6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-11-02 22:23:10 +00:00
Code Issues Projects Releases Wiki Activity

Combine fmul vector FP constants when unsafe math is allowed.

Browse Source 
This is an extension of the change made with r215820:
http://llvm.org/viewvc/llvm-project?view=revision&revision=215820

That patch allowed combining of splatted vector FP constants that are multiplied.

This patch allows combining non-uniform vector FP constants too by relaxing the
check on the type of vector. Also, canonicalize a vector fmul in the
same way that we already do for scalars - if only one operand of the fmul is a
constant, make it operand 1. Otherwise, we miss potential folds.

This fold is also done by -instcombine, but it's possible that extra
fmuls may have been generated during lowering.

Differential Revision: http://reviews.llvm.org/D5254



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217599 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Sanjay Patel
2014-09-11 15:45:27 +00:00
parent 338692246d
commit 04bb0e721f
2 changed files with 70 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
test/CodeGen/X86/fmul-combines.ll
View File

@@ -55,6 +55,54 @@ define <4 x float> @fmul_c3_c4_v4f32(<4 x float> %x) #0 {
ret <4 x float> %z
}
; We should be able to pre-multiply the two constant vectors.
; CHECK: ## float 5.000000e+00
; CHECK: ## float 1.200000e+01
; CHECK: ## float 2.100000e+01
; CHECK: ## float 3.200000e+01
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat:
; CHECK: mulps
; CHECK-NOT: mulps
; CHECK-NEXT: ret
define <4 x float> @fmul_v4f32_two_consts_no_splat(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 4.0>
%z = fmul <4 x float> %y, <float 5.0, float 6.0, float 7.0, float 8.0>
ret <4 x float> %z
}
; Same as above, but reverse operands to make sure non-canonical form is also handled.
; CHECK: ## float 5.000000e+00
; CHECK: ## float 1.200000e+01
; CHECK: ## float 2.100000e+01
; CHECK: ## float 3.200000e+01
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat_non_canonical:
; CHECK: mulps
; CHECK-NOT: mulps
; CHECK-NEXT: ret
define <4 x float> @fmul_v4f32_two_consts_no_splat_non_canonical(<4 x float> %x) #0 {
%y = fmul <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
%z = fmul <4 x float> <float 5.0, float 6.0, float 7.0, float 8.0>, %y
ret <4 x float> %z
}
; More than one use of a constant multiply should not inhibit the optimization.
; Instead of a chain of 2 dependent mults, this test will have 2 independent mults.
; CHECK: ## float 5.000000e+00
; CHECK: ## float 1.200000e+01
; CHECK: ## float 2.100000e+01
; CHECK: ## float 3.200000e+01
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat_multiple_use:
; CHECK: mulps
; CHECK: mulps
; CHECK: addps
; CHECK: ret
define <4 x float> @fmul_v4f32_two_consts_no_splat_multiple_use(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 4.0>
%z = fmul <4 x float> %y, <float 5.0, float 6.0, float 7.0, float 8.0>
%a = fadd <4 x float> %y, %z
ret <4 x float> %a
}
; CHECK-LABEL: fmul_c2_c4_f32:
; CHECK-NOT: addss
; CHECK: mulss