Page MenuHomePhabricator

Please use GitHub pull requests for new patches. Phabricator shutdown timeline

Differential D47749 Diff 150172 llvm/trunk/test/CodeGen/PowerPC/fmf-propagation.ll

Changeset View

Standalone View

View Options

llvm/trunk/test/CodeGen/PowerPC/fmf-propagation.ll

Show First 20 Lines • Show All 294 Lines • ▼ Show 20 Lines; GLOBAL-NEXT: blr
%mul = fmul fast float %x, 42.0 %mul = fmul fast float %x, 42.0
%fma = call fast float @llvm.fma.f32(float %x, float 7.0, float %mul) %fma = call fast float @llvm.fma.f32(float %x, float 7.0, float %mul)
ret float %fma ret float %fma
} }
; Reduced precision for sqrt is allowed - should use estimate and NR iterations. ; Reduced precision for sqrt is allowed - should use estimate and NR iterations.
; FMFDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_afn:' ; FMFDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_afn:'
; FMFDEBUG: fsqrt afn {{t[0-9]+}} ; FMFDEBUG: fmul afn {{t[0-9]+}}
; FMFDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_afn:' ; FMFDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_afn:'
; GLOBALDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_afn:' ; GLOBALDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_afn:'
; GLOBALDEBUG: fmul reassoc {{t[0-9]+}} ; GLOBALDEBUG: fmul afn {{t[0-9]+}}
; GLOBALDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_afn:' ; GLOBALDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_afn:'
define float @sqrt_afn(float %x) { define float @sqrt_afn(float %x) {
; FMF-LABEL: sqrt_afn: ; FMF-LABEL: sqrt_afn:
; FMF: # %bb.0: ; FMF: # %bb.0:
; FMF-NEXT: xssqrtsp 1, 1 ; FMF-NEXT: xxlxor 0, 0, 0
; FMF-NEXT: fcmpu 0, 1, 0
; FMF-NEXT: beq 0, .LBB10_2
; FMF-NEXT: # %bb.1:
; FMF-NEXT: addis 3, 2, .LCPI10_0@toc@ha
; FMF-NEXT: xsrsqrtesp 3, 1
; FMF-NEXT: addi 3, 3, .LCPI10_0@toc@l
; FMF-NEXT: lfsx 0, 0, 3
; FMF-NEXT: xsmulsp 2, 1, 0
; FMF-NEXT: xsmulsp 4, 3, 3
; FMF-NEXT: xssubsp 2, 2, 1
; FMF-NEXT: xsmulsp 2, 2, 4
; FMF-NEXT: xssubsp 0, 0, 2
; FMF-NEXT: xsmulsp 0, 3, 0
; FMF-NEXT: xsmulsp 0, 0, 1
; FMF-NEXT: .LBB10_2:
; FMF-NEXT: fmr 1, 0
; FMF-NEXT: blr ; FMF-NEXT: blr
; ;
; GLOBAL-LABEL: sqrt_afn: ; GLOBAL-LABEL: sqrt_afn:
; GLOBAL: # %bb.0: ; GLOBAL: # %bb.0:
; GLOBAL-NEXT: xxlxor 0, 0, 0 ; GLOBAL-NEXT: xxlxor 0, 0, 0
; GLOBAL-NEXT: fcmpu 0, 1, 0 ; GLOBAL-NEXT: fcmpu 0, 1, 0
; GLOBAL-NEXT: beq 0, .LBB10_2 ; GLOBAL-NEXT: beq 0, .LBB10_2
; GLOBAL-NEXT: # %bb.1: ; GLOBAL-NEXT: # %bb.1:
; GLOBAL-NEXT: xsrsqrtesp 2, 1 ; GLOBAL-NEXT: xsrsqrtesp 2, 1
Show All 12 Lines
; GLOBAL-NEXT: blr ; GLOBAL-NEXT: blr
%rt = call afn float @llvm.sqrt.f32(float %x) %rt = call afn float @llvm.sqrt.f32(float %x)
ret float %rt ret float %rt
} }
; The call is now fully 'fast'. This implies that approximation is allowed. ; The call is now fully 'fast'. This implies that approximation is allowed.
; FMFDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_fast:' ; FMFDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_fast:'
; FMFDEBUG: fsqrt nnan ninf nsz arcp contract afn reassoc {{t[0-9]+}} ; FMFDEBUG: fmul nnan ninf nsz arcp contract afn reassoc {{t[0-9]+}}
; FMFDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_fast:' ; FMFDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_fast:'
; GLOBALDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_fast:' ; GLOBALDEBUG-LABEL: Optimized lowered selection DAG: %bb.0 'sqrt_fast:'
; GLOBALDEBUG: fmul reassoc {{t[0-9]+}} ; GLOBALDEBUG: fmul nnan ninf nsz arcp contract afn reassoc {{t[0-9]+}}
; GLOBALDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_fast:' ; GLOBALDEBUG: Type-legalized selection DAG: %bb.0 'sqrt_fast:'
define float @sqrt_fast(float %x) { define float @sqrt_fast(float %x) {
; FMF-LABEL: sqrt_fast: ; FMF-LABEL: sqrt_fast:
; FMF: # %bb.0: ; FMF: # %bb.0:
; FMF-NEXT: xssqrtsp 1, 1 ; FMF-NEXT: xxlxor 0, 0, 0
; FMF-NEXT: fcmpu 0, 1, 0
; FMF-NEXT: beq 0, .LBB11_2
; FMF-NEXT: # %bb.1:
; FMF-NEXT: xsrsqrtesp 2, 1
; FMF-NEXT: addis 3, 2, .LCPI11_0@toc@ha
; FMF-NEXT: fneg 0, 1
; FMF-NEXT: fmr 4, 1
; FMF-NEXT: addi 3, 3, .LCPI11_0@toc@l
; FMF-NEXT: lfsx 3, 0, 3
; FMF-NEXT: xsmaddasp 4, 0, 3
; FMF-NEXT: xsmulsp 0, 2, 2
; FMF-NEXT: xsmaddasp 3, 4, 0
; FMF-NEXT: xsmulsp 0, 2, 3
; FMF-NEXT: xsmulsp 0, 0, 1
; FMF-NEXT: .LBB11_2:
; FMF-NEXT: fmr 1, 0
; FMF-NEXT: blr ; FMF-NEXT: blr
; ;
; GLOBAL-LABEL: sqrt_fast: ; GLOBAL-LABEL: sqrt_fast:
; GLOBAL: # %bb.0: ; GLOBAL: # %bb.0:
; GLOBAL-NEXT: xxlxor 0, 0, 0 ; GLOBAL-NEXT: xxlxor 0, 0, 0
; GLOBAL-NEXT: fcmpu 0, 1, 0 ; GLOBAL-NEXT: fcmpu 0, 1, 0
; GLOBAL-NEXT: beq 0, .LBB11_2 ; GLOBAL-NEXT: beq 0, .LBB11_2
; GLOBAL-NEXT: # %bb.1: ; GLOBAL-NEXT: # %bb.1:
; GLOBAL-NEXT: xsrsqrtesp 2, 1 ; GLOBAL-NEXT: xsrsqrtesp 2, 1
▲ Show 20 Lines • Show All 122 Lines • Show Last 20 Lines