[ARM] FP16 VSEL codegen

This is a follow up of rL327695 to instruction select more variants of VSELGT
and VSELGE, for which it is necessary to custom lower SELECT.

More work is required in this area, which will be addressed soon:
- more variants need to be regression tested, but this depends on the next point.
- first LowerConstantFP need to be adjusted for fp16 values.

Differential Revision: https://reviews.llvm.org/D45205

llvm-svn: 329788

1 files changed, 142 insertions, 12 deletions

diff --git a/llvm/test/CodeGen/ARM/fp16-instructions.ll b/llvm/test/CodeGen/ARM/fp16-instructions.ll
index 3aef5fc60fd..d61a631da3d 100644
--- a/llvm/test/CodeGen/ARM/fp16-instructions.ll
+++ b/llvm/test/CodeGen/ARM/fp16-instructions.ll
@@ -4,11 +4,11 @@
 
 ; SOFTFP:
 ; RUN: llc < %s -mtriple=arm-none-eabi -mattr=+vfp3        | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-VFP3
-; RUN: llc < %s -mtriple=arm-none-eabi -mattr=+vfp4        | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-FP16
+; RUN: llc < %s -mtriple=arm-none-eabi -mattr=+vfp4        | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-FP16,CHECK-SOFTFP-FP16-A32
 ; RUN: llc < %s -mtriple=arm-none-eabi -mattr=+fullfp16    | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-FULLFP16
 
 ; RUN: llc < %s -mtriple=thumbv7-none-eabi -mattr=+vfp3        | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-VFP3
-; RUN: llc < %s -mtriple=thumbv7-none-eabi -mattr=+vfp4        | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-FP16
+; RUN: llc < %s -mtriple=thumbv7-none-eabi -mattr=+vfp4        | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-FP16,CHECK-SOFTFP-FP16-T32
 ; RUN: llc < %s -mtriple=thumbv7-none-eabi -mattr=+fullfp16    | FileCheck %s --check-prefixes=CHECK,CHECK-SOFTFP-FULLFP16
 
 ; Test fast-isel
@@ -703,37 +703,167 @@ define half @select_cc1()  {
   ret half %2
 
 ; CHECK-LABEL:                 select_cc1:
+
+; CHECK-HARDFP-FULLFP16:	     vcmp.f16 s0, s0
+; CHECK-HARDFP-FULLFP16-NEXT:	 vmrs APSR_nzcv, fpscr
 ; CHECK-HARDFP-FULLFP16:       vseleq.f16  s0, s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-A32:       vcmp.f32 s0, s0
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmoveq.f32 s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-T32:       vcmp.f32 s0, s0
+; CHECK-SOFTFP-FP16-T32:       vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-T32:       it eq
+; CHECK-SOFTFP-FP16-T32:       vmoveq.f32 s{{.}}, s{{.}}
 }
 
+; FIXME: more tests need to be added for VSELGE and VSELGT.
+; That is, more combinations of immediate operands that can or can't
+; be encoded as an FP16 immediate need to be added here.
+;
 ; 36. VSELGE
-define half @select_cc2()  {
+define half @select_cc_ge1()  {
   %1 = fcmp nsz oge half undef, 0xH0001
   %2 = select i1 %1, half 0xHC000, half 0xH0002
   ret half %2
 
-; CHECK-LABEL:                 select_cc2:
-; CHECK-HARDFP-FULLFP16:       vselge.f16  s0, s{{.}}, s{{.}}
+; CHECK-LABEL:                 select_cc_ge1:
+
+; CHECK-HARDFP-FULLFP16:	     vcmpe.f16 s0, s0
+; CHECK-HARDFP-FULLFP16-NEXT:	 vmrs APSR_nzcv, fpscr
+; CHECK-HARDFP-FULLFP16-NEXT:  vselge.f16 s0, s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-A32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmovge.f32 s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-T32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-T32-NEXT:  it ge
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmovge.f32 s{{.}}, s{{.}}
+}
+
+;
+; FIXME: add fcmp ole, ult here.
+;
+
+define half @select_cc_ge3()  {
+  %1 = fcmp nsz ugt half undef, 0xH0001
+  %2 = select i1 %1, half 0xHC000, half 0xH0002
+  ret half %2
+
+; CHECK-LABEL:                 select_cc_ge3:
+
+; CHECK-HARDFP-FULLFP16: 	     vcmpe.f16 s0, s0
+; CHECK-HARDFP-FULLFP16-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-HARDFP-FULLFP16-NEXT:  vselge.f16 s0, s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-A32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmovhi.f32 s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-T32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-T32-NEXT:  it hi
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmovhi.f32 s{{.}}, s{{.}}
 }
 
 ; 37. VSELGT
-define half @select_cc3()  {
+define half @select_cc_gt1()  {
   %1 = fcmp nsz ogt half undef, 0xH0001
   %2 = select i1 %1, half 0xHC000, half 0xH0002
   ret half %2
 
-; CHECK-LABEL:                 select_cc3:
-; CHECK-HARDFP-FULLFP16:       vselgt.f16  s0, s{{.}}, s{{.}}
+; CHECK-LABEL:                 select_cc_gt1:
+
+; CHECK-HARDFP-FULLFP16:	     vcmpe.f16 s0, s0
+; CHECK-HARDFP-FULLFP16-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-HARDFP-FULLFP16-NEXT:  vselgt.f16  s0, s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-A32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmovgt.f32 s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-T32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-T32-NEXT:  it gt
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmovgt.f32 s{{.}}, s{{.}}
 }
 
-; 38. VSELVS
-define half @select_cc4()  {
-  %1 = fcmp nsz ueq half undef, 0xH0001
+define half @select_cc_gt2()  {
+  %1 = fcmp nsz uge half undef, 0xH0001
   %2 = select i1 %1, half 0xHC000, half 0xH0002
   ret half %2
 
+; CHECK-LABEL:                 select_cc_gt2:
+
+; CHECK-HARDFP-FULLFP16:       vcmpe.f16 s0, s0
+; CHECK-HARDFP-FULLFP16-NEXT:  vmrs  APSR_nzcv, fpscr
+; CHECK-HARDFP-FULLFP16-NEXT:  vselgt.f16  s0, s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-A32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmovpl.f32 s{{.}}, s{{.}}
+
+; CHECK-SOFTFP-FP16-T32:       vcmpe.f32 s0, s0
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmrs APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-T32-NEXT:  it pl
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmovpl.f32 s{{.}}, s{{.}}
+}
+
+;
+; FIXME: add fcmp ule, olt here.
+;
+
+; 38. VSELVS
+define float @select_cc4(float %a.coerce) {
+entry:
+  %0 = bitcast float %a.coerce to i32
+  %tmp.0.extract.trunc = trunc i32 %0 to i16
+  %1 = bitcast i16 %tmp.0.extract.trunc to half
+
+  %2 = fcmp nsz ueq half %1, 0xH0001
+  %3 = select i1 %2, half 0xHC000, half 0xH0002
+
+  %4 = bitcast half %3 to i16
+  %tmp4.0.insert.ext = zext i16 %4 to i32
+  %5 = bitcast i32 %tmp4.0.insert.ext to float
+  ret float %5
+
 ; CHECK-LABEL:                 select_cc4:
-; CHECK-HARDFP-FULLFP16:       vselvs.f16  s0, s{{.}}, s{{.}}
+
+; CHECK-HARDFP-FULLFP16:       vldr.16	[[S2:s[0-9]]], .LCPI{{.*}}
+; CHECK-HARDFP-FULLFP16:       vldr.16	[[S4:s[0-9]]], .LCPI{{.*}}
+; CHECK-HARDFP-FULLFP16:       vmov.f16 [[S6:s[0-9]]], #-2.000000e+00
+; CHECK-HARDFP-FULLFP16:       vcmp.f16	s0, [[S2]]
+; CHECK-HARDFP-FULLFP16-NEXT:  vmrs	APSR_nzcv, fpscr
+; CHECK-HARDFP-FULLFP16-NEXT:  vseleq.f16	[[S0:s[0-9]]], [[S6]], [[S4]]
+; CHECK-HARDFP-FULLFP16-NEXT:  vselvs.f16	s0, [[S6]], [[S0]]
+
+; CHECK-SOFTFP-FP16-A32:       vmov	[[S6:s[0-9]]], r0
+; CHECK-SOFTFP-FP16-A32:       vldr	s0, .LCP{{.*}}
+; CHECK-SOFTFP-FP16-A32:       vcvtb.f32.f16	[[S6]], [[S6]]
+; CHECK-SOFTFP-FP16-A32:       vmov.f32	[[S2:s[0-9]]], #-2.000000e+00
+; CHECK-SOFTFP-FP16-A32:       vcmp.f32	[[S6]], s0
+; CHECK-SOFTFP-FP16-A32:       vldr	[[S4:s[0-9]]], .LCPI{{.*}}
+; CHECK-SOFTFP-FP16-A32:       vmrs	APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-A32:       vmoveq.f32	[[S4]], [[S2]]
+; CHECK-SOFTFP-FP16-A32-NEXT:  vmovvs.f32	[[S4]], [[S2]]
+; CHECK-SOFTFP-FP16-A32-NEXT:  vcvtb.f16.f32 s0, [[S4]]
+
+; CHECK-SOFTFP-FP16-T32:       vmov	[[S6:s[0-9]]], r0
+; CHECK-SOFTFP-FP16-T32:       vldr	s0, .LCP{{.*}}
+; CHECK-SOFTFP-FP16-T32:       vcvtb.f32.f16	[[S6]], [[S6]]
+; CHECK-SOFTFP-FP16-T32:       vmov.f32	[[S2:s[0-9]]], #-2.000000e+00
+; CHECK-SOFTFP-FP16-T32:       vcmp.f32	[[S6]], s0
+; CHECK-SOFTFP-FP16-T32:       vldr	[[S4:s[0-9]]], .LCPI{{.*}}
+; CHECK-SOFTFP-FP16-T32:       vmrs	APSR_nzcv, fpscr
+; CHECK-SOFTFP-FP16-T32:       it eq
+; CHECK-SOFTFP-FP16-T32:       vmoveq.f32	[[S4]], [[S2]]
+; CHECK-SOFTFP-FP16-T32:       it vs
+; CHECK-SOFTFP-FP16-T32-NEXT:  vmovvs.f32	[[S4]], [[S2]]
+; CHECK-SOFTFP-FP16-T32-NEXT:  vcvtb.f16.f32 s0, [[S4]]
 }
 
 ; 39. VSQRT - TODO