mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
440296ff6f
r319980 added new patterns to the machine combiner for transforming (fsub (fmul x y) z) into (fmla (fneg z) x y). That is, fsub's where the first source operand is an fmul are transformed. We previously only matched the case where the second source operand of an fsub was an fmul, transforming (fsub z (fmul x y)) into (fmls z x y). Now, if we have an fsub where both source operands are fmuls, both of the above patterns are applicable. However, the order in which we add the patterns to the list of candidates determines the transformation that takes place, since only the first pattern that matches will be used. This patch changes the order these two patterns are added to the list of candidates such that we prefer the case where the second source operand is an fmul (the fmls case), rather than the other one (the fmla/fneg case). When both source operands are fmuls, this ordering results in fewer instructions. Differential Revision: https://reviews.llvm.org/D41587 llvm-svn: 321491
162 lines
4.5 KiB
YAML
162 lines
4.5 KiB
YAML
# RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=cortex-a57 -enable-unsafe-fp-math %s | FileCheck --check-prefixes=UNPROFITABLE,ALL %s
|
|
# RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=falkor -enable-unsafe-fp-math %s | FileCheck --check-prefixes=PROFITABLE,ALL %s
|
|
# RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=exynosm1 -enable-unsafe-fp-math %s | FileCheck --check-prefixes=PROFITABLE,ALL %s
|
|
# RUN: llc -run-pass=machine-combiner -o - -mtriple=aarch64-unknown-linux -mcpu=thunderx2t99 -enable-unsafe-fp-math %s | FileCheck --check-prefixes=PROFITABLE,ALL %s
|
|
#
|
|
name: f1_2s
|
|
registers:
|
|
- { id: 0, class: fpr64 }
|
|
- { id: 1, class: fpr64 }
|
|
- { id: 2, class: fpr64 }
|
|
- { id: 3, class: fpr64 }
|
|
- { id: 4, class: fpr64 }
|
|
body: |
|
|
bb.0.entry:
|
|
%2:fpr64 = COPY %d2
|
|
%1:fpr64 = COPY %d1
|
|
%0:fpr64 = COPY %d0
|
|
%3:fpr64 = FMULv2f32 %0, %1
|
|
%4:fpr64 = FSUBv2f32 killed %3, %2
|
|
%d0 = COPY %4
|
|
RET_ReallyLR implicit %d0
|
|
|
|
...
|
|
# UNPROFITABLE-LABEL: name: f1_2s
|
|
# UNPROFITABLE: %3:fpr64 = FMULv2f32 %0, %1
|
|
# UNPROFITABLE-NEXT: FSUBv2f32 killed %3, %2
|
|
#
|
|
# PROFITABLE-LABEL: name: f1_2s
|
|
# PROFITABLE: %5:fpr64 = FNEGv2f32 %2
|
|
# PROFITABLE-NEXT: FMLAv2f32 killed %5, %0, %1
|
|
---
|
|
name: f1_4s
|
|
registers:
|
|
- { id: 0, class: fpr128 }
|
|
- { id: 1, class: fpr128 }
|
|
- { id: 2, class: fpr128 }
|
|
- { id: 3, class: fpr128 }
|
|
- { id: 4, class: fpr128 }
|
|
body: |
|
|
bb.0.entry:
|
|
%2:fpr128 = COPY %q2
|
|
%1:fpr128 = COPY %q1
|
|
%0:fpr128 = COPY %q0
|
|
%3:fpr128 = FMULv4f32 %0, %1
|
|
%4:fpr128 = FSUBv4f32 killed %3, %2
|
|
%q0 = COPY %4
|
|
RET_ReallyLR implicit %q0
|
|
|
|
...
|
|
# UNPROFITABLE-LABEL: name: f1_4s
|
|
# UNPROFITABLE: %3:fpr128 = FMULv4f32 %0, %1
|
|
# UNPROFITABLE-NEXT: FSUBv4f32 killed %3, %2
|
|
#
|
|
# PROFITABLE-LABEL: name: f1_4s
|
|
# PROFITABLE: %5:fpr128 = FNEGv4f32 %2
|
|
# PROFITABLE-NEXT: FMLAv4f32 killed %5, %0, %1
|
|
---
|
|
name: f1_2d
|
|
registers:
|
|
- { id: 0, class: fpr128 }
|
|
- { id: 1, class: fpr128 }
|
|
- { id: 2, class: fpr128 }
|
|
- { id: 3, class: fpr128 }
|
|
- { id: 4, class: fpr128 }
|
|
body: |
|
|
bb.0.entry:
|
|
%2:fpr128 = COPY %q2
|
|
%1:fpr128 = COPY %q1
|
|
%0:fpr128 = COPY %q0
|
|
%3:fpr128 = FMULv2f64 %0, %1
|
|
%4:fpr128 = FSUBv2f64 killed %3, %2
|
|
%q0 = COPY %4
|
|
RET_ReallyLR implicit %q0
|
|
|
|
...
|
|
# UNPROFITABLE-LABEL: name: f1_2d
|
|
# UNPROFITABLE: %3:fpr128 = FMULv2f64 %0, %1
|
|
# UNPROFITABLE-NEXT: FSUBv2f64 killed %3, %2
|
|
#
|
|
# PROFITABLE-LABEL: name: f1_2d
|
|
# PROFITABLE: %5:fpr128 = FNEGv2f64 %2
|
|
# PROFITABLE-NEXT: FMLAv2f64 killed %5, %0, %1
|
|
---
|
|
name: f1_both_fmul_2s
|
|
registers:
|
|
- { id: 0, class: fpr64 }
|
|
- { id: 1, class: fpr64 }
|
|
- { id: 2, class: fpr64 }
|
|
- { id: 3, class: fpr64 }
|
|
- { id: 4, class: fpr64 }
|
|
- { id: 5, class: fpr64 }
|
|
- { id: 6, class: fpr64 }
|
|
body: |
|
|
bb.0.entry:
|
|
%3:fpr64 = COPY %q3
|
|
%2:fpr64 = COPY %q2
|
|
%1:fpr64 = COPY %q1
|
|
%0:fpr64 = COPY %q0
|
|
%4:fpr64 = FMULv2f32 %0, %1
|
|
%5:fpr64 = FMULv2f32 %2, %3
|
|
%6:fpr64 = FSUBv2f32 killed %4, %5
|
|
%q0 = COPY %6
|
|
RET_ReallyLR implicit %q0
|
|
|
|
...
|
|
# ALL-LABEL: name: f1_both_fmul_2s
|
|
# ALL: %4:fpr64 = FMULv2f32 %0, %1
|
|
# ALL-NEXT: FMLSv2f32 killed %4, %2, %3
|
|
---
|
|
name: f1_both_fmul_4s
|
|
registers:
|
|
- { id: 0, class: fpr128 }
|
|
- { id: 1, class: fpr128 }
|
|
- { id: 2, class: fpr128 }
|
|
- { id: 3, class: fpr128 }
|
|
- { id: 4, class: fpr128 }
|
|
- { id: 5, class: fpr128 }
|
|
- { id: 6, class: fpr128 }
|
|
body: |
|
|
bb.0.entry:
|
|
%3:fpr128 = COPY %q3
|
|
%2:fpr128 = COPY %q2
|
|
%1:fpr128 = COPY %q1
|
|
%0:fpr128 = COPY %q0
|
|
%4:fpr128 = FMULv4f32 %0, %1
|
|
%5:fpr128 = FMULv4f32 %2, %3
|
|
%6:fpr128 = FSUBv4f32 killed %4, %5
|
|
%q0 = COPY %6
|
|
RET_ReallyLR implicit %q0
|
|
|
|
...
|
|
# ALL-LABEL: name: f1_both_fmul_4s
|
|
# ALL: %4:fpr128 = FMULv4f32 %0, %1
|
|
# ALL-NEXT: FMLSv4f32 killed %4, %2, %3
|
|
---
|
|
name: f1_both_fmul_2d
|
|
registers:
|
|
- { id: 0, class: fpr128 }
|
|
- { id: 1, class: fpr128 }
|
|
- { id: 2, class: fpr128 }
|
|
- { id: 3, class: fpr128 }
|
|
- { id: 4, class: fpr128 }
|
|
- { id: 5, class: fpr128 }
|
|
- { id: 6, class: fpr128 }
|
|
body: |
|
|
bb.0.entry:
|
|
%3:fpr128 = COPY %q3
|
|
%2:fpr128 = COPY %q2
|
|
%1:fpr128 = COPY %q1
|
|
%0:fpr128 = COPY %q0
|
|
%4:fpr128 = FMULv2f64 %0, %1
|
|
%5:fpr128 = FMULv2f64 %2, %3
|
|
%6:fpr128 = FSUBv2f64 killed %4, %5
|
|
%q0 = COPY %6
|
|
RET_ReallyLR implicit %q0
|
|
|
|
...
|
|
# ALL-LABEL: name: f1_both_fmul_2d
|
|
# ALL: %4:fpr128 = FMULv2f64 %0, %1
|
|
# ALL-NEXT: FMLSv2f64 killed %4, %2, %3
|
|
|