Changes between Version 3 and Version 4 of SIMDVectorExampleInLLVM

Timestamp:

10/25/11 10:57:14 (19 months ago)

Author:

pmonday

Comment:

--

SIMDVectorExampleInLLVM

@@ -9 +9 @@
 To demonstrate the vector instructions, we can start with a basic C program (just to illustrate ... remember, LLVM is not functional so starting in an imperative language makes a lot of sense):
 {{{
+#include <stdio.h>
+
 int main()
 {
@@ -24 +26 @@
    z[1] = x[1] + y[1]; 
    z[2] = x[2] + y[2]; 
-   z[3] = x[3] + y[3]; 
-} 
+   z[3] = x[3] + y[3];
+   printf("%f %f %f %f\n", z[0], z[1], z[2], z[3]);
+}
 }}}
 
@@ -32 +35 @@
 This converts easily to LLVM human readable format (use the [http://llvm.org/demo/index.cgi online generator] if you'd like):
 {{{
-; ModuleID = '/tmp/webcompile/_20751_0.bc'
+; 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 {
@@ -86 +91 @@
   %33 = getelementptr inbounds [4 x float]* %z, i32 0, i64 3
   store float %32, float* %33
-  %34 = load i32* %1
-  ret i32 %34
+  %34 = getelementptr inbounds [4 x float]* %z, i32 0, i64 0
+  %35 = load float* %34
+  %36 = fpext float %35 to double
+  %37 = getelementptr inbounds [4 x float]* %z, i32 0, i64 1
+  %38 = load float* %37
+  %39 = fpext float %38 to double
+  %40 = getelementptr inbounds [4 x float]* %z, i32 0, i64 2
+  %41 = load float* %40
+  %42 = fpext float %41 to double
+  %43 = getelementptr inbounds [4 x float]* %z, i32 0, i64 3
+  %44 = load float* %43
+  %45 = fpext float %44 to double
+  %46 = call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([13 x i8]* @.str, i32 0, i32 0), double %36, double %39, double %42, double %45)
+  %47 = load i32* %1
+  ret i32 %47
 }
+
+declare i32 @printf(i8*, ...)
 }}}