mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 04:32:44 +01:00
08762f9f1e
An identity COPY like this: %AL = COPY %AL, %EAX<imp-def> has no semantic effect, but encodes liveness information: Further users of %EAX only depend on this instruction even though it does not define the full register. Replace the COPY with a KILL instruction in those cases to maintain this liveness information. (This reverts a small part of r238588 but this time adds a comment explaining why a KILL instruction is useful). llvm-svn: 274952
193 lines
6.2 KiB
LLVM
193 lines
6.2 KiB
LLVM
; RUN: llc -O3 -mcpu=pwr7 -enable-unsafe-fp-math < %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-PWR
|
|
; RUN: llc -O3 -mcpu=a2q -enable-unsafe-fp-math < %s | FileCheck %s -check-prefix=CHECK -check-prefix=CHECK-QPX
|
|
target datalayout = "E-m:e-i64:64-n32:64"
|
|
target triple = "powerpc64-unknown-linux-gnu"
|
|
|
|
; Verify that the first two adds are independent regardless of how the inputs are
|
|
; commuted. The destination registers are used as source registers for the third add.
|
|
|
|
define float @reassociate_adds1(float %x0, float %x1, float %x2, float %x3) {
|
|
; CHECK-LABEL: reassociate_adds1:
|
|
; CHECK: # BB#0:
|
|
; CHECK: fadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK: fadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK: fadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd float %x0, %x1
|
|
%t1 = fadd float %t0, %x2
|
|
%t2 = fadd float %t1, %x3
|
|
ret float %t2
|
|
}
|
|
|
|
define float @reassociate_adds2(float %x0, float %x1, float %x2, float %x3) {
|
|
; CHECK-LABEL: reassociate_adds2:
|
|
; CHECK: # BB#0:
|
|
; CHECK: fadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK: fadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK: fadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd float %x0, %x1
|
|
%t1 = fadd float %x2, %t0
|
|
%t2 = fadd float %t1, %x3
|
|
ret float %t2
|
|
}
|
|
|
|
define float @reassociate_adds3(float %x0, float %x1, float %x2, float %x3) {
|
|
; CHECK-LABEL: reassociate_adds3:
|
|
; CHECK: # BB#0:
|
|
; CHECK: fadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK: fadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK: fadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd float %x0, %x1
|
|
%t1 = fadd float %t0, %x2
|
|
%t2 = fadd float %x3, %t1
|
|
ret float %t2
|
|
}
|
|
|
|
define float @reassociate_adds4(float %x0, float %x1, float %x2, float %x3) {
|
|
; CHECK-LABEL: reassociate_adds4:
|
|
; CHECK: # BB#0:
|
|
; CHECK: fadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK: fadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK: fadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd float %x0, %x1
|
|
%t1 = fadd float %x2, %t0
|
|
%t2 = fadd float %x3, %t1
|
|
ret float %t2
|
|
}
|
|
|
|
; Verify that we reassociate some of these ops. The optimal balanced tree of adds is not
|
|
; produced because that would cost more compile time.
|
|
|
|
define float @reassociate_adds5(float %x0, float %x1, float %x2, float %x3, float %x4, float %x5, float %x6, float %x7) {
|
|
; CHECK-LABEL: reassociate_adds5:
|
|
; CHECK: # BB#0:
|
|
; CHECK: fadds [[REG12:[0-9]+]], 5, 6
|
|
; CHECK: fadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK: fadds [[REG11:[0-9]+]], 3, 4
|
|
; CHECK: fadds [[REG13:[0-9]+]], [[REG12]], 7
|
|
; CHECK: fadds [[REG1:[0-9]+]], [[REG0]], [[REG11]]
|
|
; CHECK: fadds [[REG2:[0-9]+]], [[REG1]], [[REG13]]
|
|
; CHECK: fadds 1, [[REG2]], 8
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd float %x0, %x1
|
|
%t1 = fadd float %t0, %x2
|
|
%t2 = fadd float %t1, %x3
|
|
%t3 = fadd float %t2, %x4
|
|
%t4 = fadd float %t3, %x5
|
|
%t5 = fadd float %t4, %x6
|
|
%t6 = fadd float %t5, %x7
|
|
ret float %t6
|
|
}
|
|
|
|
; Verify that we reassociate vector instructions too.
|
|
|
|
define <4 x float> @vector_reassociate_adds1(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
|
|
; CHECK-LABEL: vector_reassociate_adds1:
|
|
; CHECK: # BB#0:
|
|
; CHECK-QPX: qvfadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK-QPX: qvfadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK-QPX: qvfadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: xvaddsp [[REG0:[0-9]+]], 34, 35
|
|
; CHECK-PWR: xvaddsp [[REG1:[0-9]+]], 36, 37
|
|
; CHECK-PWR: xvaddsp 34, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: # kill
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd <4 x float> %x0, %x1
|
|
%t1 = fadd <4 x float> %t0, %x2
|
|
%t2 = fadd <4 x float> %t1, %x3
|
|
ret <4 x float> %t2
|
|
}
|
|
|
|
define <4 x float> @vector_reassociate_adds2(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
|
|
; CHECK-LABEL: vector_reassociate_adds2:
|
|
; CHECK: # BB#0:
|
|
; CHECK-QPX: qvfadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK-QPX: qvfadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK-QPX: qvfadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: xvaddsp [[REG0:[0-9]+]], 34, 35
|
|
; CHECK-PWR: xvaddsp [[REG1:[0-9]+]], 36, 37
|
|
; CHECK-PWR: xvaddsp 34, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: # kill
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd <4 x float> %x0, %x1
|
|
%t1 = fadd <4 x float> %x2, %t0
|
|
%t2 = fadd <4 x float> %t1, %x3
|
|
ret <4 x float> %t2
|
|
}
|
|
|
|
define <4 x float> @vector_reassociate_adds3(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
|
|
; CHECK-LABEL: vector_reassociate_adds3:
|
|
; CHECK: # BB#0:
|
|
; CHECK-QPX: qvfadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK-QPX: qvfadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK-QPX: qvfadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: xvaddsp [[REG0:[0-9]+]], 34, 35
|
|
; CHECK-PWR: xvaddsp [[REG1:[0-9]+]], 36, 37
|
|
; CHECK-PWR: xvaddsp 34, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: # kill
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd <4 x float> %x0, %x1
|
|
%t1 = fadd <4 x float> %t0, %x2
|
|
%t2 = fadd <4 x float> %x3, %t1
|
|
ret <4 x float> %t2
|
|
}
|
|
|
|
define <4 x float> @vector_reassociate_adds4(<4 x float> %x0, <4 x float> %x1, <4 x float> %x2, <4 x float> %x3) {
|
|
; CHECK-LABEL: vector_reassociate_adds4:
|
|
; CHECK: # BB#0:
|
|
; CHECK-QPX: qvfadds [[REG0:[0-9]+]], 1, 2
|
|
; CHECK-QPX: qvfadds [[REG1:[0-9]+]], 3, 4
|
|
; CHECK-QPX: qvfadds 1, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: xvaddsp [[REG0:[0-9]+]], 34, 35
|
|
; CHECK-PWR: xvaddsp [[REG1:[0-9]+]], 36, 37
|
|
; CHECK-PWR: xvaddsp 34, [[REG0]], [[REG1]]
|
|
; CHECK-PWR: # kill
|
|
; CHECK-NEXT: blr
|
|
|
|
%t0 = fadd <4 x float> %x0, %x1
|
|
%t1 = fadd <4 x float> %x2, %t0
|
|
%t2 = fadd <4 x float> %x3, %t1
|
|
ret <4 x float> %t2
|
|
}
|
|
|
|
define float @reassociate_adds6(float %x0, float %x1, float %x2, float %x3) {
|
|
%t0 = fdiv float %x0, %x1
|
|
%t1 = fadd float %x2, %t0
|
|
%t2 = fadd float %x3, %t1
|
|
ret float %t2
|
|
}
|
|
|
|
define float @reassociate_muls1(float %x0, float %x1, float %x2, float %x3) {
|
|
%t0 = fdiv float %x0, %x1
|
|
%t1 = fmul float %x2, %t0
|
|
%t2 = fmul float %x3, %t1
|
|
ret float %t2
|
|
}
|
|
|
|
define double @reassociate_adds_double(double %x0, double %x1, double %x2, double %x3) {
|
|
%t0 = fdiv double %x0, %x1
|
|
%t1 = fadd double %x2, %t0
|
|
%t2 = fadd double %x3, %t1
|
|
ret double %t2
|
|
}
|
|
|
|
define double @reassociate_muls_double(double %x0, double %x1, double %x2, double %x3) {
|
|
%t0 = fdiv double %x0, %x1
|
|
%t1 = fmul double %x2, %t0
|
|
%t2 = fmul double %x3, %t1
|
|
ret double %t2
|
|
}
|
|
|
|
|