4bf97aa818
This adds the `llvm.modf` intrinsic, legalization, and lowering (mostly
reusing the lowering for sincos and frexp).
The `llvm.modf` intrinsic takes a floating-point value and returns both
the integral and fractional parts (as a struct).
```
declare { float, float } @llvm.modf.f32(float %Val)
declare { double, double } @llvm.modf.f64(double %Val)
declare { x86_fp80, x86_fp80 } @llvm.modf.f80(x86_fp80 %Val)
declare { fp128, fp128 } @llvm.modf.f128(fp128 %Val)
declare { ppc_fp128, ppc_fp128 } @llvm.modf.ppcf128(ppc_fp128 %Val)
declare { <4 x float>, <4 x float> } @llvm.modf.v4f32(<4 x float> %Val)
```
This corresponds to the libm `modf` function but returns multiple values
in a struct (rather than take output pointers), which makes it easier to
vectorize.
256 lines
9.8 KiB
LLVM
256 lines
9.8 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc -mtriple=aarch64-gnu-linux < %s | FileCheck -check-prefixes=CHECK %s
|
|
|
|
define { half, half } @test_modf_f16(half %a) {
|
|
; CHECK-LABEL: test_modf_f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: fcvt s0, h0
|
|
; CHECK-NEXT: add x0, sp, #12
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr s1, [sp, #12]
|
|
; CHECK-NEXT: fcvt h0, s0
|
|
; CHECK-NEXT: fcvt h1, s1
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%result = call { half, half } @llvm.modf.f16(half %a)
|
|
ret { half, half } %result
|
|
}
|
|
|
|
define half @test_modf_f16_only_use_fractional_part(half %a) {
|
|
; CHECK-LABEL: test_modf_f16_only_use_fractional_part:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: fcvt s0, h0
|
|
; CHECK-NEXT: add x0, sp, #12
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: fcvt h0, s0
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%result = call { half, half } @llvm.modf.f16(half %a)
|
|
%result.0 = extractvalue { half, half } %result, 0
|
|
ret half %result.0
|
|
}
|
|
|
|
define half @test_modf_f16_only_use_integral_part(half %a) {
|
|
; CHECK-LABEL: test_modf_f16_only_use_integral_part:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: fcvt s0, h0
|
|
; CHECK-NEXT: add x0, sp, #12
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr s0, [sp, #12]
|
|
; CHECK-NEXT: fcvt h0, s0
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%result = call { half, half } @llvm.modf.f16(half %a)
|
|
%result.1 = extractvalue { half, half } %result, 1
|
|
ret half %result.1
|
|
}
|
|
|
|
define { <2 x half>, <2 x half> } @test_modf_v2f16(<2 x half> %a) {
|
|
; CHECK-LABEL: test_modf_v2f16:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #64
|
|
; CHECK-NEXT: str x30, [sp, #48] // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: mov h1, v0.h[1]
|
|
; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill
|
|
; CHECK-NEXT: add x0, sp, #44
|
|
; CHECK-NEXT: fcvt s0, h1
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: fcvt h0, s0
|
|
; CHECK-NEXT: add x0, sp, #40
|
|
; CHECK-NEXT: fcvt s1, h1
|
|
; CHECK-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: fmov s0, s1
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: fcvt h2, s0
|
|
; CHECK-NEXT: add x0, sp, #56
|
|
; CHECK-NEXT: mov h1, v1.h[2]
|
|
; CHECK-NEXT: fcvt s0, h1
|
|
; CHECK-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: mov v2.h[1], v1.h[0]
|
|
; CHECK-NEXT: str q2, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: fcvt h2, s0
|
|
; CHECK-NEXT: add x0, sp, #60
|
|
; CHECK-NEXT: mov h1, v1.h[3]
|
|
; CHECK-NEXT: fcvt s0, h1
|
|
; CHECK-NEXT: ldr q1, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: mov v1.h[2], v2.h[0]
|
|
; CHECK-NEXT: str q1, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldp s2, s1, [sp, #40]
|
|
; CHECK-NEXT: fcvt h4, s0
|
|
; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: ldr x30, [sp, #48] // 8-byte Folded Reload
|
|
; CHECK-NEXT: fcvt h3, s1
|
|
; CHECK-NEXT: fcvt h1, s2
|
|
; CHECK-NEXT: ldr s2, [sp, #56]
|
|
; CHECK-NEXT: mov v0.h[3], v4.h[0]
|
|
; CHECK-NEXT: fcvt h2, s2
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-NEXT: mov v1.h[1], v3.h[0]
|
|
; CHECK-NEXT: ldr s3, [sp, #60]
|
|
; CHECK-NEXT: mov v1.h[2], v2.h[0]
|
|
; CHECK-NEXT: fcvt h2, s3
|
|
; CHECK-NEXT: mov v1.h[3], v2.h[0]
|
|
; CHECK-NEXT: // kill: def $d1 killed $d1 killed $q1
|
|
; CHECK-NEXT: add sp, sp, #64
|
|
; CHECK-NEXT: ret
|
|
%result = call { <2 x half>, <2 x half> } @llvm.modf.v2f16(<2 x half> %a)
|
|
ret { <2 x half>, <2 x half> } %result
|
|
}
|
|
|
|
define { float, float } @test_modf_f32(float %a) {
|
|
; CHECK-LABEL: test_modf_f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: add x0, sp, #12
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr s1, [sp, #12]
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%result = call { float, float } @llvm.modf.f32(float %a)
|
|
ret { float, float } %result
|
|
}
|
|
|
|
define { <3 x float>, <3 x float> } @test_modf_v3f32(<3 x float> %a) {
|
|
; CHECK-LABEL: test_modf_v3f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #80
|
|
; CHECK-NEXT: str x30, [sp, #48] // 8-byte Folded Spill
|
|
; CHECK-NEXT: stp x20, x19, [sp, #64] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 80
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w20, -16
|
|
; CHECK-NEXT: .cfi_offset w30, -32
|
|
; CHECK-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov s0, v0.s[1]
|
|
; CHECK-NEXT: add x0, sp, #56
|
|
; CHECK-NEXT: add x19, sp, #56
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
|
|
; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill
|
|
; CHECK-NEXT: add x0, sp, #44
|
|
; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $q0
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
|
|
; CHECK-NEXT: add x0, sp, #60
|
|
; CHECK-NEXT: add x20, sp, #60
|
|
; CHECK-NEXT: mov v0.s[1], v1.s[0]
|
|
; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill
|
|
; CHECK-NEXT: ldr q0, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: mov s0, v0.s[2]
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr s1, [sp, #44]
|
|
; CHECK-NEXT: ldr q2, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
|
|
; CHECK-NEXT: ldr x30, [sp, #48] // 8-byte Folded Reload
|
|
; CHECK-NEXT: ld1 { v1.s }[1], [x19]
|
|
; CHECK-NEXT: mov v2.s[2], v0.s[0]
|
|
; CHECK-NEXT: ld1 { v1.s }[2], [x20]
|
|
; CHECK-NEXT: ldp x20, x19, [sp, #64] // 16-byte Folded Reload
|
|
; CHECK-NEXT: mov v0.16b, v2.16b
|
|
; CHECK-NEXT: add sp, sp, #80
|
|
; CHECK-NEXT: ret
|
|
%result = call { <3 x float>, <3 x float> } @llvm.modf.v3f32(<3 x float> %a)
|
|
ret { <3 x float>, <3 x float> } %result
|
|
}
|
|
|
|
define { <2 x float>, <2 x float> } @test_modf_v2f32(<2 x float> %a) {
|
|
; CHECK-LABEL: test_modf_v2f32:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #64
|
|
; CHECK-NEXT: stp x30, x19, [sp, #48] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill
|
|
; CHECK-NEXT: add x0, sp, #40
|
|
; CHECK-NEXT: add x19, sp, #40
|
|
; CHECK-NEXT: mov s0, v0.s[1]
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
|
|
; CHECK-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: add x0, sp, #44
|
|
; CHECK-NEXT: ldr q0, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $q0
|
|
; CHECK-NEXT: bl modff
|
|
; CHECK-NEXT: ldr s1, [sp, #44]
|
|
; CHECK-NEXT: ldr q2, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $s0 killed $s0 def $q0
|
|
; CHECK-NEXT: ld1 { v1.s }[1], [x19]
|
|
; CHECK-NEXT: ldp x30, x19, [sp, #48] // 16-byte Folded Reload
|
|
; CHECK-NEXT: mov v0.s[1], v2.s[0]
|
|
; CHECK-NEXT: // kill: def $d1 killed $d1 killed $q1
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-NEXT: add sp, sp, #64
|
|
; CHECK-NEXT: ret
|
|
%result = call { <2 x float>, <2 x float> } @llvm.modf.v2f32(<2 x float> %a)
|
|
ret { <2 x float>, <2 x float> } %result
|
|
}
|
|
|
|
define { double, double } @test_modf_f64(double %a) {
|
|
; CHECK-LABEL: test_modf_f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 16
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: add x0, sp, #8
|
|
; CHECK-NEXT: bl modf
|
|
; CHECK-NEXT: ldr d1, [sp, #8]
|
|
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
|
|
; CHECK-NEXT: ret
|
|
%result = call { double, double } @llvm.modf.f64(double %a)
|
|
ret { double, double } %result
|
|
}
|
|
|
|
define { <2 x double>, <2 x double> } @test_modf_v2f64(<2 x double> %a) {
|
|
; CHECK-LABEL: test_modf_v2f64:
|
|
; CHECK: // %bb.0:
|
|
; CHECK-NEXT: sub sp, sp, #64
|
|
; CHECK-NEXT: stp x30, x19, [sp, #48] // 16-byte Folded Spill
|
|
; CHECK-NEXT: .cfi_def_cfa_offset 64
|
|
; CHECK-NEXT: .cfi_offset w19, -8
|
|
; CHECK-NEXT: .cfi_offset w30, -16
|
|
; CHECK-NEXT: str q0, [sp] // 16-byte Folded Spill
|
|
; CHECK-NEXT: mov d0, v0.d[1]
|
|
; CHECK-NEXT: add x0, sp, #32
|
|
; CHECK-NEXT: add x19, sp, #32
|
|
; CHECK-NEXT: bl modf
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: str q0, [sp, #16] // 16-byte Folded Spill
|
|
; CHECK-NEXT: add x0, sp, #40
|
|
; CHECK-NEXT: ldr q0, [sp] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $q0
|
|
; CHECK-NEXT: bl modf
|
|
; CHECK-NEXT: ldr d1, [sp, #40]
|
|
; CHECK-NEXT: ldr q2, [sp, #16] // 16-byte Folded Reload
|
|
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
|
|
; CHECK-NEXT: ld1 { v1.d }[1], [x19]
|
|
; CHECK-NEXT: ldp x30, x19, [sp, #48] // 16-byte Folded Reload
|
|
; CHECK-NEXT: mov v0.d[1], v2.d[0]
|
|
; CHECK-NEXT: add sp, sp, #64
|
|
; CHECK-NEXT: ret
|
|
%result = call { <2 x double>, <2 x double> } @llvm.modf.v2f64(<2 x double> %a)
|
|
ret { <2 x double>, <2 x double> } %result
|
|
}
|