diff options
| author | Nemanja Ivanovic <nemanja.i.ibm@gmail.com> | 2019-05-07 13:48:03 +0000 |
|---|---|---|
| committer | Nemanja Ivanovic <nemanja.i.ibm@gmail.com> | 2019-05-07 13:48:03 +0000 |
| commit | b4f028f0f3f6c4326ff9ff3c077f71b01d5adc2e (patch) | |
| tree | dc0d51ef3204f44cdf1dec98975ded5442bad306 /llvm/test/CodeGen/PowerPC/fmf-propagation.ll | |
| parent | 5c922f698847a7059e9015dcf73721af3be852a3 (diff) | |
| download | bcm5719-llvm-b4f028f0f3f6c4326ff9ff3c077f71b01d5adc2e.tar.gz bcm5719-llvm-b4f028f0f3f6c4326ff9ff3c077f71b01d5adc2e.zip | |
[PowerPC] Use the two-constant NR algorithm for refining estimates
The single-constant algorithm produces infinities on a lot of denormal values.
The precision of the two-constant algorithm is actually sufficient across the
range of denormals. We will switch to that algorithm for now to avoid the
infinities on denormals. In the future, we will re-evaluate the algorithm to
find the optimal one for PowerPC.
Differential revision: https://reviews.llvm.org/D60037
llvm-svn: 360144
Diffstat (limited to 'llvm/test/CodeGen/PowerPC/fmf-propagation.ll')
| -rw-r--r-- | llvm/test/CodeGen/PowerPC/fmf-propagation.ll | 69 |
1 files changed, 33 insertions, 36 deletions
diff --git a/llvm/test/CodeGen/PowerPC/fmf-propagation.ll b/llvm/test/CodeGen/PowerPC/fmf-propagation.ll index ea40e4edd34..0ce4701d683 100644 --- a/llvm/test/CodeGen/PowerPC/fmf-propagation.ll +++ b/llvm/test/CodeGen/PowerPC/fmf-propagation.ll @@ -284,16 +284,16 @@ define float @sqrt_afn(float %x) { ; FMF-NEXT: fcmpu 0, 1, 0 ; FMF-NEXT: beq 0, .LBB10_2 ; FMF-NEXT: # %bb.1: +; FMF-NEXT: xsrsqrtesp 0, 1 ; FMF-NEXT: addis 3, 2, .LCPI10_0@toc@ha -; FMF-NEXT: xsrsqrtesp 3, 1 -; FMF-NEXT: lfs 0, .LCPI10_0@toc@l(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: addis 4, 2, .LCPI10_1@toc@ha +; FMF-NEXT: lfs 2, .LCPI10_0@toc@l(3) +; FMF-NEXT: lfs 3, .LCPI10_1@toc@l(4) +; FMF-NEXT: xsmulsp 1, 1, 0 +; FMF-NEXT: xsmulsp 0, 1, 0 +; FMF-NEXT: xsmulsp 1, 1, 2 +; FMF-NEXT: xsaddsp 0, 0, 3 +; FMF-NEXT: xsmulsp 0, 1, 0 ; FMF-NEXT: .LBB10_2: ; FMF-NEXT: fmr 1, 0 ; FMF-NEXT: blr @@ -304,16 +304,15 @@ define float @sqrt_afn(float %x) { ; GLOBAL-NEXT: fcmpu 0, 1, 0 ; GLOBAL-NEXT: beq 0, .LBB10_2 ; GLOBAL-NEXT: # %bb.1: -; GLOBAL-NEXT: xsrsqrtesp 2, 1 -; GLOBAL-NEXT: fneg 0, 1 +; GLOBAL-NEXT: xsrsqrtesp 0, 1 ; GLOBAL-NEXT: addis 3, 2, .LCPI10_0@toc@ha -; GLOBAL-NEXT: fmr 4, 1 -; GLOBAL-NEXT: lfs 3, .LCPI10_0@toc@l(3) -; GLOBAL-NEXT: xsmaddasp 4, 0, 3 -; GLOBAL-NEXT: xsmulsp 0, 2, 2 -; GLOBAL-NEXT: xsmaddasp 3, 4, 0 -; GLOBAL-NEXT: xsmulsp 0, 2, 3 -; GLOBAL-NEXT: xsmulsp 0, 0, 1 +; GLOBAL-NEXT: addis 4, 2, .LCPI10_1@toc@ha +; GLOBAL-NEXT: lfs 2, .LCPI10_0@toc@l(3) +; GLOBAL-NEXT: lfs 3, .LCPI10_1@toc@l(4) +; GLOBAL-NEXT: xsmulsp 1, 1, 0 +; GLOBAL-NEXT: xsmaddasp 2, 1, 0 +; GLOBAL-NEXT: xsmulsp 0, 1, 3 +; GLOBAL-NEXT: xsmulsp 0, 0, 2 ; GLOBAL-NEXT: .LBB10_2: ; GLOBAL-NEXT: fmr 1, 0 ; GLOBAL-NEXT: blr @@ -338,16 +337,15 @@ define float @sqrt_fast(float %x) { ; FMF-NEXT: fcmpu 0, 1, 0 ; FMF-NEXT: beq 0, .LBB11_2 ; FMF-NEXT: # %bb.1: -; FMF-NEXT: xsrsqrtesp 2, 1 -; FMF-NEXT: fneg 0, 1 +; FMF-NEXT: xsrsqrtesp 0, 1 ; FMF-NEXT: addis 3, 2, .LCPI11_0@toc@ha -; FMF-NEXT: fmr 4, 1 -; FMF-NEXT: lfs 3, .LCPI11_0@toc@l(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: addis 4, 2, .LCPI11_1@toc@ha +; FMF-NEXT: lfs 2, .LCPI11_0@toc@l(3) +; FMF-NEXT: lfs 3, .LCPI11_1@toc@l(4) +; FMF-NEXT: xsmulsp 1, 1, 0 +; FMF-NEXT: xsmaddasp 2, 1, 0 +; FMF-NEXT: xsmulsp 0, 1, 3 +; FMF-NEXT: xsmulsp 0, 0, 2 ; FMF-NEXT: .LBB11_2: ; FMF-NEXT: fmr 1, 0 ; FMF-NEXT: blr @@ -358,16 +356,15 @@ define float @sqrt_fast(float %x) { ; GLOBAL-NEXT: fcmpu 0, 1, 0 ; GLOBAL-NEXT: beq 0, .LBB11_2 ; GLOBAL-NEXT: # %bb.1: -; GLOBAL-NEXT: xsrsqrtesp 2, 1 -; GLOBAL-NEXT: fneg 0, 1 +; GLOBAL-NEXT: xsrsqrtesp 0, 1 ; GLOBAL-NEXT: addis 3, 2, .LCPI11_0@toc@ha -; GLOBAL-NEXT: fmr 4, 1 -; GLOBAL-NEXT: lfs 3, .LCPI11_0@toc@l(3) -; GLOBAL-NEXT: xsmaddasp 4, 0, 3 -; GLOBAL-NEXT: xsmulsp 0, 2, 2 -; GLOBAL-NEXT: xsmaddasp 3, 4, 0 -; GLOBAL-NEXT: xsmulsp 0, 2, 3 -; GLOBAL-NEXT: xsmulsp 0, 0, 1 +; GLOBAL-NEXT: addis 4, 2, .LCPI11_1@toc@ha +; GLOBAL-NEXT: lfs 2, .LCPI11_0@toc@l(3) +; GLOBAL-NEXT: lfs 3, .LCPI11_1@toc@l(4) +; GLOBAL-NEXT: xsmulsp 1, 1, 0 +; GLOBAL-NEXT: xsmaddasp 2, 1, 0 +; GLOBAL-NEXT: xsmulsp 0, 1, 3 +; GLOBAL-NEXT: xsmulsp 0, 0, 2 ; GLOBAL-NEXT: .LBB11_2: ; GLOBAL-NEXT: fmr 1, 0 ; GLOBAL-NEXT: blr |
