llvm-project/llvm/test/CodeGen/SystemZ/vector-constrained-fp-intri...

6446 lines
246 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O3 -mtriple=s390x-linux-gnu < %s | FileCheck --check-prefix=S390X %s
; RUN: llc -O3 -mtriple=s390x-linux-gnu -mcpu=z13 < %s | FileCheck --check-prefix=SZ13 %s
define <1 x float> @constrained_vector_fdiv_v1f32() {
; S390X-LABEL: constrained_vector_fdiv_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI0_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI0_1
; S390X-NEXT: deb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fdiv_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI0_0
; SZ13-NEXT: vgmf %v0, 2, 8
; SZ13-NEXT: deb %f0, 0(%r1)
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%div = call <1 x float> @llvm.experimental.constrained.fdiv.v1f32(
<1 x float> <float 1.000000e+00>,
<1 x float> <float 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %div
}
define <2 x double> @constrained_vector_fdiv_v2f64() {
; S390X-LABEL: constrained_vector_fdiv_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI1_0
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI1_1
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI1_2
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: ddbr %f2, %f1
; S390X-NEXT: ddbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fdiv_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI1_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI1_1
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: vfddb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%div = call <2 x double> @llvm.experimental.constrained.fdiv.v2f64(
<2 x double> <double 1.000000e+00, double 2.000000e+00>,
<2 x double> <double 1.000000e+01, double 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %div
}
define <3 x float> @constrained_vector_fdiv_v3f32() {
; S390X-LABEL: constrained_vector_fdiv_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI2_0
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI2_1
; S390X-NEXT: le %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI2_2
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI2_3
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: debr %f4, %f1
; S390X-NEXT: debr %f2, %f1
; S390X-NEXT: debr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fdiv_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI2_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI2_1
; SZ13-NEXT: lde %f1, 0(%r1)
; SZ13-NEXT: debr %f1, %f0
; SZ13-NEXT: vgmf %v2, 2, 8
; SZ13-NEXT: vgmf %v3, 1, 1
; SZ13-NEXT: debr %f2, %f0
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: debr %f3, %f0
; SZ13-NEXT: vmrhf %v0, %v2, %v3
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: br %r14
entry:
%div = call <3 x float> @llvm.experimental.constrained.fdiv.v3f32(
<3 x float> <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>,
<3 x float> <float 1.000000e+01, float 1.000000e+01, float 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %div
}
define void @constrained_vector_fdiv_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_fdiv_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: ld %f0, 16(%r2)
; S390X-NEXT: ld %f1, 8(%r2)
; S390X-NEXT: larl %r1, .LCPI3_0
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI3_1
; S390X-NEXT: ldeb %f3, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI3_2
; S390X-NEXT: ldeb %f4, 0(%r1)
; S390X-NEXT: ddbr %f3, %f1
; S390X-NEXT: ddb %f2, 0(%r2)
; S390X-NEXT: ddbr %f4, %f0
; S390X-NEXT: std %f4, 16(%r2)
; S390X-NEXT: std %f3, 8(%r2)
; S390X-NEXT: std %f2, 0(%r2)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fdiv_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI3_0
; SZ13-NEXT: ldeb %f1, 0(%r1)
; SZ13-NEXT: ddb %f1, 16(%r2)
; SZ13-NEXT: larl %r1, .LCPI3_1
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: vl %v2, 0(%r1), 3
; SZ13-NEXT: std %f1, 16(%r2)
; SZ13-NEXT: vfddb %v0, %v2, %v0
; SZ13-NEXT: vst %v0, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%div = call <3 x double> @llvm.experimental.constrained.fdiv.v3f64(
<3 x double> <double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>,
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %div, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_fdiv_v4f64() {
; S390X-LABEL: constrained_vector_fdiv_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI4_0
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI4_1
; S390X-NEXT: ldeb %f6, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI4_2
; S390X-NEXT: ldeb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI4_3
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI4_4
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: ddbr %f6, %f1
; S390X-NEXT: ddbr %f4, %f1
; S390X-NEXT: ddbr %f2, %f1
; S390X-NEXT: ddbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fdiv_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI4_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI4_1
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: vfddb %v26, %v1, %v0
; SZ13-NEXT: larl %r1, .LCPI4_2
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: vfddb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%div = call <4 x double> @llvm.experimental.constrained.fdiv.v4f64(
<4 x double> <double 1.000000e+00, double 2.000000e+00,
double 3.000000e+00, double 4.000000e+00>,
<4 x double> <double 1.000000e+01, double 1.000000e+01,
double 1.000000e+01, double 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %div
}
define <1 x float> @constrained_vector_frem_v1f32() {
; S390X-LABEL: constrained_vector_frem_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI5_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI5_1
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fmodf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_frem_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI5_0
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: vgmf %v0, 2, 8
; SZ13-NEXT: brasl %r14, fmodf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%rem = call <1 x float> @llvm.experimental.constrained.frem.v1f32(
<1 x float> <float 1.000000e+00>,
<1 x float> <float 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %rem
}
define <2 x double> @constrained_vector_frem_v2f64() {
; S390X-LABEL: constrained_vector_frem_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI6_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI6_1
; S390X-NEXT: ldeb %f8, 0(%r1)
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: larl %r1, .LCPI6_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_frem_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -184
; SZ13-NEXT: .cfi_def_cfa_offset 344
; SZ13-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI6_0
; SZ13-NEXT: ldeb %f8, 0(%r1)
; SZ13-NEXT: vgmg %v0, 1, 1
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vgmg %v0, 2, 11
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 296(%r15)
; SZ13-NEXT: br %r14
entry:
%rem = call <2 x double> @llvm.experimental.constrained.frem.v2f64(
<2 x double> <double 1.000000e+00, double 2.000000e+00>,
<2 x double> <double 1.000000e+01, double 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %rem
}
define <3 x float> @constrained_vector_frem_v3f32() {
; S390X-LABEL: constrained_vector_frem_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI7_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI7_1
; S390X-NEXT: le %f8, 0(%r1)
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, fmodf@PLT
; S390X-NEXT: larl %r1, .LCPI7_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, fmodf@PLT
; S390X-NEXT: larl %r1, .LCPI7_3
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f10, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, fmodf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f9
; S390X-NEXT: ler %f2, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_frem_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI7_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI7_1
; SZ13-NEXT: lde %f8, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmodf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vgmf %v0, 2, 8
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmodf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vgmf %v0, 1, 1
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmodf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%rem = call <3 x float> @llvm.experimental.constrained.frem.v3f32(
<3 x float> <float 1.000000e+00, float 2.000000e+00, float 3.000000e+00>,
<3 x float> <float 1.000000e+01, float 1.000000e+01, float 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %rem
}
define void @constrained_vector_frem_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_frem_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f2, 0(%r2)
; S390X-NEXT: larl %r1, .LCPI8_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: larl %r1, .LCPI8_1
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: larl %r1, .LCPI8_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_frem_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v2, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: vgmg %v0, 2, 11
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v2, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f2d killed $f2d killed $v2
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v2, %v0, 1
; SZ13-NEXT: vgmg %v0, 1, 1
; SZ13-NEXT: # kill: def $f2d killed $f2d killed $v2
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: larl %r1, .LCPI8_0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%rem = call <3 x double> @llvm.experimental.constrained.frem.v3f64(
<3 x double> <double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>,
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %rem, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_frem_v4f64() {
; S390X-LABEL: constrained_vector_frem_v4f64:
; S390X: # %bb.0:
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -192
; S390X-NEXT: .cfi_def_cfa_offset 352
; S390X-NEXT: std %f8, 184(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f11, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: .cfi_offset %f11, -192
; S390X-NEXT: larl %r1, .LCPI9_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI9_1
; S390X-NEXT: ldeb %f8, 0(%r1)
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: larl %r1, .LCPI9_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: larl %r1, .LCPI9_3
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: larl %r1, .LCPI9_4
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f11, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, fmod@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: ldr %f2, %f10
; S390X-NEXT: ldr %f4, %f11
; S390X-NEXT: ld %f8, 184(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f11, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 304(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_frem_v4f64:
; SZ13: # %bb.0:
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI9_0
; SZ13-NEXT: ldeb %f8, 0(%r1)
; SZ13-NEXT: vgmg %v0, 1, 1
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vgmg %v0, 2, 11
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI9_1
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: larl %r1, .LCPI9_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmod@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 312(%r15)
; SZ13-NEXT: br %r14
%rem = call <4 x double> @llvm.experimental.constrained.frem.v4f64(
<4 x double> <double 1.000000e+00, double 2.000000e+00,
double 3.000000e+00, double 4.000000e+00>,
<4 x double> <double 1.000000e+01, double 1.000000e+01,
double 1.000000e+01, double 1.000000e+01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %rem
}
define <1 x float> @constrained_vector_fmul_v1f32() {
; S390X-LABEL: constrained_vector_fmul_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI10_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI10_1
; S390X-NEXT: meeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fmul_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 1, 1
; SZ13-NEXT: vgmf %v1, 1, 8
; SZ13-NEXT: meebr %f1, %f0
; SZ13-NEXT: vlr %v24, %v1
; SZ13-NEXT: br %r14
entry:
%mul = call <1 x float> @llvm.experimental.constrained.fmul.v1f32(
<1 x float> <float 0x7FF0000000000000>,
<1 x float> <float 2.000000e+00>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %mul
}
define <2 x double> @constrained_vector_fmul_v2f64() {
; S390X-LABEL: constrained_vector_fmul_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI11_0
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI11_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI11_2
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: mdbr %f2, %f1
; S390X-NEXT: mdbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fmul_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI11_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI11_1
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: vfmdb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%mul = call <2 x double> @llvm.experimental.constrained.fmul.v2f64(
<2 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
<2 x double> <double 2.000000e+00, double 3.000000e+00>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %mul
}
define <3 x float> @constrained_vector_fmul_v3f32() {
; S390X-LABEL: constrained_vector_fmul_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI12_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI12_1
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: meeb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI12_2
; S390X-NEXT: ler %f2, %f0
; S390X-NEXT: meeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI12_3
; S390X-NEXT: meeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fmul_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 1, 8
; SZ13-NEXT: larl %r1, .LCPI12_0
; SZ13-NEXT: vgmf %v2, 2, 8
; SZ13-NEXT: vgmf %v1, 1, 8
; SZ13-NEXT: meeb %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI12_1
; SZ13-NEXT: meebr %f2, %f0
; SZ13-NEXT: meeb %f0, 0(%r1)
; SZ13-NEXT: vmrhf %v0, %v2, %v0
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: br %r14
entry:
%mul = call <3 x float> @llvm.experimental.constrained.fmul.v3f32(
<3 x float> <float 0x7FF0000000000000, float 0x7FF0000000000000,
float 0x7FF0000000000000>,
<3 x float> <float 1.000000e+00, float 1.000000e+01, float 1.000000e+02>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %mul
}
define void @constrained_vector_fmul_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_fmul_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: ld %f0, 8(%r2)
; S390X-NEXT: larl %r1, .LCPI13_0
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ld %f2, 16(%r2)
; S390X-NEXT: mdbr %f0, %f1
; S390X-NEXT: ldr %f3, %f1
; S390X-NEXT: mdb %f3, 0(%r2)
; S390X-NEXT: mdbr %f2, %f1
; S390X-NEXT: std %f2, 16(%r2)
; S390X-NEXT: std %f0, 8(%r2)
; S390X-NEXT: std %f3, 0(%r2)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fmul_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI13_0
; SZ13-NEXT: ld %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI13_1
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: vl %v2, 0(%r1), 3
; SZ13-NEXT: mdb %f1, 16(%r2)
; SZ13-NEXT: vfmdb %v0, %v2, %v0
; SZ13-NEXT: std %f1, 16(%r2)
; SZ13-NEXT: vst %v0, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%mul = call <3 x double> @llvm.experimental.constrained.fmul.v3f64(
<3 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
double 0x7FEFFFFFFFFFFFFF>,
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %mul, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_fmul_v4f64() {
; S390X-LABEL: constrained_vector_fmul_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI14_0
; S390X-NEXT: ldeb %f6, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI14_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI14_2
; S390X-NEXT: ldeb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI14_3
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI14_4
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: mdbr %f6, %f1
; S390X-NEXT: mdbr %f4, %f1
; S390X-NEXT: mdbr %f2, %f1
; S390X-NEXT: mdbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fmul_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI14_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI14_1
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI14_2
; SZ13-NEXT: vfmdb %v26, %v1, %v0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfmdb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%mul = call <4 x double> @llvm.experimental.constrained.fmul.v4f64(
<4 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
<4 x double> <double 2.000000e+00, double 3.000000e+00,
double 4.000000e+00, double 5.000000e+00>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %mul
}
define <1 x float> @constrained_vector_fadd_v1f32() {
; S390X-LABEL: constrained_vector_fadd_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI15_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI15_1
; S390X-NEXT: aeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fadd_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 2, 8
; SZ13-NEXT: vgmf %v1, 1, 8
; SZ13-NEXT: aebr %f1, %f0
; SZ13-NEXT: vlr %v24, %v1
; SZ13-NEXT: br %r14
entry:
%add = call <1 x float> @llvm.experimental.constrained.fadd.v1f32(
<1 x float> <float 0x7FF0000000000000>,
<1 x float> <float 1.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %add
}
define <2 x double> @constrained_vector_fadd_v2f64() {
; S390X-LABEL: constrained_vector_fadd_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI16_0
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI16_2
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI16_1
; S390X-NEXT: ldr %f2, %f1
; S390X-NEXT: adb %f2, 0(%r1)
; S390X-NEXT: adbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fadd_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI16_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI16_1
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: vfadb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%add = call <2 x double> @llvm.experimental.constrained.fadd.v2f64(
<2 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
<2 x double> <double 1.000000e+00, double 1.000000e-01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %add
}
define <3 x float> @constrained_vector_fadd_v3f32() {
; S390X-LABEL: constrained_vector_fadd_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI17_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: lzer %f4
; S390X-NEXT: aebr %f4, %f0
; S390X-NEXT: larl %r1, .LCPI17_1
; S390X-NEXT: ler %f2, %f0
; S390X-NEXT: aeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI17_2
; S390X-NEXT: aeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fadd_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgbm %v0, 15
; SZ13-NEXT: vgmf %v2, 1, 1
; SZ13-NEXT: vgmf %v3, 2, 8
; SZ13-NEXT: lzer %f1
; SZ13-NEXT: aebr %f1, %f0
; SZ13-NEXT: aebr %f2, %f0
; SZ13-NEXT: aebr %f3, %f0
; SZ13-NEXT: vmrhf %v0, %v2, %v3
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: br %r14
entry:
%add = call <3 x float> @llvm.experimental.constrained.fadd.v3f32(
<3 x float> <float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000,
float 0xFFFFFFFFE0000000>,
<3 x float> <float 2.0, float 1.0, float 0.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %add
}
define void @constrained_vector_fadd_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_fadd_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: ld %f0, 8(%r2)
; S390X-NEXT: larl %r1, .LCPI18_0
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ld %f2, 16(%r2)
; S390X-NEXT: adbr %f0, %f1
; S390X-NEXT: ldr %f3, %f1
; S390X-NEXT: adb %f3, 0(%r2)
; S390X-NEXT: adbr %f2, %f1
; S390X-NEXT: std %f2, 16(%r2)
; S390X-NEXT: std %f0, 8(%r2)
; S390X-NEXT: std %f3, 0(%r2)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fadd_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI18_0
; SZ13-NEXT: ld %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI18_1
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: vl %v2, 0(%r1), 3
; SZ13-NEXT: adb %f1, 16(%r2)
; SZ13-NEXT: vfadb %v0, %v2, %v0
; SZ13-NEXT: std %f1, 16(%r2)
; SZ13-NEXT: vst %v0, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%add = call <3 x double> @llvm.experimental.constrained.fadd.v3f64(
<3 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
double 0x7FEFFFFFFFFFFFFF>,
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %add, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_fadd_v4f64() {
; S390X-LABEL: constrained_vector_fadd_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI19_0
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI19_1
; S390X-NEXT: ldr %f2, %f1
; S390X-NEXT: ldr %f6, %f1
; S390X-NEXT: adb %f6, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI19_2
; S390X-NEXT: ldeb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI19_4
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI19_3
; S390X-NEXT: adb %f2, 0(%r1)
; S390X-NEXT: adbr %f4, %f1
; S390X-NEXT: adbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fadd_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI19_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI19_1
; SZ13-NEXT: vl %v1, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI19_2
; SZ13-NEXT: vfadb %v26, %v1, %v0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfadb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%add = call <4 x double> @llvm.experimental.constrained.fadd.v4f64(
<4 x double> <double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF,
double 0x7FEFFFFFFFFFFFFF, double 0x7FEFFFFFFFFFFFFF>,
<4 x double> <double 1.000000e+00, double 1.000000e-01,
double 2.000000e+00, double 2.000000e-01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %add
}
define <1 x float> @constrained_vector_fsub_v1f32() {
; S390X-LABEL: constrained_vector_fsub_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI20_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI20_1
; S390X-NEXT: seb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fsub_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 2, 8
; SZ13-NEXT: vgmf %v1, 1, 8
; SZ13-NEXT: sebr %f1, %f0
; SZ13-NEXT: vlr %v24, %v1
; SZ13-NEXT: br %r14
entry:
%sub = call <1 x float> @llvm.experimental.constrained.fsub.v1f32(
<1 x float> <float 0x7FF0000000000000>,
<1 x float> <float 1.000000e+00>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %sub
}
define <2 x double> @constrained_vector_fsub_v2f64() {
; S390X-LABEL: constrained_vector_fsub_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI21_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI21_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI21_1
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: sdb %f2, 0(%r1)
; S390X-NEXT: sdbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fsub_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI21_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vgmg %v1, 12, 10
; SZ13-NEXT: vfsdb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%sub = call <2 x double> @llvm.experimental.constrained.fsub.v2f64(
<2 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF>,
<2 x double> <double 1.000000e+00, double 1.000000e-01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %sub
}
define <3 x float> @constrained_vector_fsub_v3f32() {
; S390X-LABEL: constrained_vector_fsub_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI22_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: larl %r1, .LCPI22_1
; S390X-NEXT: ler %f2, %f0
; S390X-NEXT: seb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI22_2
; S390X-NEXT: seb %f0, 0(%r1)
; S390X-NEXT: lzer %f1
; S390X-NEXT: sebr %f4, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fsub_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgbm %v2, 15
; SZ13-NEXT: lzer %f1
; SZ13-NEXT: sebr %f2, %f1
; SZ13-NEXT: vgmf %v1, 1, 1
; SZ13-NEXT: vgbm %v3, 15
; SZ13-NEXT: vgbm %v0, 15
; SZ13-NEXT: sebr %f3, %f1
; SZ13-NEXT: vgmf %v1, 2, 8
; SZ13-NEXT: sebr %f0, %f1
; SZ13-NEXT: vmrhf %v0, %v3, %v0
; SZ13-NEXT: vrepf %v1, %v2, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: br %r14
entry:
%sub = call <3 x float> @llvm.experimental.constrained.fsub.v3f32(
<3 x float> <float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000,
float 0xFFFFFFFFE0000000>,
<3 x float> <float 2.0, float 1.0, float 0.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %sub
}
define void @constrained_vector_fsub_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_fsub_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI23_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: ld %f1, 8(%r2)
; S390X-NEXT: ld %f2, 16(%r2)
; S390X-NEXT: ldr %f3, %f0
; S390X-NEXT: sdb %f3, 0(%r2)
; S390X-NEXT: ldr %f4, %f0
; S390X-NEXT: sdbr %f4, %f1
; S390X-NEXT: sdbr %f0, %f2
; S390X-NEXT: std %f0, 16(%r2)
; S390X-NEXT: std %f4, 8(%r2)
; S390X-NEXT: std %f3, 0(%r2)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fsub_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: vgmg %v2, 12, 10
; SZ13-NEXT: sdb %f2, 16(%r2)
; SZ13-NEXT: vgmg %v1, 12, 10
; SZ13-NEXT: vfsdb %v0, %v1, %v0
; SZ13-NEXT: std %f2, 16(%r2)
; SZ13-NEXT: vst %v0, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%sub = call <3 x double> @llvm.experimental.constrained.fsub.v3f64(
<3 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF,
double 0xFFEFFFFFFFFFFFFF>,
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %sub, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_fsub_v4f64() {
; S390X-LABEL: constrained_vector_fsub_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI24_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI24_1
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: sdb %f6, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI24_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI24_4
; S390X-NEXT: ldeb %f3, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI24_3
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: sdb %f2, 0(%r1)
; S390X-NEXT: ldr %f4, %f0
; S390X-NEXT: sdbr %f4, %f1
; S390X-NEXT: sdbr %f0, %f3
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fsub_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI24_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vgmg %v1, 12, 10
; SZ13-NEXT: larl %r1, .LCPI24_1
; SZ13-NEXT: vfsdb %v26, %v1, %v0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfsdb %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%sub = call <4 x double> @llvm.experimental.constrained.fsub.v4f64(
<4 x double> <double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF,
double 0xFFEFFFFFFFFFFFFF, double 0xFFEFFFFFFFFFFFFF>,
<4 x double> <double 1.000000e+00, double 1.000000e-01,
double 2.000000e+00, double 2.000000e-01>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %sub
}
define <1 x float> @constrained_vector_sqrt_v1f32() {
; S390X-LABEL: constrained_vector_sqrt_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI25_0
; S390X-NEXT: sqeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sqrt_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI25_0
; SZ13-NEXT: sqeb %f0, 0(%r1)
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%sqrt = call <1 x float> @llvm.experimental.constrained.sqrt.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %sqrt
}
define <2 x double> @constrained_vector_sqrt_v2f64() {
; S390X-LABEL: constrained_vector_sqrt_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI26_0
; S390X-NEXT: larl %r2, .LCPI26_1
; S390X-NEXT: ldeb %f0, 0(%r2)
; S390X-NEXT: sqdb %f2, 0(%r1)
; S390X-NEXT: sqdbr %f0, %f0
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sqrt_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI26_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfsqdb %v24, %v0
; SZ13-NEXT: br %r14
entry:
%sqrt = call <2 x double> @llvm.experimental.constrained.sqrt.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %sqrt
}
define <3 x float> @constrained_vector_sqrt_v3f32() {
; S390X-LABEL: constrained_vector_sqrt_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI27_0
; S390X-NEXT: sqeb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI27_1
; S390X-NEXT: sqeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI27_2
; S390X-NEXT: sqeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sqrt_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI27_0
; SZ13-NEXT: sqeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI27_1
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: sqeb %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI27_2
; SZ13-NEXT: sqeb %f2, 0(%r1)
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%sqrt = call <3 x float> @llvm.experimental.constrained.sqrt.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %sqrt
}
define void @constrained_vector_sqrt_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_sqrt_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: ld %f0, 8(%r2)
; S390X-NEXT: ld %f1, 16(%r2)
; S390X-NEXT: sqdb %f2, 0(%r2)
; S390X-NEXT: sqdbr %f0, %f0
; S390X-NEXT: sqdbr %f1, %f1
; S390X-NEXT: std %f1, 16(%r2)
; S390X-NEXT: std %f0, 8(%r2)
; S390X-NEXT: std %f2, 0(%r2)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sqrt_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: sqdb %f1, 16(%r2)
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: std %f1, 16(%r2)
; SZ13-NEXT: vfsqdb %v0, %v0
; SZ13-NEXT: vst %v0, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%sqrt = call <3 x double> @llvm.experimental.constrained.sqrt.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %sqrt, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_sqrt_v4f64() {
; S390X-LABEL: constrained_vector_sqrt_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI29_0
; S390X-NEXT: sqdb %f6, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI29_1
; S390X-NEXT: sqdb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI29_3
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI29_2
; S390X-NEXT: sqdb %f2, 0(%r1)
; S390X-NEXT: sqdbr %f0, %f0
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sqrt_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI29_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfsqdb %v26, %v0
; SZ13-NEXT: larl %r1, .LCPI29_1
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfsqdb %v24, %v0
; SZ13-NEXT: br %r14
entry:
%sqrt = call <4 x double> @llvm.experimental.constrained.sqrt.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %sqrt
}
define <1 x float> @constrained_vector_pow_v1f32() {
; S390X-LABEL: constrained_vector_pow_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI30_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI30_1
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: brasl %r14, powf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_pow_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI30_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI30_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, powf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%pow = call <1 x float> @llvm.experimental.constrained.pow.v1f32(
<1 x float> <float 42.0>,
<1 x float> <float 3.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %pow
}
define <2 x double> @constrained_vector_pow_v2f64() {
; S390X-LABEL: constrained_vector_pow_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI31_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI31_1
; S390X-NEXT: ldeb %f8, 0(%r1)
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: larl %r1, .LCPI31_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_pow_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -184
; SZ13-NEXT: .cfi_def_cfa_offset 344
; SZ13-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI31_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI31_1
; SZ13-NEXT: ldeb %f8, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: larl %r1, .LCPI31_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 296(%r15)
; SZ13-NEXT: br %r14
entry:
%pow = call <2 x double> @llvm.experimental.constrained.pow.v2f64(
<2 x double> <double 42.1, double 42.2>,
<2 x double> <double 3.0, double 3.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %pow
}
define <3 x float> @constrained_vector_pow_v3f32() {
; S390X-LABEL: constrained_vector_pow_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI32_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI32_1
; S390X-NEXT: le %f8, 0(%r1)
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, powf@PLT
; S390X-NEXT: larl %r1, .LCPI32_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, powf@PLT
; S390X-NEXT: larl %r1, .LCPI32_3
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f10, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, powf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f9
; S390X-NEXT: ler %f2, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_pow_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI32_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI32_1
; SZ13-NEXT: lde %f8, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, powf@PLT
; SZ13-NEXT: larl %r1, .LCPI32_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, powf@PLT
; SZ13-NEXT: larl %r1, .LCPI32_3
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, powf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%pow = call <3 x float> @llvm.experimental.constrained.pow.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
<3 x float> <float 3.0, float 3.0, float 3.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %pow
}
define void @constrained_vector_pow_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_pow_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -192
; S390X-NEXT: .cfi_def_cfa_offset 352
; S390X-NEXT: std %f8, 184(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f11, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: .cfi_offset %f11, -192
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: larl %r1, .LCPI33_0
; S390X-NEXT: ldeb %f9, 0(%r1)
; S390X-NEXT: ld %f10, 8(%r2)
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: ldr %f11, %f0
; S390X-NEXT: ldr %f0, %f10
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f10, 8(%r13)
; S390X-NEXT: std %f11, 0(%r13)
; S390X-NEXT: ld %f8, 184(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f11, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_pow_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -208
; SZ13-NEXT: .cfi_def_cfa_offset 368
; SZ13-NEXT: std %f8, 200(%r15) # 8-byte Folded Spill
; SZ13-NEXT: std %f9, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: .cfi_offset %f9, -176
; SZ13-NEXT: larl %r1, .LCPI33_0
; SZ13-NEXT: ldeb %f9, 0(%r1)
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: ldr %f2, %f9
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ldr %f2, %f9
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: ldr %f2, %f9
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 200(%r15) # 8-byte Folded Reload
; SZ13-NEXT: ld %f9, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%pow = call <3 x double> @llvm.experimental.constrained.pow.v3f64(
<3 x double> %b,
<3 x double> <double 3.0, double 3.0, double 3.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %pow, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_pow_v4f64() {
; S390X-LABEL: constrained_vector_pow_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -192
; S390X-NEXT: .cfi_def_cfa_offset 352
; S390X-NEXT: std %f8, 184(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f11, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: .cfi_offset %f11, -192
; S390X-NEXT: larl %r1, .LCPI34_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI34_1
; S390X-NEXT: ldeb %f8, 0(%r1)
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: larl %r1, .LCPI34_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: larl %r1, .LCPI34_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: larl %r1, .LCPI34_4
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f11, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: ldr %f2, %f8
; S390X-NEXT: brasl %r14, pow@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: ldr %f2, %f10
; S390X-NEXT: ldr %f4, %f11
; S390X-NEXT: ld %f8, 184(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f11, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 304(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_pow_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI34_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI34_1
; SZ13-NEXT: ldeb %f8, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: larl %r1, .LCPI34_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI34_3
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: larl %r1, .LCPI34_4
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, pow@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%pow = call <4 x double> @llvm.experimental.constrained.pow.v4f64(
<4 x double> <double 42.1, double 42.2,
double 42.3, double 42.4>,
<4 x double> <double 3.0, double 3.0,
double 3.0, double 3.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %pow
}
define <1 x float> @constrained_vector_powi_v1f32() {
; S390X-LABEL: constrained_vector_powi_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI35_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: brasl %r14, __powisf2@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_powi_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI35_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powisf2@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%powi = call <1 x float> @llvm.experimental.constrained.powi.v1f32(
<1 x float> <float 42.0>,
i32 3,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %powi
}
define <2 x double> @constrained_vector_powi_v2f64() {
; S390X-LABEL: constrained_vector_powi_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI36_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: larl %r1, .LCPI36_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_powi_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI36_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: larl %r1, .LCPI36_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%powi = call <2 x double> @llvm.experimental.constrained.powi.v2f64(
<2 x double> <double 42.1, double 42.2>,
i32 3,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %powi
}
define <3 x float> @constrained_vector_powi_v3f32() {
; S390X-LABEL: constrained_vector_powi_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI37_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: brasl %r14, __powisf2@PLT
; S390X-NEXT: larl %r1, .LCPI37_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, __powisf2@PLT
; S390X-NEXT: larl %r1, .LCPI37_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, __powisf2@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_powi_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI37_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powisf2@PLT
; SZ13-NEXT: larl %r1, .LCPI37_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powisf2@PLT
; SZ13-NEXT: larl %r1, .LCPI37_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powisf2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%powi = call <3 x float> @llvm.experimental.constrained.powi.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
i32 3,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %powi
}
define void @constrained_vector_powi_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_powi_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI38_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: larl %r1, .LCPI38_1
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: larl %r1, .LCPI38_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: std %f0, 8(%r13)
; S390X-NEXT: std %f9, 0(%r13)
; S390X-NEXT: std %f8, 16(%r13)
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_powi_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI38_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: larl %r1, .LCPI38_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI38_2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 280(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%powi = call <3 x double> @llvm.experimental.constrained.powi.v3f64(
<3 x double> <double 42.0, double 42.1, double 42.2>,
i32 3,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %powi, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_powi_v4f64() {
; S390X-LABEL: constrained_vector_powi_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI39_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: larl %r1, .LCPI39_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: larl %r1, .LCPI39_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: larl %r1, .LCPI39_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: lghi %r2, 3
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, __powidf2@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_powi_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI39_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: larl %r1, .LCPI39_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI39_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: larl %r1, .LCPI39_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: lghi %r2, 3
; SZ13-NEXT: brasl %r14, __powidf2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%powi = call <4 x double> @llvm.experimental.constrained.powi.v4f64(
<4 x double> <double 42.1, double 42.2,
double 42.3, double 42.4>,
i32 3,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %powi
}
define <1 x float> @constrained_vector_sin_v1f32() {
; S390X-LABEL: constrained_vector_sin_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI40_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, sinf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sin_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI40_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sinf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%sin = call <1 x float> @llvm.experimental.constrained.sin.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %sin
}
define <2 x double> @constrained_vector_sin_v2f64() {
; S390X-LABEL: constrained_vector_sin_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI41_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: larl %r1, .LCPI41_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sin_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI41_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: larl %r1, .LCPI41_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%sin = call <2 x double> @llvm.experimental.constrained.sin.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %sin
}
define <3 x float> @constrained_vector_sin_v3f32() {
; S390X-LABEL: constrained_vector_sin_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI42_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, sinf@PLT
; S390X-NEXT: larl %r1, .LCPI42_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, sinf@PLT
; S390X-NEXT: larl %r1, .LCPI42_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, sinf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sin_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI42_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sinf@PLT
; SZ13-NEXT: larl %r1, .LCPI42_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sinf@PLT
; SZ13-NEXT: larl %r1, .LCPI42_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sinf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%sin = call <3 x float> @llvm.experimental.constrained.sin.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %sin
}
define void @constrained_vector_sin_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_sin_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sin_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%sin = call <3 x double> @llvm.experimental.constrained.sin.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %sin, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_sin_v4f64() {
; S390X-LABEL: constrained_vector_sin_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI44_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: larl %r1, .LCPI44_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: larl %r1, .LCPI44_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: larl %r1, .LCPI44_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, sin@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_sin_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI44_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: larl %r1, .LCPI44_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI44_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: larl %r1, .LCPI44_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, sin@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%sin = call <4 x double> @llvm.experimental.constrained.sin.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %sin
}
define <1 x float> @constrained_vector_cos_v1f32() {
; S390X-LABEL: constrained_vector_cos_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI45_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, cosf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_cos_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI45_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cosf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%cos = call <1 x float> @llvm.experimental.constrained.cos.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %cos
}
define <2 x double> @constrained_vector_cos_v2f64() {
; S390X-LABEL: constrained_vector_cos_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI46_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: larl %r1, .LCPI46_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_cos_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI46_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: larl %r1, .LCPI46_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%cos = call <2 x double> @llvm.experimental.constrained.cos.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %cos
}
define <3 x float> @constrained_vector_cos_v3f32() {
; S390X-LABEL: constrained_vector_cos_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI47_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, cosf@PLT
; S390X-NEXT: larl %r1, .LCPI47_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, cosf@PLT
; S390X-NEXT: larl %r1, .LCPI47_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, cosf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_cos_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI47_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cosf@PLT
; SZ13-NEXT: larl %r1, .LCPI47_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cosf@PLT
; SZ13-NEXT: larl %r1, .LCPI47_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cosf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%cos = call <3 x float> @llvm.experimental.constrained.cos.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %cos
}
define void @constrained_vector_cos_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_cos_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_cos_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%cos = call <3 x double> @llvm.experimental.constrained.cos.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %cos, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_cos_v4f64() {
; S390X-LABEL: constrained_vector_cos_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI49_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: larl %r1, .LCPI49_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: larl %r1, .LCPI49_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: larl %r1, .LCPI49_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, cos@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_cos_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI49_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: larl %r1, .LCPI49_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI49_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: larl %r1, .LCPI49_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, cos@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%cos = call <4 x double> @llvm.experimental.constrained.cos.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %cos
}
define <1 x float> @constrained_vector_exp_v1f32() {
; S390X-LABEL: constrained_vector_exp_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI50_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, expf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI50_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, expf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%exp = call <1 x float> @llvm.experimental.constrained.exp.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %exp
}
define <2 x double> @constrained_vector_exp_v2f64() {
; S390X-LABEL: constrained_vector_exp_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI51_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: larl %r1, .LCPI51_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI51_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: larl %r1, .LCPI51_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%exp = call <2 x double> @llvm.experimental.constrained.exp.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %exp
}
define <3 x float> @constrained_vector_exp_v3f32() {
; S390X-LABEL: constrained_vector_exp_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI52_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, expf@PLT
; S390X-NEXT: larl %r1, .LCPI52_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, expf@PLT
; S390X-NEXT: larl %r1, .LCPI52_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, expf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI52_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, expf@PLT
; SZ13-NEXT: larl %r1, .LCPI52_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, expf@PLT
; SZ13-NEXT: larl %r1, .LCPI52_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, expf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%exp = call <3 x float> @llvm.experimental.constrained.exp.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %exp
}
define void @constrained_vector_exp_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_exp_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%exp = call <3 x double> @llvm.experimental.constrained.exp.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %exp, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_exp_v4f64() {
; S390X-LABEL: constrained_vector_exp_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI54_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: larl %r1, .LCPI54_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: larl %r1, .LCPI54_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: larl %r1, .LCPI54_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI54_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: larl %r1, .LCPI54_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI54_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: larl %r1, .LCPI54_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%exp = call <4 x double> @llvm.experimental.constrained.exp.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %exp
}
define <1 x float> @constrained_vector_exp2_v1f32() {
; S390X-LABEL: constrained_vector_exp2_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI55_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, exp2f@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp2_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI55_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2f@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%exp2 = call <1 x float> @llvm.experimental.constrained.exp2.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %exp2
}
define <2 x double> @constrained_vector_exp2_v2f64() {
; S390X-LABEL: constrained_vector_exp2_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI56_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: larl %r1, .LCPI56_1
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp2_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI56_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: larl %r1, .LCPI56_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%exp2 = call <2 x double> @llvm.experimental.constrained.exp2.v2f64(
<2 x double> <double 42.1, double 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %exp2
}
define <3 x float> @constrained_vector_exp2_v3f32() {
; S390X-LABEL: constrained_vector_exp2_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI57_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, exp2f@PLT
; S390X-NEXT: larl %r1, .LCPI57_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, exp2f@PLT
; S390X-NEXT: larl %r1, .LCPI57_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, exp2f@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp2_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI57_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2f@PLT
; SZ13-NEXT: larl %r1, .LCPI57_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2f@PLT
; SZ13-NEXT: larl %r1, .LCPI57_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2f@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%exp2 = call <3 x float> @llvm.experimental.constrained.exp2.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %exp2
}
define void @constrained_vector_exp2_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_exp2_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp2_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%exp2 = call <3 x double> @llvm.experimental.constrained.exp2.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %exp2, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_exp2_v4f64() {
; S390X-LABEL: constrained_vector_exp2_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI59_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: larl %r1, .LCPI59_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: larl %r1, .LCPI59_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: larl %r1, .LCPI59_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, exp2@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_exp2_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI59_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: larl %r1, .LCPI59_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI59_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: larl %r1, .LCPI59_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, exp2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%exp2 = call <4 x double> @llvm.experimental.constrained.exp2.v4f64(
<4 x double> <double 42.1, double 42.2,
double 42.3, double 42.4>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %exp2
}
define <1 x float> @constrained_vector_log_v1f32() {
; S390X-LABEL: constrained_vector_log_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI60_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, logf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI60_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, logf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%log = call <1 x float> @llvm.experimental.constrained.log.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %log
}
define <2 x double> @constrained_vector_log_v2f64() {
; S390X-LABEL: constrained_vector_log_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI61_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: larl %r1, .LCPI61_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI61_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: larl %r1, .LCPI61_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%log = call <2 x double> @llvm.experimental.constrained.log.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %log
}
define <3 x float> @constrained_vector_log_v3f32() {
; S390X-LABEL: constrained_vector_log_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI62_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, logf@PLT
; S390X-NEXT: larl %r1, .LCPI62_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, logf@PLT
; S390X-NEXT: larl %r1, .LCPI62_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, logf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI62_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, logf@PLT
; SZ13-NEXT: larl %r1, .LCPI62_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, logf@PLT
; SZ13-NEXT: larl %r1, .LCPI62_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, logf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%log = call <3 x float> @llvm.experimental.constrained.log.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %log
}
define void @constrained_vector_log_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_log_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%log = call <3 x double> @llvm.experimental.constrained.log.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %log, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_log_v4f64() {
; S390X-LABEL: constrained_vector_log_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI64_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: larl %r1, .LCPI64_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: larl %r1, .LCPI64_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: larl %r1, .LCPI64_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI64_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: larl %r1, .LCPI64_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI64_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: larl %r1, .LCPI64_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%log = call <4 x double> @llvm.experimental.constrained.log.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %log
}
define <1 x float> @constrained_vector_log10_v1f32() {
; S390X-LABEL: constrained_vector_log10_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI65_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log10f@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log10_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI65_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10f@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%log10 = call <1 x float> @llvm.experimental.constrained.log10.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %log10
}
define <2 x double> @constrained_vector_log10_v2f64() {
; S390X-LABEL: constrained_vector_log10_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI66_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: larl %r1, .LCPI66_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log10_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI66_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: larl %r1, .LCPI66_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%log10 = call <2 x double> @llvm.experimental.constrained.log10.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %log10
}
define <3 x float> @constrained_vector_log10_v3f32() {
; S390X-LABEL: constrained_vector_log10_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI67_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log10f@PLT
; S390X-NEXT: larl %r1, .LCPI67_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, log10f@PLT
; S390X-NEXT: larl %r1, .LCPI67_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, log10f@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log10_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI67_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10f@PLT
; SZ13-NEXT: larl %r1, .LCPI67_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10f@PLT
; SZ13-NEXT: larl %r1, .LCPI67_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10f@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%log10 = call <3 x float> @llvm.experimental.constrained.log10.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %log10
}
define void @constrained_vector_log10_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_log10_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log10_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%log10 = call <3 x double> @llvm.experimental.constrained.log10.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %log10, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_log10_v4f64() {
; S390X-LABEL: constrained_vector_log10_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI69_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: larl %r1, .LCPI69_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: larl %r1, .LCPI69_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: larl %r1, .LCPI69_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log10@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log10_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI69_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: larl %r1, .LCPI69_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI69_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: larl %r1, .LCPI69_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log10@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%log10 = call <4 x double> @llvm.experimental.constrained.log10.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %log10
}
define <1 x float> @constrained_vector_log2_v1f32() {
; S390X-LABEL: constrained_vector_log2_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI70_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log2f@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log2_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI70_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2f@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%log2 = call <1 x float> @llvm.experimental.constrained.log2.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %log2
}
define <2 x double> @constrained_vector_log2_v2f64() {
; S390X-LABEL: constrained_vector_log2_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI71_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: larl %r1, .LCPI71_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log2_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI71_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: larl %r1, .LCPI71_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%log2 = call <2 x double> @llvm.experimental.constrained.log2.v2f64(
<2 x double> <double 42.0, double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %log2
}
define <3 x float> @constrained_vector_log2_v3f32() {
; S390X-LABEL: constrained_vector_log2_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI72_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log2f@PLT
; S390X-NEXT: larl %r1, .LCPI72_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, log2f@PLT
; S390X-NEXT: larl %r1, .LCPI72_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, log2f@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log2_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI72_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2f@PLT
; SZ13-NEXT: larl %r1, .LCPI72_1
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2f@PLT
; SZ13-NEXT: larl %r1, .LCPI72_2
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2f@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%log2 = call <3 x float> @llvm.experimental.constrained.log2.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %log2
}
define void @constrained_vector_log2_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_log2_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log2_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%log2 = call <3 x double> @llvm.experimental.constrained.log2.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %log2, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_log2_v4f64() {
; S390X-LABEL: constrained_vector_log2_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI74_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: larl %r1, .LCPI74_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: larl %r1, .LCPI74_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: larl %r1, .LCPI74_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, log2@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log2_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI74_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: larl %r1, .LCPI74_1
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI74_2
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: larl %r1, .LCPI74_3
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: brasl %r14, log2@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%log2 = call <4 x double> @llvm.experimental.constrained.log2.v4f64(
<4 x double> <double 42.0, double 42.1,
double 42.2, double 42.3>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %log2
}
define <1 x float> @constrained_vector_rint_v1f32() {
; S390X-LABEL: constrained_vector_rint_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI75_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: fiebr %f0, 0, %f0
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_rint_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI75_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: fiebr %f0, 0, %f0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%rint = call <1 x float> @llvm.experimental.constrained.rint.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %rint
}
define <2 x double> @constrained_vector_rint_v2f64() {
; S390X-LABEL: constrained_vector_rint_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI76_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI76_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: fidbr %f2, 0, %f0
; S390X-NEXT: fidbr %f0, 0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_rint_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI76_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v24, %v0, 0, 0
; SZ13-NEXT: br %r14
entry:
%rint = call <2 x double> @llvm.experimental.constrained.rint.v2f64(
<2 x double> <double 42.1, double 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %rint
}
define <3 x float> @constrained_vector_rint_v3f32() {
; S390X-LABEL: constrained_vector_rint_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI77_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI77_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI77_2
; S390X-NEXT: le %f3, 0(%r1)
; S390X-NEXT: fiebr %f4, 0, %f0
; S390X-NEXT: fiebr %f2, 0, %f1
; S390X-NEXT: fiebr %f0, 0, %f3
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_rint_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI77_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI77_1
; SZ13-NEXT: lde %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI77_2
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: fiebr %f0, 0, %f0
; SZ13-NEXT: fiebr %f1, 0, %f1
; SZ13-NEXT: fiebr %f2, 0, %f2
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%rint = call <3 x float> @llvm.experimental.constrained.rint.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %rint
}
define void @constrained_vector_rint_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_rint_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f1, 8(%r2)
; S390X-NEXT: ld %f2, 16(%r2)
; S390X-NEXT: fidbr %f0, 0, %f0
; S390X-NEXT: fidbr %f1, 0, %f1
; S390X-NEXT: fidbr %f2, 0, %f2
; S390X-NEXT: std %f2, 16(%r2)
; S390X-NEXT: std %f1, 8(%r2)
; S390X-NEXT: std %f0, 0(%r2)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_rint_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: vfidb %v1, %v1, 0, 0
; SZ13-NEXT: fidbra %f0, 0, %f0, 0
; SZ13-NEXT: std %f0, 16(%r2)
; SZ13-NEXT: vst %v1, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%rint = call <3 x double> @llvm.experimental.constrained.rint.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %rint, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_rint_v4f64() {
; S390X-LABEL: constrained_vector_rint_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI79_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI79_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI79_2
; S390X-NEXT: ld %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI79_3
; S390X-NEXT: ld %f3, 0(%r1)
; S390X-NEXT: fidbr %f6, 0, %f0
; S390X-NEXT: fidbr %f4, 0, %f1
; S390X-NEXT: fidbr %f2, 0, %f2
; S390X-NEXT: fidbr %f0, 0, %f3
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_rint_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI79_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI79_1
; SZ13-NEXT: vfidb %v24, %v0, 0, 0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v26, %v0, 0, 0
; SZ13-NEXT: br %r14
entry:
%rint = call <4 x double> @llvm.experimental.constrained.rint.v4f64(
<4 x double> <double 42.1, double 42.2,
double 42.3, double 42.4>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %rint
}
define <1 x float> @constrained_vector_nearbyint_v1f32() {
; S390X-LABEL: constrained_vector_nearbyint_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI80_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, nearbyintf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_nearbyint_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI80_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: fiebra %f0, 0, %f0, 4
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%nearby = call <1 x float> @llvm.experimental.constrained.nearbyint.v1f32(
<1 x float> <float 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %nearby
}
define <2 x double> @constrained_vector_nearbyint_v2f64() {
; S390X-LABEL: constrained_vector_nearbyint_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI81_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: larl %r1, .LCPI81_1
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_nearbyint_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI81_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v24, %v0, 4, 0
; SZ13-NEXT: br %r14
entry:
%nearby = call <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(
<2 x double> <double 42.1, double 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %nearby
}
define <3 x float> @constrained_vector_nearbyint_v3f32() {
; S390X-LABEL: constrained_vector_nearbyint_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI82_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, nearbyintf@PLT
; S390X-NEXT: larl %r1, .LCPI82_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, nearbyintf@PLT
; S390X-NEXT: larl %r1, .LCPI82_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, nearbyintf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_nearbyint_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI82_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI82_1
; SZ13-NEXT: lde %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI82_2
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: fiebra %f0, 0, %f0, 4
; SZ13-NEXT: fiebra %f1, 0, %f1, 4
; SZ13-NEXT: fiebra %f2, 0, %f2, 4
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%nearby = call <3 x float> @llvm.experimental.constrained.nearbyint.v3f32(
<3 x float> <float 42.0, float 43.0, float 44.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %nearby
}
define void @constrained_vector_nearbyint_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_nearbyint_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_nearbyint_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: vfidb %v1, %v1, 4, 0
; SZ13-NEXT: fidbra %f0, 0, %f0, 4
; SZ13-NEXT: std %f0, 16(%r2)
; SZ13-NEXT: vst %v1, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%nearby = call <3 x double> @llvm.experimental.constrained.nearbyint.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %nearby, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_nearbyint_v4f64() {
; S390X-LABEL: constrained_vector_nearbyint_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI84_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: larl %r1, .LCPI84_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: larl %r1, .LCPI84_2
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: larl %r1, .LCPI84_3
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, nearbyint@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_nearbyint_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI84_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: larl %r1, .LCPI84_1
; SZ13-NEXT: vfidb %v24, %v0, 4, 0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v26, %v0, 4, 0
; SZ13-NEXT: br %r14
entry:
%nearby = call <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(
<4 x double> <double 42.1, double 42.2,
double 42.3, double 42.4>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %nearby
}
define <1 x float> @constrained_vector_maxnum_v1f32() {
; S390X-LABEL: constrained_vector_maxnum_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI85_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI85_1
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fmaxf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_maxnum_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI85_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI85_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmaxf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%max = call <1 x float> @llvm.experimental.constrained.maxnum.v1f32(
<1 x float> <float 42.0>, <1 x float> <float 41.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %max
}
define <2 x double> @constrained_vector_maxnum_v2f64() {
; S390X-LABEL: constrained_vector_maxnum_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI86_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI86_1
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: larl %r1, .LCPI86_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI86_3
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_maxnum_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI86_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI86_1
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: larl %r1, .LCPI86_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI86_3
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%max = call <2 x double> @llvm.experimental.constrained.maxnum.v2f64(
<2 x double> <double 43.0, double 42.0>,
<2 x double> <double 41.0, double 40.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %max
}
define <3 x float> @constrained_vector_maxnum_v3f32() {
; S390X-LABEL: constrained_vector_maxnum_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI87_0
; S390X-NEXT: le %f8, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI87_1
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: brasl %r14, fmaxf@PLT
; S390X-NEXT: larl %r1, .LCPI87_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI87_3
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, fmaxf@PLT
; S390X-NEXT: larl %r1, .LCPI87_4
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f10, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, fmaxf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f9
; S390X-NEXT: ler %f2, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_maxnum_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI87_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI87_1
; SZ13-NEXT: lde %f8, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fmaxf@PLT
; SZ13-NEXT: larl %r1, .LCPI87_2
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, fmaxf@PLT
; SZ13-NEXT: larl %r1, .LCPI87_3
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI87_4
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmaxf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%max = call <3 x float> @llvm.experimental.constrained.maxnum.v3f32(
<3 x float> <float 43.0, float 44.0, float 45.0>,
<3 x float> <float 41.0, float 42.0, float 43.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %max
}
define void @constrained_vector_log10_maxnum_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_log10_maxnum_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: larl %r1, .LCPI88_0
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: larl %r1, .LCPI88_1
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: larl %r1, .LCPI88_2
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_log10_maxnum_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI88_0
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: larl %r1, .LCPI88_1
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: larl %r1, .LCPI88_2
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%max = call <3 x double> @llvm.experimental.constrained.maxnum.v3f64(
<3 x double> %b,
<3 x double> <double 40.0, double 41.0, double 42.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %max, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_maxnum_v4f64() {
; S390X-LABEL: constrained_vector_maxnum_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI89_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI89_1
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: larl %r1, .LCPI89_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI89_3
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: larl %r1, .LCPI89_4
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI89_5
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: larl %r1, .LCPI89_6
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI89_7
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmax@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_maxnum_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI89_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI89_1
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: larl %r1, .LCPI89_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI89_3
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI89_4
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI89_5
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: larl %r1, .LCPI89_6
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI89_7
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmax@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%max = call <4 x double> @llvm.experimental.constrained.maxnum.v4f64(
<4 x double> <double 44.0, double 45.0,
double 46.0, double 47.0>,
<4 x double> <double 40.0, double 41.0,
double 42.0, double 43.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %max
}
define <1 x float> @constrained_vector_minnum_v1f32() {
; S390X-LABEL: constrained_vector_minnum_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI90_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI90_1
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fminf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_minnum_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -160
; SZ13-NEXT: .cfi_def_cfa_offset 320
; SZ13-NEXT: larl %r1, .LCPI90_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI90_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fminf@PLT
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: lmg %r14, %r15, 272(%r15)
; SZ13-NEXT: br %r14
entry:
%min = call <1 x float> @llvm.experimental.constrained.minnum.v1f32(
<1 x float> <float 42.0>, <1 x float> <float 41.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %min
}
define <2 x double> @constrained_vector_minnum_v2f64() {
; S390X-LABEL: constrained_vector_minnum_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI91_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI91_1
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: larl %r1, .LCPI91_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI91_3
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_minnum_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -176
; SZ13-NEXT: .cfi_def_cfa_offset 336
; SZ13-NEXT: larl %r1, .LCPI91_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI91_1
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: larl %r1, .LCPI91_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI91_3
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 288(%r15)
; SZ13-NEXT: br %r14
entry:
%min = call <2 x double> @llvm.experimental.constrained.minnum.v2f64(
<2 x double> <double 43.0, double 42.0>,
<2 x double> <double 41.0, double 40.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %min
}
define <3 x float> @constrained_vector_minnum_v3f32() {
; S390X-LABEL: constrained_vector_minnum_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI92_0
; S390X-NEXT: le %f8, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI92_1
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: brasl %r14, fminf@PLT
; S390X-NEXT: larl %r1, .LCPI92_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI92_3
; S390X-NEXT: le %f2, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, fminf@PLT
; S390X-NEXT: larl %r1, .LCPI92_4
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f10, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: ler %f2, %f8
; S390X-NEXT: brasl %r14, fminf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f9
; S390X-NEXT: ler %f2, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_minnum_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -200
; SZ13-NEXT: .cfi_def_cfa_offset 360
; SZ13-NEXT: std %f8, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: larl %r1, .LCPI92_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI92_1
; SZ13-NEXT: lde %f8, 0(%r1)
; SZ13-NEXT: ldr %f2, %f8
; SZ13-NEXT: brasl %r14, fminf@PLT
; SZ13-NEXT: larl %r1, .LCPI92_2
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: brasl %r14, fminf@PLT
; SZ13-NEXT: larl %r1, .LCPI92_3
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI92_4
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fminf@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0s killed $f0s def $v0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vrepf %v1, %v1, 0
; SZ13-NEXT: vmrhg %v24, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%min = call <3 x float> @llvm.experimental.constrained.minnum.v3f32(
<3 x float> <float 43.0, float 44.0, float 45.0>,
<3 x float> <float 41.0, float 42.0, float 43.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %min
}
define void @constrained_vector_minnum_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_minnum_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -192
; S390X-NEXT: .cfi_def_cfa_offset 352
; S390X-NEXT: std %f8, 184(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f11, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: .cfi_offset %f11, -192
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: larl %r1, .LCPI93_0
; S390X-NEXT: ldeb %f9, 0(%r1)
; S390X-NEXT: ld %f10, 8(%r2)
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: ldr %f11, %f0
; S390X-NEXT: ldr %f0, %f10
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f10, 8(%r13)
; S390X-NEXT: std %f11, 0(%r13)
; S390X-NEXT: ld %f8, 184(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f11, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_minnum_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r13, %r15, 104(%r15)
; SZ13-NEXT: .cfi_offset %r13, -56
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -208
; SZ13-NEXT: .cfi_def_cfa_offset 368
; SZ13-NEXT: std %f8, 200(%r15) # 8-byte Folded Spill
; SZ13-NEXT: std %f9, 192(%r15) # 8-byte Folded Spill
; SZ13-NEXT: .cfi_offset %f8, -168
; SZ13-NEXT: .cfi_offset %f9, -176
; SZ13-NEXT: larl %r1, .LCPI93_0
; SZ13-NEXT: ldeb %f9, 0(%r1)
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: ld %f8, 16(%r2)
; SZ13-NEXT: ldr %f2, %f9
; SZ13-NEXT: lgr %r13, %r2
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: vl %v0, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ldr %f2, %f9
; SZ13-NEXT: vrepg %v0, %v0, 1
; SZ13-NEXT: # kill: def $f0d killed $f0d killed $v0
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v1, %v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldr %f0, %f8
; SZ13-NEXT: ldr %f2, %f9
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: std %f0, 16(%r13)
; SZ13-NEXT: vl %v0, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: ld %f8, 200(%r15) # 8-byte Folded Reload
; SZ13-NEXT: ld %f9, 192(%r15) # 8-byte Folded Reload
; SZ13-NEXT: vst %v0, 0(%r13), 4
; SZ13-NEXT: lmg %r13, %r15, 312(%r15)
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%min = call <3 x double> @llvm.experimental.constrained.minnum.v3f64(
<3 x double> %b,
<3 x double> <double 3.0, double 3.0, double 3.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %min, <3 x double>* %a
ret void
}
define <4 x double> @constrained_vector_minnum_v4f64() {
; S390X-LABEL: constrained_vector_minnum_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: larl %r1, .LCPI94_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI94_1
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: larl %r1, .LCPI94_2
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI94_3
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: larl %r1, .LCPI94_4
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI94_5
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: larl %r1, .LCPI94_6
; S390X-NEXT: ldeb %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI94_7
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, fmin@PLT
; S390X-NEXT: ldr %f6, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ldr %f2, %f9
; S390X-NEXT: ldr %f4, %f10
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 296(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_minnum_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: stmg %r14, %r15, 112(%r15)
; SZ13-NEXT: .cfi_offset %r14, -48
; SZ13-NEXT: .cfi_offset %r15, -40
; SZ13-NEXT: aghi %r15, -192
; SZ13-NEXT: .cfi_def_cfa_offset 352
; SZ13-NEXT: larl %r1, .LCPI94_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI94_1
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: larl %r1, .LCPI94_2
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI94_3
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: vl %v1, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v0, %v0, %v1
; SZ13-NEXT: larl %r1, .LCPI94_4
; SZ13-NEXT: vst %v0, 176(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI94_5
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: larl %r1, .LCPI94_6
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vst %v0, 160(%r15), 3 # 16-byte Folded Spill
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI94_7
; SZ13-NEXT: ldeb %f2, 0(%r1)
; SZ13-NEXT: brasl %r14, fmin@PLT
; SZ13-NEXT: vl %v1, 160(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: vl %v24, 176(%r15), 3 # 16-byte Folded Reload
; SZ13-NEXT: # kill: def $f0d killed $f0d def $v0
; SZ13-NEXT: vmrhg %v26, %v0, %v1
; SZ13-NEXT: lmg %r14, %r15, 304(%r15)
; SZ13-NEXT: br %r14
entry:
%min = call <4 x double> @llvm.experimental.constrained.minnum.v4f64(
<4 x double> <double 44.0, double 45.0,
double 46.0, double 47.0>,
<4 x double> <double 40.0, double 41.0,
double 42.0, double 43.0>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x double> %min
}
define <1 x float> @constrained_vector_fptrunc_v1f64() {
; S390X-LABEL: constrained_vector_fptrunc_v1f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI95_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: ledbr %f0, %f0
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fptrunc_v1f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI95_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: wledb %v24, %f0, 0, 0
; SZ13-NEXT: br %r14
entry:
%result = call <1 x float> @llvm.experimental.constrained.fptrunc.v1f32.v1f64(
<1 x double><double 42.1>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %result
}
define <2 x float> @constrained_vector_fptrunc_v2f64() {
; S390X-LABEL: constrained_vector_fptrunc_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI96_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI96_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ledbr %f2, %f0
; S390X-NEXT: ledbr %f0, %f1
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fptrunc_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI96_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI96_1
; SZ13-NEXT: ld %f1, 0(%r1)
; SZ13-NEXT: ledbra %f0, 0, %f0, 0
; SZ13-NEXT: ledbra %f1, 0, %f1, 0
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: vmrhg %v24, %v0, %v0
; SZ13-NEXT: br %r14
entry:
%result = call <2 x float> @llvm.experimental.constrained.fptrunc.v2f32.v2f64(
<2 x double><double 42.1, double 42.2>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x float> %result
}
define void @constrained_vector_fptrunc_v3f64(<3 x double>* %src, <3 x float>* %dest) {
; S390X-LABEL: constrained_vector_fptrunc_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f1, 16(%r2)
; S390X-NEXT: ld %f2, 8(%r2)
; S390X-NEXT: ledbr %f0, %f0
; S390X-NEXT: lgdr %r0, %f0
; S390X-NEXT: nilf %r0, 0
; S390X-NEXT: ledbr %f0, %f2
; S390X-NEXT: lgdr %r1, %f0
; S390X-NEXT: srlg %r1, %r1, 32
; S390X-NEXT: lr %r0, %r1
; S390X-NEXT: ledbr %f0, %f1
; S390X-NEXT: ste %f0, 8(%r3)
; S390X-NEXT: stg %r0, 0(%r3)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fptrunc_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ledbra %f2, 0, %f1, 0
; SZ13-NEXT: vrepg %v1, %v1, 1
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: ledbra %f1, 0, %f1, 0
; SZ13-NEXT: ledbra %f0, 0, %f0, 0
; SZ13-NEXT: vmrhf %v1, %v2, %v1
; SZ13-NEXT: vmrhg %v1, %v1, %v1
; SZ13-NEXT: ste %f0, 8(%r3)
; SZ13-NEXT: vsteg %v1, 0(%r3), 0
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %src
%result = call <3 x float> @llvm.experimental.constrained.fptrunc.v3f32.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x float> %result, <3 x float>* %dest
ret void
}
define <4 x float> @constrained_vector_fptrunc_v4f64() {
; S390X-LABEL: constrained_vector_fptrunc_v4f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI98_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI98_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI98_2
; S390X-NEXT: ld %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI98_3
; S390X-NEXT: ld %f3, 0(%r1)
; S390X-NEXT: ledbr %f6, %f0
; S390X-NEXT: ledbr %f4, %f1
; S390X-NEXT: ledbr %f2, %f2
; S390X-NEXT: ledbr %f0, %f3
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fptrunc_v4f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI98_0
; SZ13-NEXT: ld %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI98_1
; SZ13-NEXT: ld %f1, 0(%r1)
; SZ13-NEXT: ledbra %f0, 0, %f0, 0
; SZ13-NEXT: ledbra %f1, 0, %f1, 0
; SZ13-NEXT: larl %r1, .LCPI98_2
; SZ13-NEXT: vmrhf %v0, %v1, %v0
; SZ13-NEXT: ld %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI98_3
; SZ13-NEXT: ld %f2, 0(%r1)
; SZ13-NEXT: ledbra %f1, 0, %f1, 0
; SZ13-NEXT: ledbra %f2, 0, %f2, 0
; SZ13-NEXT: vmrhf %v1, %v2, %v1
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%result = call <4 x float> @llvm.experimental.constrained.fptrunc.v4f32.v4f64(
<4 x double><double 42.1, double 42.2,
double 42.3, double 42.4>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <4 x float> %result
}
define <1 x double> @constrained_vector_fpext_v1f32() {
; S390X-LABEL: constrained_vector_fpext_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI99_0
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fpext_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI99_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%result = call <1 x double> @llvm.experimental.constrained.fpext.v1f64.v1f32(
<1 x float><float 42.0>,
metadata !"fpexcept.strict")
ret <1 x double> %result
}
define <2 x double> @constrained_vector_fpext_v2f32() {
; S390X-LABEL: constrained_vector_fpext_v2f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI100_0
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI100_1
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fpext_v2f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI100_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI100_1
; SZ13-NEXT: ldeb %f1, 0(%r1)
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%result = call <2 x double> @llvm.experimental.constrained.fpext.v2f64.v2f32(
<2 x float><float 42.0, float 43.0>,
metadata !"fpexcept.strict")
ret <2 x double> %result
}
define void @constrained_vector_fpext_v3f64(<3 x float>* %src, <3 x double>* %dest) {
; S390X-LABEL: constrained_vector_fpext_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: lg %r0, 0(%r2)
; S390X-NEXT: sllg %r1, %r0, 32
; S390X-NEXT: ldgr %f0, %r1
; S390X-NEXT: nilf %r0, 0
; S390X-NEXT: ldeb %f1, 8(%r2)
; S390X-NEXT: ldgr %f2, %r0
; S390X-NEXT: ldebr %f2, %f2
; S390X-NEXT: ldebr %f0, %f0
; S390X-NEXT: std %f1, 16(%r3)
; S390X-NEXT: std %f0, 8(%r3)
; S390X-NEXT: std %f2, 0(%r3)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fpext_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v0, 0(%r2), 4
; SZ13-NEXT: vrepf %v2, %v0, 1
; SZ13-NEXT: ldebr %f1, %f0
; SZ13-NEXT: ldebr %f2, %f2
; SZ13-NEXT: vrepf %v0, %v0, 2
; SZ13-NEXT: ldebr %f0, %f0
; SZ13-NEXT: vmrhg %v1, %v1, %v2
; SZ13-NEXT: std %f0, 16(%r3)
; SZ13-NEXT: vst %v1, 0(%r3), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x float>, <3 x float>* %src
%result = call <3 x double> @llvm.experimental.constrained.fpext.v3f64.v3f32(
<3 x float> %b,
metadata !"fpexcept.strict")
store <3 x double> %result, <3 x double>* %dest
ret void
}
define <4 x double> @constrained_vector_fpext_v4f32() {
; S390X-LABEL: constrained_vector_fpext_v4f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: larl %r1, .LCPI102_0
; S390X-NEXT: ldeb %f6, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI102_1
; S390X-NEXT: ldeb %f4, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI102_2
; S390X-NEXT: ldeb %f2, 0(%r1)
; S390X-NEXT: larl %r1, .LCPI102_3
; S390X-NEXT: ldeb %f0, 0(%r1)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_fpext_v4f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI102_0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI102_1
; SZ13-NEXT: ldeb %f1, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI102_2
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: ldeb %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI102_3
; SZ13-NEXT: ldeb %f1, 0(%r1)
; SZ13-NEXT: vmrhg %v26, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%result = call <4 x double> @llvm.experimental.constrained.fpext.v4f64.v4f32(
<4 x float><float 42.0, float 43.0,
float 44.0, float 45.0>,
metadata !"fpexcept.strict")
ret <4 x double> %result
}
define <1 x float> @constrained_vector_ceil_v1f32() {
; S390X-LABEL: constrained_vector_ceil_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI103_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, ceilf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_ceil_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 2, 9
; SZ13-NEXT: fiebra %f0, 6, %f0, 4
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%ceil = call <1 x float> @llvm.experimental.constrained.ceil.v1f32(
<1 x float> <float 1.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %ceil
}
define <2 x double> @constrained_vector_ceil_v2f64() {
; S390X-LABEL: constrained_vector_ceil_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI104_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, ceil@PLT
; S390X-NEXT: larl %r1, .LCPI104_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, ceil@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_ceil_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI104_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v24, %v0, 4, 6
; SZ13-NEXT: br %r14
entry:
%ceil = call <2 x double> @llvm.experimental.constrained.ceil.v2f64(
<2 x double> <double 1.1, double 1.9>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %ceil
}
define <3 x float> @constrained_vector_ceil_v3f32() {
; S390X-LABEL: constrained_vector_ceil_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI105_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, ceilf@PLT
; S390X-NEXT: larl %r1, .LCPI105_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, ceilf@PLT
; S390X-NEXT: larl %r1, .LCPI105_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, ceilf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_ceil_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI105_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI105_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: vgmf %v1, 2, 9
; SZ13-NEXT: fiebra %f0, 6, %f0, 4
; SZ13-NEXT: fiebra %f1, 6, %f1, 4
; SZ13-NEXT: fiebra %f2, 6, %f2, 4
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%ceil = call <3 x float> @llvm.experimental.constrained.ceil.v3f32(
<3 x float> <float 1.5, float 2.5, float 3.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %ceil
}
define void @constrained_vector_ceil_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_ceil_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, ceil@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, ceil@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, ceil@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_ceil_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: vfidb %v1, %v1, 4, 6
; SZ13-NEXT: fidbra %f0, 6, %f0, 4
; SZ13-NEXT: std %f0, 16(%r2)
; SZ13-NEXT: vst %v1, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%ceil = call <3 x double> @llvm.experimental.constrained.ceil.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %ceil, <3 x double>* %a
ret void
}
define <1 x float> @constrained_vector_floor_v1f32() {
; S390X-LABEL: constrained_vector_floor_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI107_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, floorf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_floor_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 2, 9
; SZ13-NEXT: fiebra %f0, 7, %f0, 4
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%floor = call <1 x float> @llvm.experimental.constrained.floor.v1f32(
<1 x float> <float 1.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %floor
}
define <2 x double> @constrained_vector_floor_v2f64() {
; S390X-LABEL: constrained_vector_floor_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI108_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, floor@PLT
; S390X-NEXT: larl %r1, .LCPI108_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, floor@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_floor_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI108_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v24, %v0, 4, 7
; SZ13-NEXT: br %r14
entry:
%floor = call <2 x double> @llvm.experimental.constrained.floor.v2f64(
<2 x double> <double 1.1, double 1.9>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %floor
}
define <3 x float> @constrained_vector_floor_v3f32() {
; S390X-LABEL: constrained_vector_floor_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI109_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, floorf@PLT
; S390X-NEXT: larl %r1, .LCPI109_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, floorf@PLT
; S390X-NEXT: larl %r1, .LCPI109_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, floorf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_floor_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI109_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI109_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: vgmf %v1, 2, 9
; SZ13-NEXT: fiebra %f0, 7, %f0, 4
; SZ13-NEXT: fiebra %f1, 7, %f1, 4
; SZ13-NEXT: fiebra %f2, 7, %f2, 4
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%floor = call <3 x float> @llvm.experimental.constrained.floor.v3f32(
<3 x float> <float 1.5, float 2.5, float 3.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %floor
}
define void @constrained_vector_floor_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_floor_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, floor@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, floor@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, floor@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_floor_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: vfidb %v1, %v1, 4, 7
; SZ13-NEXT: fidbra %f0, 7, %f0, 4
; SZ13-NEXT: std %f0, 16(%r2)
; SZ13-NEXT: vst %v1, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%floor = call <3 x double> @llvm.experimental.constrained.floor.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %floor, <3 x double>* %a
ret void
}
define <1 x float> @constrained_vector_round_v1f32() {
; S390X-LABEL: constrained_vector_round_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI111_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, roundf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_round_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 2, 9
; SZ13-NEXT: fiebra %f0, 1, %f0, 4
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%round = call <1 x float> @llvm.experimental.constrained.round.v1f32(
<1 x float> <float 1.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %round
}
define <2 x double> @constrained_vector_round_v2f64() {
; S390X-LABEL: constrained_vector_round_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI112_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, round@PLT
; S390X-NEXT: larl %r1, .LCPI112_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, round@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_round_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI112_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v24, %v0, 4, 1
; SZ13-NEXT: br %r14
entry:
%round = call <2 x double> @llvm.experimental.constrained.round.v2f64(
<2 x double> <double 1.1, double 1.9>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %round
}
define <3 x float> @constrained_vector_round_v3f32() {
; S390X-LABEL: constrained_vector_round_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI113_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, roundf@PLT
; S390X-NEXT: larl %r1, .LCPI113_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, roundf@PLT
; S390X-NEXT: larl %r1, .LCPI113_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, roundf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_round_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI113_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI113_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: vgmf %v1, 2, 9
; SZ13-NEXT: fiebra %f0, 1, %f0, 4
; SZ13-NEXT: fiebra %f1, 1, %f1, 4
; SZ13-NEXT: fiebra %f2, 1, %f2, 4
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%round = call <3 x float> @llvm.experimental.constrained.round.v3f32(
<3 x float> <float 1.5, float 2.5, float 3.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %round
}
define void @constrained_vector_round_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_round_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, round@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, round@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, round@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_round_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: vfidb %v1, %v1, 4, 1
; SZ13-NEXT: fidbra %f0, 1, %f0, 4
; SZ13-NEXT: std %f0, 16(%r2)
; SZ13-NEXT: vst %v1, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%round = call <3 x double> @llvm.experimental.constrained.round.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %round, <3 x double>* %a
ret void
}
define <1 x float> @constrained_vector_trunc_v1f32() {
; S390X-LABEL: constrained_vector_trunc_v1f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -160
; S390X-NEXT: .cfi_def_cfa_offset 320
; S390X-NEXT: larl %r1, .LCPI115_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, truncf@PLT
; S390X-NEXT: lmg %r14, %r15, 272(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_trunc_v1f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vgmf %v0, 2, 9
; SZ13-NEXT: fiebra %f0, 5, %f0, 4
; SZ13-NEXT: vlr %v24, %v0
; SZ13-NEXT: br %r14
entry:
%trunc = call <1 x float> @llvm.experimental.constrained.trunc.v1f32(
<1 x float> <float 1.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <1 x float> %trunc
}
define <2 x double> @constrained_vector_trunc_v2f64() {
; S390X-LABEL: constrained_vector_trunc_v2f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -168
; S390X-NEXT: .cfi_def_cfa_offset 328
; S390X-NEXT: std %f8, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: larl %r1, .LCPI116_0
; S390X-NEXT: ld %f0, 0(%r1)
; S390X-NEXT: brasl %r14, trunc@PLT
; S390X-NEXT: larl %r1, .LCPI116_1
; S390X-NEXT: ld %f1, 0(%r1)
; S390X-NEXT: ldr %f8, %f0
; S390X-NEXT: ldr %f0, %f1
; S390X-NEXT: brasl %r14, trunc@PLT
; S390X-NEXT: ldr %f2, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: ld %f8, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 280(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_trunc_v2f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI116_0
; SZ13-NEXT: vl %v0, 0(%r1), 3
; SZ13-NEXT: vfidb %v24, %v0, 4, 5
; SZ13-NEXT: br %r14
entry:
%trunc = call <2 x double> @llvm.experimental.constrained.trunc.v2f64(
<2 x double> <double 1.1, double 1.9>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <2 x double> %trunc
}
define <3 x float> @constrained_vector_trunc_v3f32() {
; S390X-LABEL: constrained_vector_trunc_v3f32:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r14, %r15, 112(%r15)
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -176
; S390X-NEXT: .cfi_def_cfa_offset 336
; S390X-NEXT: std %f8, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: larl %r1, .LCPI117_0
; S390X-NEXT: le %f0, 0(%r1)
; S390X-NEXT: brasl %r14, truncf@PLT
; S390X-NEXT: larl %r1, .LCPI117_1
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f8, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, truncf@PLT
; S390X-NEXT: larl %r1, .LCPI117_2
; S390X-NEXT: le %f1, 0(%r1)
; S390X-NEXT: ler %f9, %f0
; S390X-NEXT: ler %f0, %f1
; S390X-NEXT: brasl %r14, truncf@PLT
; S390X-NEXT: ler %f4, %f0
; S390X-NEXT: ler %f0, %f8
; S390X-NEXT: ler %f2, %f9
; S390X-NEXT: ld %f8, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r14, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_trunc_v3f32:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: larl %r1, .LCPI117_0
; SZ13-NEXT: lde %f0, 0(%r1)
; SZ13-NEXT: larl %r1, .LCPI117_1
; SZ13-NEXT: lde %f2, 0(%r1)
; SZ13-NEXT: vgmf %v1, 2, 9
; SZ13-NEXT: fiebra %f0, 5, %f0, 4
; SZ13-NEXT: fiebra %f1, 5, %f1, 4
; SZ13-NEXT: fiebra %f2, 5, %f2, 4
; SZ13-NEXT: vmrhf %v1, %v1, %v2
; SZ13-NEXT: vrepf %v0, %v0, 0
; SZ13-NEXT: vmrhg %v24, %v1, %v0
; SZ13-NEXT: br %r14
entry:
%trunc = call <3 x float> @llvm.experimental.constrained.trunc.v3f32(
<3 x float> <float 1.5, float 2.5, float 3.5>,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
ret <3 x float> %trunc
}
define void @constrained_vector_trunc_v3f64(<3 x double>* %a) {
; S390X-LABEL: constrained_vector_trunc_v3f64:
; S390X: # %bb.0: # %entry
; S390X-NEXT: stmg %r13, %r15, 104(%r15)
; S390X-NEXT: .cfi_offset %r13, -56
; S390X-NEXT: .cfi_offset %r14, -48
; S390X-NEXT: .cfi_offset %r15, -40
; S390X-NEXT: aghi %r15, -184
; S390X-NEXT: .cfi_def_cfa_offset 344
; S390X-NEXT: std %f8, 176(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f9, 168(%r15) # 8-byte Folded Spill
; S390X-NEXT: std %f10, 160(%r15) # 8-byte Folded Spill
; S390X-NEXT: .cfi_offset %f8, -168
; S390X-NEXT: .cfi_offset %f9, -176
; S390X-NEXT: .cfi_offset %f10, -184
; S390X-NEXT: lgr %r13, %r2
; S390X-NEXT: ld %f8, 16(%r2)
; S390X-NEXT: ld %f0, 0(%r2)
; S390X-NEXT: ld %f9, 8(%r2)
; S390X-NEXT: brasl %r14, trunc@PLT
; S390X-NEXT: ldr %f10, %f0
; S390X-NEXT: ldr %f0, %f9
; S390X-NEXT: brasl %r14, trunc@PLT
; S390X-NEXT: ldr %f9, %f0
; S390X-NEXT: ldr %f0, %f8
; S390X-NEXT: brasl %r14, trunc@PLT
; S390X-NEXT: std %f0, 16(%r13)
; S390X-NEXT: std %f9, 8(%r13)
; S390X-NEXT: std %f10, 0(%r13)
; S390X-NEXT: ld %f8, 176(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f9, 168(%r15) # 8-byte Folded Reload
; S390X-NEXT: ld %f10, 160(%r15) # 8-byte Folded Reload
; S390X-NEXT: lmg %r13, %r15, 288(%r15)
; S390X-NEXT: br %r14
;
; SZ13-LABEL: constrained_vector_trunc_v3f64:
; SZ13: # %bb.0: # %entry
; SZ13-NEXT: vl %v1, 0(%r2), 4
; SZ13-NEXT: ld %f0, 16(%r2)
; SZ13-NEXT: vfidb %v1, %v1, 4, 5
; SZ13-NEXT: fidbra %f0, 5, %f0, 4
; SZ13-NEXT: std %f0, 16(%r2)
; SZ13-NEXT: vst %v1, 0(%r2), 4
; SZ13-NEXT: br %r14
entry:
%b = load <3 x double>, <3 x double>* %a
%trunc = call <3 x double> @llvm.experimental.constrained.trunc.v3f64(
<3 x double> %b,
metadata !"round.dynamic",
metadata !"fpexcept.strict")
store <3 x double> %trunc, <3 x double>* %a
ret void
}
declare <2 x double> @llvm.experimental.constrained.fadd.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fsub.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fmul.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fdiv.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.frem.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sqrt.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.pow.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.powi.v2f64(<2 x double>, i32, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.sin.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.cos.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.exp.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.exp2.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.log.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.log10.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.log2.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.rint.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.nearbyint.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.maxnum.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.minnum.v2f64(<2 x double>, <2 x double>, metadata, metadata)
declare <2 x float> @llvm.experimental.constrained.fptrunc.v2f32.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.fpext.v2f64.v2f32(<2 x float>, metadata)
declare <2 x double> @llvm.experimental.constrained.ceil.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.floor.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.round.v2f64(<2 x double>, metadata, metadata)
declare <2 x double> @llvm.experimental.constrained.trunc.v2f64(<2 x double>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fadd.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fsub.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fmul.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fdiv.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.frem.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.sqrt.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.pow.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.powi.v1f32(<1 x float>, i32, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.sin.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.cos.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.exp.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.exp2.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.log.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.log10.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.log2.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.rint.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.nearbyint.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.maxnum.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.minnum.v1f32(<1 x float>, <1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.fptrunc.v1f32.v1f64(<1 x double>, metadata, metadata)
declare <1 x double> @llvm.experimental.constrained.fpext.v1f64.v1f32(<1 x float>, metadata)
declare <1 x float> @llvm.experimental.constrained.ceil.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.floor.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.round.v1f32(<1 x float>, metadata, metadata)
declare <1 x float> @llvm.experimental.constrained.trunc.v1f32(<1 x float>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fadd.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fadd.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fsub.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fsub.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fmul.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fmul.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fdiv.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fdiv.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.frem.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.frem.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.sqrt.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.sqrt.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.pow.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.pow.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.powi.v3f32(<3 x float>, i32, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.powi.v3f64(<3 x double>, i32, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.sin.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.sin.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.cos.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.cos.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.exp.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.exp.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.exp2.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.exp2.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.log.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.log.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.log10.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.log10.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.log2.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.log2.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.rint.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.rint.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.nearbyint.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.nearbyint.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.maxnum.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.maxnum.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.minnum.v3f32(<3 x float>, <3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.minnum.v3f64(<3 x double>, <3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.fptrunc.v3f32.v3f64(<3 x double>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.fpext.v3f64.v3f32(<3 x float>, metadata)
declare <3 x float> @llvm.experimental.constrained.ceil.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.ceil.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.floor.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.floor.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.round.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.round.v3f64(<3 x double>, metadata, metadata)
declare <3 x float> @llvm.experimental.constrained.trunc.v3f32(<3 x float>, metadata, metadata)
declare <3 x double> @llvm.experimental.constrained.trunc.v3f64(<3 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fadd.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fsub.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fmul.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fdiv.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.frem.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.sqrt.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.pow.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.powi.v4f64(<4 x double>, i32, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.sin.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.cos.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.exp.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.exp2.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.log.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.log10.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.log2.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.rint.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.nearbyint.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.maxnum.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.minnum.v4f64(<4 x double>, <4 x double>, metadata, metadata)
declare <4 x float> @llvm.experimental.constrained.fptrunc.v4f32.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.fpext.v4f64.v4f32(<4 x float>, metadata)
declare <4 x double> @llvm.experimental.constrained.ceil.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.floor.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.round.v4f64(<4 x double>, metadata, metadata)
declare <4 x double> @llvm.experimental.constrained.trunc.v4f64(<4 x double>, metadata, metadata)