search for: then4

...= alloca i32 %zero = alloca i32 %inc = alloca i32 store i32 5, i32* %n store i32 1, i32* %f store i32 1, i32* %i store i32 0 , i32* %zero store i32 1 , i32* %inc %tmp7 = load i32* %n %tmp8 = load i32* %zero %tmp6 = icmp sgt i32 %tmp7, %tmp8 br i1 %tmp6, label %then4, label %else12 then4: %tmp14 = load i32* %i %tmp16 = load i32* %n %tmp18 = load i32* %inc %tmp15 = add i32 %tmp16, %tmp18 %tmp13 = icmp slt i32 %tmp14, %tmp15 br i1 %tmp13, label %then11, label %else12 then11: %tmp20 = load i32* %f %tmp22 = alloca i32 store i32 1...

...%n > > store i32 1, i32* %f > > store i32 1, i32* %i > > store i32 0 , i32* %zero > > store i32 1 , i32* %inc > > > > %tmp7 = load i32* %n > > %tmp8 = load i32* %zero > > %tmp6 = icmp sgt i32 %tmp7, %tmp8 > > br i1 %tmp6, label %then4, label %else12 > > > > then4: > > %tmp14 = load i32* %i > > %tmp16 = load i32* %n > > %tmp18 = load i32* %inc > > %tmp15 = add i32 %tmp16, %tmp18 > > %tmp13 = icmp slt i32 %tmp14, %tmp15 > > br i1 %tmp13, label %then11, label %else12 >...

------------------------------------ IR ------------------------------------------------------------------ if.then.i.i.i.i.i.i: ; preds = %if.then4 %S25_D = zext <2 x i32> %splatLDS17_D.splat to <2 x i64> %umul_with_overflow.i.iS26_D = shl <2 x i64> %S25_D, <i64 3, i64 3> %extumul_with_overflow.i.iS26_D = extractelement <2 x i64> %umul_with_overflow.i.iS26_D, i32 1 %call5.i.i = tail call noalias i8* @_Znam...

...e it could be rewritten in terms of the i8* %call5.i.i and a bitcast. On 07/24/2015 10:52 AM, zhi chen wrote: > ------------------------------------ IR > ------------------------------------------------------------------ > if.then.i.i.i.i.i.i: ; preds = %if.then4 > %S25_D = zext <2 x i32> %splatLDS17_D.splat to <2 x i64> > %umul_with_overflow.i.iS26_D = shl <2 x i64> %S25_D, <i64 3, i64 3> > %extumul_with_overflow.i.iS26_D = extractelement <2 x i64> > %umul_with_overflow.i.iS26_D, i32 1 > %call5.i.i = ta...

On 07/24/2015 03:42 AM, Benjamin Kramer wrote: >> On 24.07.2015, at 08:06, zhi chen <zchenhn at gmail.com> wrote: >> >> It seems that that it's hard to vectorize int64 in LLVM. For example, LLVM 3.4 generates very complicated code for the following IR. I am running on a Haswell processor. Is it because there is no alternative AVX/2 instructions for int64? The same thing

...load i32* %gep3 %cond3 = icmp ugt i32 %val3, 3 br i1 %cond3, label %then3, label %else3, !prof !0 then3: call void @error(i32 %i, i32 1, i32 %b) br label %else3 else3: %gep4 = getelementptr i32* %a, i32 4 %val4 = load i32* %gep4 %cond4 = icmp ugt i32 %val4, 4 br i1 %cond4, label %then4, label %else4, !prof !0 then4: call void @error(i32 %i, i32 1, i32 %b) br label %else4 else4: %gep5 = getelementptr i32* %a, i32 3 %val5 = load i32* %gep5 %cond5 = icmp ugt i32 %val5, 3 br i1 %cond5, label %then5, label %exit, !prof !0 then5: call void @error(i32 %i, i32 1, i32 %b)...

On Tue, Oct 18, 2011 at 6:58 PM, Jakob Stoklund Olesen <stoklund at 2pi.dk>wrote: > > On Oct 18, 2011, at 5:22 PM, Chandler Carruth wrote: > > As for why it should be an IR pass, mostly because once the selection dag >> runs through the code, we can never recover all of the freedom we have at >> the IR level. To start with, splicing MBBs around requires known about

Hi, My pass heavily relies on llvm::Loop's getSmallConstantTripCount method. However, I found that it doesn't work for some simple cases. In the following example, I can get the constant trip count of the outermost loop if statement "a[l] = a[l] + 1" is there. After commenting out this line, the returned constant trip count for that loop is 0. In my pass, I traverse the nested