mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
29c427c639
Currently ( D10321, http://reviews.llvm.org/rL239486 ), we can use the machine combiner pass to reassociate the following sequence to reduce the critical path: A = ? op ? B = A op X C = B op Y --> A = ? op ? B = X op Y C = A op B 'op' is currently limited to x86 AVX scalar FP adds (with fast-math on), but in theory, it could be any associative math/logic op (see TODO in code comment). This patch generalizes the pattern match to ignore the instruction that defines 'A'. So instead of a sequence of 3 adds, we now only need to find 2 dependent adds and decide if it's worth reassociating them. This generalization has a compile-time cost because we can now match more instruction sequences and we rely more heavily on the machine combiner to discard sequences where reassociation doesn't improve the critical path. For example, in the new test case: A = M div N B = A add X C = B add Y We'll match 2 reassociation patterns, but this transform doesn't reduce the critical path: A = M div N B = A add Y C = B add X We need the combiner to reject that pattern but select this: A = M div N B = X add Y C = B add A Differential Revision: http://reviews.llvm.org/D10460 llvm-svn: 240361
117 lines
2.5 KiB
LLVM
117 lines
2.5 KiB
LLVM
; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=avx -enable-unsafe-fp-math < %s | FileCheck %s
|
|
|
|
define float @test1(float %a) {
|
|
; CHECK-LABEL: test1:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fadd float %a, %a
|
|
%r = fadd float %t1, %t1
|
|
ret float %r
|
|
}
|
|
|
|
define float @test2(float %a) {
|
|
; CHECK-LABEL: test2:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul float 4.0, %a
|
|
%t2 = fadd float %a, %a
|
|
%r = fadd float %t1, %t2
|
|
ret float %r
|
|
}
|
|
|
|
define float @test3(float %a) {
|
|
; CHECK-LABEL: test3:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul float %a, 4.0
|
|
%t2 = fadd float %a, %a
|
|
%r = fadd float %t1, %t2
|
|
ret float %r
|
|
}
|
|
|
|
define float @test4(float %a) {
|
|
; CHECK-LABEL: test4:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fadd float %a, %a
|
|
%t2 = fmul float 4.0, %a
|
|
%r = fadd float %t1, %t2
|
|
ret float %r
|
|
}
|
|
|
|
define float @test5(float %a) {
|
|
; CHECK-LABEL: test5:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vmulss {{.*}}(%rip), %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fadd float %a, %a
|
|
%t2 = fmul float %a, 4.0
|
|
%r = fadd float %t1, %t2
|
|
ret float %r
|
|
}
|
|
|
|
define float @test6(float %a) {
|
|
; CHECK-LABEL: test6:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul float 2.0, %a
|
|
%t2 = fadd float %a, %a
|
|
%r = fsub float %t1, %t2
|
|
ret float %r
|
|
}
|
|
|
|
define float @test7(float %a) {
|
|
; CHECK-LABEL: test7:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul float %a, 2.0
|
|
%t2 = fadd float %a, %a
|
|
%r = fsub float %t1, %t2
|
|
ret float %r
|
|
}
|
|
|
|
define float @test8(float %a) {
|
|
; CHECK-LABEL: test8:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul float %a, 0.0
|
|
%t2 = fadd float %a, %t1
|
|
ret float %t2
|
|
}
|
|
|
|
define float @test9(float %a) {
|
|
; CHECK-LABEL: test9:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: retq
|
|
%t1 = fmul float 0.0, %a
|
|
%t2 = fadd float %t1, %a
|
|
ret float %t2
|
|
}
|
|
|
|
define float @test10(float %a) {
|
|
; CHECK-LABEL: test10:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fsub float -0.0, %a
|
|
%t2 = fadd float %a, %t1
|
|
ret float %t2
|
|
}
|
|
|
|
define float @test11(float %a) {
|
|
; CHECK-LABEL: test11:
|
|
; CHECK: # BB#0:
|
|
; CHECK-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; CHECK-NEXT: retq
|
|
%t1 = fsub float -0.0, %a
|
|
%t2 = fadd float %a, %t1
|
|
ret float %t2
|
|
}
|
|
|