi
; WIN32-NEXT: popl %edi
; WIN32-NEXT: retl
%result = call { <4 x float>, <4 x i32> } @llvm.frexp.v4f32.v4i32(<4 x float> %a)
ret { <4 x float>, <4 x i32> } %result
Expand Down Expand Up @@ -489,35 +499,46 @@ define <4 x i32> @test_frexp_v4f32_v4i32_only_use_exp(<4 x float> %a) {
;
; WIN32-LABEL: test_frexp_v4f32_v4i32_only_use_exp:
; WIN32: # %bb.0:
; WIN32-NEXT: pushl %edi
; WIN32-NEXT: pushl %esi
; WIN32-NEXT: subl $12, %esp
; WIN32-NEXT: subl $28, %esp
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %esi
; WIN32-NEXT: leal 8(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: fstp %st(0)
; WIN32-NEXT: leal 4(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: fstp %st(0)
; WIN32-NEXT: leal 12(%esi), %eax
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: fstp %st(0)
; WIN32-NEXT: movl %esi, {{[0-9]+}}(%esp)
; WIN32-NEXT: leal {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl %eax, {{[0-9]+}}(%esp)
; WIN32-NEXT: flds {{[0-9]+}}(%esp)
; WIN32-NEXT: fstpl (%esp)
; WIN32-NEXT: calll _frexp
; WIN32-NEXT: fstp %st(0)
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %eax
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %ecx
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %edx
; WIN32-NEXT: movl {{[0-9]+}}(%esp), %edi
; WIN32-NEXT: movl %edi, 12(%esi)
; WIN32-NEXT: movl %edx, 8(%esi)
; WIN32-NEXT: movl %ecx, 4(%esi)
; WIN32-NEXT: movl %eax, (%esi)
; WIN32-NEXT: movl %esi, %eax
; WIN32-NEXT: addl $12, %esp
; WIN32-NEXT: addl $28, %esp
; WIN32-NEXT: popl %esi
; WIN32-NEXT: popl %edi
; WIN32-NEXT: retl
%result = call { <4 x float>, <4 x i32> } @llvm.frexp.v4f32.v4i32(<4 x float> %a)
%result.1 = extractvalue { <4 x float>, <4 x i32> } %result, 1
Expand Down
Loading
Loading