maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/WebAssembly/f16.ll

71 lines
2.4 KiB
LLVM
Raw Normal View History

[WebAssembly] Added default stack-only instruction mode for MC. Summary: Made it convert from register to stack based instructions, and removed the registers. Fixes to related code that was expecting register based instructions. Added the correct testing flag to all tests, depending on what the format they were expecting so far. Translated one test to stack format as example: reg-stackify-stack.ll tested: llvm-lit -v `find test -name WebAssembly` unittests/MC/* Reviewers: dschuff, sunfish Subscribers: sbc100, jgravelle-google, eraman, aheejin, llvm-commits, jfb Differential Revision: https://reviews.llvm.org/D51241 llvm-svn: 340750
2018-08-27 23:45:51 +08:00
; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers | FileCheck %s
; RUN: llc < %s -asm-verbose=false -disable-wasm-fallthrough-return-opt -wasm-keep-registers -fast-isel | FileCheck %s
[WebAssembly] Configure codegen to legalize f16 values. llvm-svn: 295850
2017-02-23 00:28:00 +08:00
; Test that f16 is expanded.
target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
[WebAsembly] Update default triple in test files to wasm32-unknown-unkown. Summary: The final -wasm component has been the default for some time now. Subscribers: jfb, dschuff, jgravelle-google, eraman, aheejin, JDevlieghere, sunfish, llvm-commits Differential Revision: https://reviews.llvm.org/D46342 llvm-svn: 332007
2018-05-11 01:49:11 +08:00
target triple = "wasm32-unknown-unknown"
[WebAssembly] Configure codegen to legalize f16 values. llvm-svn: 295850
2017-02-23 00:28:00 +08:00
[WebAssembly] Support f16 libcalls Add support for f16 libcalls in WebAssembly. This entails adding signatures for the remaining F16 libcalls, and renaming gnu_f2h_ieee/gnu_h2f_ieee to truncsfhf2/extendhfsf2 for consistency between f32 and f64/f128 (compiler-rt already supports this). Differential Revision: https://reviews.llvm.org/D61287 Reviewer: dschuff llvm-svn: 359600
2019-05-01 03:17:59 +08:00
; CHECK-LABEL: demote.f32:
; CHECK-NEXT: .functype demote.f32 (f32) -> (f32){{$}}
[WebAssembly] Massive instruction renaming Summary: An automated renaming of all the instructions listed at https://github.com/WebAssembly/spec/issues/884#issuecomment-426433329 as well as some similarly-named identifiers. Reviewers: aheejin, dschuff, aardappel Subscribers: sbc100, jgravelle-google, eraman, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D56338 llvm-svn: 350609
2019-01-08 14:25:55 +08:00
; CHECK-NEXT: local.get $push[[L0:[0-9]+]]=, 0{{$}}
[WebAssembly] Support f16 libcalls Add support for f16 libcalls in WebAssembly. This entails adding signatures for the remaining F16 libcalls, and renaming gnu_f2h_ieee/gnu_h2f_ieee to truncsfhf2/extendhfsf2 for consistency between f32 and f64/f128 (compiler-rt already supports this). Differential Revision: https://reviews.llvm.org/D61287 Reviewer: dschuff llvm-svn: 359600
2019-05-01 03:17:59 +08:00
; CHECK-NEXT: i32.call $push[[L1:[0-9]+]]=, __truncsfhf2, $pop[[L0]]{{$}}
; CHECK-NEXT: f32.call $push[[L2:[0-9]+]]=, __extendhfsf2, $pop[[L1]]{{$}}
[WebAssembly] Configure codegen to legalize f16 values. llvm-svn: 295850
2017-02-23 00:28:00 +08:00
; CHECK-NEXT: return $pop[[L2]]{{$}}
[WebAssembly] Support f16 libcalls Add support for f16 libcalls in WebAssembly. This entails adding signatures for the remaining F16 libcalls, and renaming gnu_f2h_ieee/gnu_h2f_ieee to truncsfhf2/extendhfsf2 for consistency between f32 and f64/f128 (compiler-rt already supports this). Differential Revision: https://reviews.llvm.org/D61287 Reviewer: dschuff llvm-svn: 359600
2019-05-01 03:17:59 +08:00
define half @demote.f32(float %f) {
[WebAssembly] Configure codegen to legalize f16 values. llvm-svn: 295850
2017-02-23 00:28:00 +08:00
%t = fptrunc float %f to half
ret half %t
}
[WebAssembly] Support f16 libcalls Add support for f16 libcalls in WebAssembly. This entails adding signatures for the remaining F16 libcalls, and renaming gnu_f2h_ieee/gnu_h2f_ieee to truncsfhf2/extendhfsf2 for consistency between f32 and f64/f128 (compiler-rt already supports this). Differential Revision: https://reviews.llvm.org/D61287 Reviewer: dschuff llvm-svn: 359600
2019-05-01 03:17:59 +08:00
; CHECK-LABEL: promote.f32:
; CHECK-NEXT: .functype promote.f32 (f32) -> (f32){{$}}
[WebAssembly] Massive instruction renaming Summary: An automated renaming of all the instructions listed at https://github.com/WebAssembly/spec/issues/884#issuecomment-426433329 as well as some similarly-named identifiers. Reviewers: aheejin, dschuff, aardappel Subscribers: sbc100, jgravelle-google, eraman, sunfish, jfb, llvm-commits Differential Revision: https://reviews.llvm.org/D56338 llvm-svn: 350609
2019-01-08 14:25:55 +08:00
; CHECK-NEXT: local.get $push0=, 0{{$}}
[WebAssembly] Configure codegen to legalize f16 values. llvm-svn: 295850
2017-02-23 00:28:00 +08:00
; CHECK-NEXT: return $pop0{{$}}
[WebAssembly] Support f16 libcalls Add support for f16 libcalls in WebAssembly. This entails adding signatures for the remaining F16 libcalls, and renaming gnu_f2h_ieee/gnu_h2f_ieee to truncsfhf2/extendhfsf2 for consistency between f32 and f64/f128 (compiler-rt already supports this). Differential Revision: https://reviews.llvm.org/D61287 Reviewer: dschuff llvm-svn: 359600
2019-05-01 03:17:59 +08:00
define float @promote.f32(half %f) {
[WebAssembly] Configure codegen to legalize f16 values. llvm-svn: 295850
2017-02-23 00:28:00 +08:00
%t = fpext half %f to float
ret float %t
}
[WebAssembly] Support f16 libcalls Add support for f16 libcalls in WebAssembly. This entails adding signatures for the remaining F16 libcalls, and renaming gnu_f2h_ieee/gnu_h2f_ieee to truncsfhf2/extendhfsf2 for consistency between f32 and f64/f128 (compiler-rt already supports this). Differential Revision: https://reviews.llvm.org/D61287 Reviewer: dschuff llvm-svn: 359600
2019-05-01 03:17:59 +08:00
; CHECK-LABEL: demote.f64:
; CHECK-NEXT: .functype demote.f64 (f64) -> (f32){{$}}
; CHECK-NEXT: local.get $push[[L0:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: i32.call $push[[L1:[0-9]+]]=, __truncdfhf2, $pop[[L0]]{{$}}
; CHECK-NEXT: f32.call $push[[L2:[0-9]+]]=, __extendhfsf2, $pop[[L1]]{{$}}
; CHECK-NEXT: return $pop[[L2]]{{$}}
define half @demote.f64(double %f) {
%t = fptrunc double %f to half
ret half %t
}
; CHECK-LABEL: promote.f64:
; CHECK-NEXT: .functype promote.f64 (f32) -> (f64){{$}}
; CHECK-NEXT: local.get $push[[L0:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: f64.promote_f32 $push[[L1:[0-9]+]]=, $pop[[L0]]{{$}}
; CHECK-NEXT: return $pop[[L1]]{{$}}
define double @promote.f64(half %f) {
%t = fpext half %f to double
ret double %t
}
; CHECK-LABEL: demote.f128:
; CHECK-NEXT: .functype demote.f128 (i64, i64) -> (f32){{$}}
; CHECK-NEXT: local.get $push[[L0:[0-9]+]]=, 0{{$}}
; CHECK-NEXT: local.get $push[[L1:[0-9]+]]=, 1{{$}}
; CHECK-NEXT: i32.call $push[[L2:[0-9]+]]=, __trunctfhf2, $pop[[L0]], $pop[[L1]]{{$}}
; CHECK-NEXT: f32.call $push[[L3:[0-9]+]]=, __extendhfsf2, $pop[[L2]]{{$}}
; CHECK-NEXT: return $pop[[L3]]{{$}}
define half @demote.f128(fp128 %f) {
%t = fptrunc fp128 %f to half
ret half %t
}
; CHECK-LABEL: promote.f128:
; CHECK-NEXT: .functype promote.f128 (i32, f32) -> (){{$}}
; CHECK: call __extendsftf2
; CHECK: i64.store
; CHECK: i64.store
define fp128 @promote.f128(half %f) {
%t = fpext half %f to fp128
ret fp128 %t
}