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/Mips/fmadd1.ll

375 lines
16 KiB
LLVM
Raw Normal View History

Re-commit: [mips] abs.[ds], and neg.[ds] should be allowed regardless of -enable-no-nans-fp-math Summary: They behave in accordance with the Has2008 and ABS2008 configuration bits of the processor which are used to select between the 1985 and 2008 versions of IEEE 754. In 1985 mode, these instructions are arithmetic (i.e. they raise invalid operation exceptions when given NaN), in 2008 mode they are non-arithmetic (i.e. they are copies). nmadd.[ds], and nmsub.[ds] are still subject to -enable-no-nans-fp-math because the ISA spec does not explicitly state that they obey Has2008 and ABS2008. Fixed the issue with the previous version of this patch (r205628). A pre-existing 'let Predicate =' statement was removing some predicates that were necessary for FP64 to behave correctly. Reviewers: matheusalmeida Reviewed By: matheusalmeida Differential Revision: http://llvm-reviews.chandlerc.com/D3274 llvm-svn: 205844
2014-04-09 17:56:43 +08:00
; Check that madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are supported
; correctly.
; The spec for nmadd.[ds], and nmsub.[ds] does not state that they obey the
; the Has2008 and ABS2008 configuration bits which govern the conformance to
; IEEE 754 (1985) and IEEE 754 (2008). These instructions are therefore only
; available when -enable-no-nans-fp-math is given.
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; RUN: llc < %s -march=mipsel -mcpu=mips32 -enable-no-nans-fp-math | FileCheck %s -check-prefixes=ALL,32-NOMADD,32-NONAN-NOMADD
[mips] Use --check-prefixes where appropriate. NFC. llvm-svn: 273669
2016-06-24 20:23:17 +08:00
; RUN: llc < %s -march=mipsel -mcpu=mips32r2 -enable-no-nans-fp-math | FileCheck %s -check-prefixes=ALL,32R2,32R2-NONAN
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; RUN: llc < %s -march=mipsel -mcpu=mips32r6 -enable-no-nans-fp-math | FileCheck %s -check-prefixes=ALL,32R6-NOMADD,32R6-NONAN-NOMADD
[mips] Use --check-prefixes where appropriate. NFC. llvm-svn: 273669
2016-06-24 20:23:17 +08:00
; RUN: llc < %s -march=mips64el -mcpu=mips64 -target-abi=n64 -enable-no-nans-fp-math | FileCheck %s -check-prefixes=ALL,64,64-NONAN
; RUN: llc < %s -march=mips64el -mcpu=mips64r2 -target-abi=n64 -enable-no-nans-fp-math | FileCheck %s -check-prefixes=ALL,64R2,64R2-NONAN
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; RUN: llc < %s -march=mips64el -mcpu=mips64r6 -target-abi=n64 -enable-no-nans-fp-math | FileCheck %s -check-prefixes=ALL,64R6-NOMADD,64R6-NONAN-NOMADD
; RUN: llc < %s -march=mipsel -mcpu=mips32 | FileCheck %s -check-prefixes=ALL,32-NOMADD,32-NAN-NOMADD
[mips] Use --check-prefixes where appropriate. NFC. llvm-svn: 273669
2016-06-24 20:23:17 +08:00
; RUN: llc < %s -march=mipsel -mcpu=mips32r2 | FileCheck %s -check-prefixes=ALL,32R2,32R2-NAN
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; RUN: llc < %s -march=mipsel -mcpu=mips32r6 | FileCheck %s -check-prefixes=ALL,32R6-NOMADD,32R6-NAN-NOMADD
[mips] Use --check-prefixes where appropriate. NFC. llvm-svn: 273669
2016-06-24 20:23:17 +08:00
; RUN: llc < %s -march=mips64el -mcpu=mips64 -target-abi=n64 | FileCheck %s -check-prefixes=ALL,64,64-NAN
; RUN: llc < %s -march=mips64el -mcpu=mips64r2 -target-abi=n64 | FileCheck %s -check-prefixes=ALL,64R2,64R2-NAN
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; RUN: llc < %s -march=mips64el -mcpu=mips64r6 -target-abi=n64 | FileCheck %s -check-prefixes=ALL,64R6-NOMADD,64R6-NAN-NOMADD
; Check that madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not generated
; when +nomadd attribute is specified.
; Output for mips32 and mips64r6 reused since aforementioned instructions are
; not generated in those cases.
; RUN: llc < %s -march=mipsel -mcpu=mips32r2 -enable-no-nans-fp-math -mattr=+nomadd4 | FileCheck %s -check-prefixes=ALL,32-NOMADD,32-NONAN-NOMADD
; RUN: llc < %s -march=mips64el -mcpu=mips64 -target-abi=n64 -enable-no-nans-fp-math -mattr=+nomadd4 | FileCheck %s -check-prefixes=ALL,64R6-NOMADD,64R6-NONAN-NOMADD
; RUN: llc < %s -march=mips64el -mcpu=mips64r2 -target-abi=n64 -enable-no-nans-fp-math -mattr=+nomadd4 | FileCheck %s -check-prefixes=ALL,64R6-NOMADD,64R6-NONAN-NOMADD
; RUN: llc < %s -march=mipsel -mcpu=mips32r2 -mattr=+nomadd4 | FileCheck %s -check-prefixes=ALL,32-NOMADD,32-NAN-NOMADD
; RUN: llc < %s -march=mips64el -mcpu=mips64 -target-abi=n64 -mattr=+nomadd4 | FileCheck %s -check-prefixes=ALL,64R6-NOMADD,64R6-NAN-NOMADD
; RUN: llc < %s -march=mips64el -mcpu=mips64r2 -target-abi=n64 -mattr=+nomadd4 | FileCheck %s -check-prefixes=ALL,64R6-NOMADD,64R6-NAN-NOMADD
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
define float @FOO0float(float %a, float %b, float %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO0float:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: add.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2: mtc1 $6, $[[T0:f[0-9]+]]
; 32R2: madd.s $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R6-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32R6-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: add.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-DAG: madd.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-DAG: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-DAG: add.s $f0, $[[T0]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2: madd.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2: add.s $f0, $[[T0]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R6-NOMADD-DAG: mul.s $[[T0:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: add.s $[[T1:f[0-9]+]], $[[T0]], $f14
; 64R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul float %a, %b
%add = fadd float %mul, %c
%add1 = fadd float %add, 0.000000e+00
ret float %add1
}
define float @FOO1float(float %a, float %b, float %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO1float:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: sub.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2: mtc1 $6, $[[T0:f[0-9]+]]
; 32R2: msub.s $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R6-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32R6-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: sub.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-DAG: msub.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-DAG: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-DAG: add.s $f0, $[[T0]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2: msub.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2: add.s $f0, $[[T0]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R6-NOMADD-DAG: mul.s $[[T0:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: sub.s $[[T1:f[0-9]+]], $[[T0]], $f14
; 64R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: add.s $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul float %a, %b
%sub = fsub float %mul, %c
%add = fadd float %sub, 0.000000e+00
ret float %add
}
define float @FOO2float(float %a, float %b, float %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO2float:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: add.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NONAN: mtc1 $6, $[[T0:f[0-9]+]]
; 32R2-NONAN: nmadd.s $f0, $[[T0]], $f12, $f14
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NAN: mtc1 $6, $[[T0:f[0-9]+]]
; 32R2-NAN: madd.s $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2-NAN: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2-NAN: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R6-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32R6-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: add.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NONAN: nmadd.s $f0, $f14, $f12, $f13
[MIPS]Multiple and add instructions for Mips are currently available in mips32r2/mips64r2 and later but should also be available in mips4, mips5, and mips64. This patch fixes the requested features and updates the corresponding test files. llvm-svn: 230500
2015-02-25 23:24:37 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NAN: madd.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-NAN: sub.s $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NONAN: nmadd.s $f0, $f14, $f12, $f13
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NAN: madd.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2-NAN: sub.s $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R6-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: add.s $[[T2:f[0-9]+]], $[[T1]], $f14
; 64R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul float %a, %b
%add = fadd float %mul, %c
%sub = fsub float 0.000000e+00, %add
ret float %sub
}
define float @FOO3float(float %a, float %b, float %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO3float:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: mtc1 $6, $[[T0:f[0-9]+]]
; 32-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: sub.s $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NONAN: mtc1 $6, $[[T0:f[0-9]+]]
; 32R2-NONAN: nmsub.s $f0, $[[T0]], $f12, $f14
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NAN: mtc1 $6, $[[T0:f[0-9]+]]
; 32R2-NAN: msub.s $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2-NAN: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2-NAN: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NAN: msub.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-NAN: sub.s $f0, $[[T1]], $[[T0]]
[MIPS]Multiple and add instructions for Mips are currently available in mips32r2/mips64r2 and later but should also be available in mips4, mips5, and mips64. This patch fixes the requested features and updates the corresponding test files. llvm-svn: 230500
2015-02-25 23:24:37 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NONAN: nmsub.s $f0, $f14, $f12, $f13
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NAN: msub.s $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2-NAN: sub.s $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R6-NOMADD-DAG: mul.s $[[T1:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: sub.s $[[T2:f[0-9]+]], $[[T1]], $f14
; 64R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: sub.s $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul float %a, %b
%sub = fsub float %mul, %c
%sub1 = fsub float 0.000000e+00, %sub
ret float %sub1
}
define double @FOO10double(double %a, double %b, double %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO10double:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: add.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: add.d $f0, $[[T1]], $[[T2]]
; 32R2: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R2: madd.d $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2: mthc1 $zero, $[[T2]]
; 32R2: add.d $f0, $[[T1]], $[[T2]]
; 32R6-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: add.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: add.d $f0, $[[T1]], $[[T2]]
; 64-DAG: madd.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-DAG: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-DAG: add.d $f0, $[[T0]], $[[T1]]
; 64R2: madd.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2: add.d $f0, $[[T0]], $[[T1]]
; 64R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: add.d $[[T2:f[0-9]+]], $[[T1]], $f14
; 64R6-NOMADD-DAG: dmtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: add.d $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul double %a, %b
%add = fadd double %mul, %c
%add1 = fadd double %add, 0.000000e+00
ret double %add1
}
define double @FOO11double(double %a, double %b, double %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO11double:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: sub.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: add.d $f0, $[[T1]], $[[T2]]
; 32R2: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R2: msub.d $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2: mthc1 $zero, $[[T2]]
; 32R2: add.d $f0, $[[T1]], $[[T2]]
; 32R6-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: sub.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: add.d $f0, $[[T1]], $[[T2]]
; 64-DAG: msub.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-DAG: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-DAG: add.d $f0, $[[T0]], $[[T1]]
; 64R2: msub.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2: add.d $f0, $[[T0]], $[[T1]]
; 64R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: sub.d $[[T2:f[0-9]+]], $[[T1]], $f14
; 64R6-NOMADD-DAG: dmtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: add.d $f0, $[[T1]], $[[T2]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul double %a, %b
%sub = fsub double %mul, %c
%add = fadd double %sub, 0.000000e+00
ret double %add
}
define double @FOO12double(double %a, double %b, double %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO12double:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: add.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NONAN: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R2-NONAN: nmadd.d $f0, $[[T0]], $f12, $f14
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NAN: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R2-NAN: madd.d $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2-NAN: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2-NAN: mthc1 $zero, $[[T2]]
; 32R2-NAN: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R6-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: add.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NONAN: nmadd.d $f0, $f14, $f12, $f13
[MIPS]Multiple and add instructions for Mips are currently available in mips32r2/mips64r2 and later but should also be available in mips4, mips5, and mips64. This patch fixes the requested features and updates the corresponding test files. llvm-svn: 230500
2015-02-25 23:24:37 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NAN: madd.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-NAN: sub.d $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NONAN: nmadd.d $f0, $f14, $f12, $f13
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NAN: madd.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2-NAN: sub.d $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: add.d $[[T2:f[0-9]+]], $[[T1]], $f14
; 64R6-NOMADD-DAG: dmtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul double %a, %b
%add = fadd double %mul, %c
%sub = fsub double 0.000000e+00, %add
ret double %sub
}
define double @FOO13double(double %a, double %b, double %c) nounwind readnone {
entry:
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
; ALL-LABEL: FOO13double:
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32-NOMADD-DAG: sub.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32-NOMADD-DAG: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NONAN: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R2-NONAN: nmsub.d $f0, $[[T0]], $f12, $f14
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R2-NAN: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R2-NAN: msub.d $[[T1:f[0-9]+]], $[[T0]], $f12, $f14
; 32R2-NAN: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R2-NAN: mthc1 $zero, $[[T2]]
; 32R2-NAN: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 32R6-NOMADD-DAG: ldc1 $[[T0:f[0-9]+]], 16($sp)
; 32R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f14
; 32R6-NOMADD-DAG: sub.d $[[T2:f[0-9]+]], $[[T1]], $[[T0]]
; 32R6-NOMADD-DAG: mtc1 $zero, $[[T2:f[0-9]+]]
; 32R6-NOMADD-DAG: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NONAN: nmsub.d $f0, $f14, $f12, $f13
[MIPS]Multiple and add instructions for Mips are currently available in mips32r2/mips64r2 and later but should also be available in mips4, mips5, and mips64. This patch fixes the requested features and updates the corresponding test files. llvm-svn: 230500
2015-02-25 23:24:37 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64-NAN: msub.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64-NAN: sub.d $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NONAN: nmsub.d $f0, $f14, $f12, $f13
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R2-NAN: msub.d $[[T0:f[0-9]+]], $f14, $f12, $f13
; 64R2-NAN: mtc1 $zero, $[[T1:f[0-9]+]]
; 64R2-NAN: sub.d $f0, $[[T1]], $[[T0]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
[mips] Add madd4 subtarget feature Addition of a feature and a predicate used to control generation of madd.fmt and similar instructions. Patch by Stefan Maksimovic. Differential Revision: https://reviews.llvm.org/D33400 llvm-svn: 304801
2017-06-06 23:33:01 +08:00
; 64R6-NOMADD-DAG: mul.d $[[T1:f[0-9]+]], $f12, $f13
; 64R6-NOMADD-DAG: sub.d $[[T2:f[0-9]+]], $[[T1]], $f14
; 64R6-NOMADD-DAG: dmtc1 $zero, $[[T2:f[0-9]+]]
; 64R6-NOMADD-DAG: sub.d $f0, $[[T2]], $[[T1]]
[mips][mips64r6] madd.[ds], msub.[ds], nmadd.[ds], and nmsub.[ds] are not available on MIPS32r6/MIPS64r6 Summary: This patch updates both the assembler and the code generator. MIPS32r6/MIPS64r6 replaces them with maddf.[ds] and msubf.[ds] which are fused multiply-add/sub operations. We don't emit these yet, this patch only prevents the removed instructions from being emitted. Depends on D3955 Reviewers: jkolek, zoran.jovanovic, vmedic Reviewed By: vmedic Differential Revision: http://reviews.llvm.org/D3956 llvm-svn: 210763
2014-06-12 19:04:18 +08:00
Add definitions of floating point multiply add/sub and negative multiply add/sub instructions. llvm-svn: 151415
2012-02-25 08:21:52 +08:00
%mul = fmul double %a, %b
%sub = fsub double %mul, %c
%sub1 = fsub double 0.000000e+00, %sub
ret double %sub1
}