Changes between Version 4 and Version 5 of SIMDVectorExampleInLLVM

Timestamp:

10/25/11 11:52:41 (19 months ago)

Author:

pmonday

Comment:

--

SIMDVectorExampleInLLVM

@@ -117 +117 @@
 Here is the .ll code rewritten with vectorization:
 {{{
+; ModuleID = '/tmp/webcompile/_21191_0.bc'
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
+target triple = "x86_64-unknown-linux-gnu"
 
+@.str = private unnamed_addr constant [13 x i8] c"%f %f %f %f\0A\00"
 
+define i32 @main() nounwind {
+  %1 = alloca i32, align 4
+
+  ; allocate three vectors
+  %x = alloca <4 x float>, align 16
+  %y = alloca <4 x float>, align 16
+  %z = alloca <4 x float>, align 16
+
+  store i32 0, i32* %1
+
+  ; store initial values to the x and y vectors
+  %2 = getelementptr inbounds <4 x float>* %x, i32 0, i64 0
+  store float 1.000000e+00, float* %2
+  %3 = getelementptr inbounds <4 x float>* %x, i32 0, i64 1
+  store float 2.000000e+00, float* %3
+  %4 = getelementptr inbounds <4 x float>* %x, i32 0, i64 2
+  store float 3.000000e+00, float* %4
+  %5 = getelementptr inbounds <4 x float>* %x, i32 0, i64 3
+  store float 4.000000e+00, float* %5
+  %6 = getelementptr inbounds <4 x float>* %y, i32 0, i64 0
+  store float 1.000000e+01, float* %6
+  %7 = getelementptr inbounds <4 x float>* %y, i32 0, i64 1
+  store float 2.000000e+01, float* %7
+  %8 = getelementptr inbounds <4 x float>* %y, i32 0, i64 2
+  store float 3.000000e+01, float* %8
+  %9 = getelementptr inbounds <4 x float>* %y, i32 0, i64 3
+  store float 4.000000e+01, float* %9
+
+  ; load the vectors
+  %xs = load <4 x float>* %x
+  %ys = load <4 x float>* %y
+
+  ; add the vectors
+  %zs = fadd <4 x float> %xs, %ys
+
+  ; store the result vector back to z
+  store <4 x float> %zs, <4 x float>* %z
+
+  ; get the elements out of the vector for printing
+  %10 = getelementptr inbounds <4 x float>* %z, i32 0, i64 0
+  %11 = load float* %10
+  %12 = fpext float %11 to double
+  %13 = getelementptr inbounds <4 x float>* %z, i32 0, i64 1
+  %14 = load float* %13
+  %15 = fpext float %14 to double
+  %16 = getelementptr inbounds <4 x float>* %z, i32 0, i64 2
+  %17 = load float* %16
+  %18 = fpext float %17 to double
+  %19 = getelementptr inbounds <4 x float>* %z, i32 0, i64 3
+  %20 = load float* %19
+  %21 = fpext float %20 to double
+
+  ; print the components of z that were extracted above
+  %22 = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([13 x i8]* @.str, i32 0, i32 0), double %12, double %15, double %18, double %21)
+
+  ; return
+  %23 = load i32* %1
+  ret i32 %23
+}
+
+declare i32 @printf(i8*, ...)
 }}}